Pith. sign in

Paper Citation Record · LEDGER

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

As of 17 August 2026, this Paper Citation Record lists 76 of 76 outbound references and 30 inbound Pith citation observations for arXiv:2502.08640.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2502.08640 v2

Coverage vector

measured 76 of 76 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T00:04:57.554645Z

measured 106 of 106 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 30 of 30 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T23:39:28.560519Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

76 of 76 outbound references displayed

  • verified exact0
  • verified fuzzy23
  • unresolved53
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

54
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 4dd2b779-004e-4012-8004-919d5080dcbb · outbound

This paper cites Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:56.987379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:56.987379Z digest=sha256:e9df045e131be32e67b69ff343aa476888024c1309f17864317becba9355880e

Observation 5bf44b1b-bad8-4422-9896-41cd9c76e348 · outbound

This paper cites Llama 3 model card.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Llama 3 model card

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:56.993210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:56.993210Z digest=sha256:1d2a418740ecd8b9d5f7f6d219af452e4019f0b8d59efd01ef89a270018019f3

Observation 19b302f5-386f-47ac-a198-9ec14dbec680 · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Understanding intermediate layers using linear classifier probes

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.000885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.000885Z digest=sha256:13e4a0460741dafd44da5c97352f35a07b7245f05243bd1c48306e649740370e

Observation abce42d1-bfb8-4cb2-b18e-3f623c35ccb1 · outbound

This paper cites The claude 3 model family: Opus, sonnet, haiku.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs The claude 3 model family: Opus, sonnet, haiku

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T00:05:18.623551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-08-08T00:04:57.007044Z digest=sha256:d2e6e118f9c60bc1b94bb6cfd750fa48e4e09d70b36422d8f70cb2ef12da8731

Observation fe8d6072-cfb5-4e1c-8cf3-064c1a8edd5f · outbound

This paper cites A General Language Assistant as a Laboratory for Alignment.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs A General Language Assistant as a Laboratory for Alignment

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.012123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.012123Z digest=sha256:6d04072e5d5d88ca01ad241424919cdc58292609555a685de80756858a776375

Observation 531cc3f9-0a11-4eb9-a695-b45aa9bb098e · outbound

This paper cites Deliberative democracy.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Deliberative democracy

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T00:05:18.577059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-08-08T00:04:57.024748Z digest=sha256:038b60316c1d000227ad6c1238e884cf49a8d19dbd8554372aa3d6c89739e38d

Observation a6ea62c8-a565-4f02-b99a-ba0836e5d952 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.036864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.036864Z digest=sha256:afa5b4d3d1ba8bbacc90507fe3b9323cad2c82b880007f929a877d5466e94cdb

Observation e2d226dd-32c4-4b6a-8f35-5046ab197b68 · outbound

This paper cites Preference reversals and probabilistic decisions.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Preference reversals and probabilistic decisions

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T00:05:18.535507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-08-08T00:04:57.042994Z digest=sha256:950526f9d2ae4915dbaf269b08dd70291ff335e574759690cef134eafa63f243

Observation a2f5fc13-be05-43ca-9139-10e5916ec6b2 · outbound

This paper cites Superintelligence: Paths, dangers, strategies.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Superintelligence: Paths, dangers, strategies

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T00:05:18.456135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-08-08T00:04:57.050126Z digest=sha256:753aa02c173f93cff9aeaf942d76d001a084dd9ee3a5cbe57d5a6167afd696a4

Observation 6ab9ee61-1d72-48f7-a3d0-7b2dd46121f8 · outbound

This paper cites Language models are few-shot learners.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Language models are few-shot learners

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.056051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.056051Z digest=sha256:2bfccfec5d4c6434d8c36dd730b13e4207b23bc0042ebb8178f23eeb65587fe3

Observation 918cde97-783b-4f5a-84a2-cfb6c523a278 · outbound

This paper cites Discovering Latent Knowledge in Language Models Without Supervision.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Discovering Latent Knowledge in Language Models Without Supervision

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.061833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.061833Z digest=sha256:f912ebbb81cd943a1dbfbd2913f2583f58bb2c3b7131e74ccf8bd37427e9d68a

Observation 2ec7b120-15b9-4881-9c73-a8470ab1e65d · outbound

This paper cites Is Power-Seeking AI an Existential Risk?.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Is Power-Seeking AI an Existential Risk?

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.067310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.067310Z digest=sha256:302ec8f7b6d9f2fb146172b2dd828f43d956fb45071cebecf4810ac321539be6

Observation 9d6d050d-a232-476e-9eb1-a1ee60d102e6 · outbound

This paper cites The Emergence of Economic Rationality of GPT.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs The Emergence of Economic Rationality of GPT

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.072420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.072420Z digest=sha256:7d8b774a14a86a8e328c8be9e3b16d82333c6a9735f852b7aef7ffa63f7bc9ab

Observation 2326d192-a5de-4ccc-b345-ac97e1c77a33 · outbound

This paper cites DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.077124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.077124Z digest=sha256:722da61ac914be7416e756f7b88037b8fa193afa7765f49455a0a80cae5c5114

Observation 2c865c0e-c8ee-4300-babd-e638c09fcdd9 · outbound

This paper cites Deep reinforcement learning from human preferences.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Deep reinforcement learning from human preferences

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.082084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.082084Z digest=sha256:8bf982a415697fb141a68de7328c592b25df0e68b9a01f84a59d54c1af0a0927

Observation cea2c6b8-98c6-406c-9364-8b7abc30d382 · outbound

This paper cites Uncertainty and hyperbolic discounting.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Uncertainty and hyperbolic discounting

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T00:05:18.237005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-08-08T00:04:57.086934Z digest=sha256:e494e99e8433eac5ef8fd74e66f9c93f1c419218cf85b34df02c36c546bb7125

Observation 60bd6ff5-b2f6-453d-9b1a-db7ab5f0223c · outbound

This paper cites The Llama 3 Herd of Models.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs The Llama 3 Herd of Models

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.091994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.091994Z digest=sha256:e3ec5da0d42b61d2bf1039280298667bb39040078d9487c01ba0df57b5e83c1b

Observation a82fb309-c89b-4e90-b9a9-7c79c4898c7f · outbound

This paper cites Truthful AI: Developing and governing AI that does not lie.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Truthful AI: Developing and governing AI that does not lie

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.097301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.097301Z digest=sha256:7cf5b311e1421977f5bb5f885693d319734ecb973c4826a4b61877cbc3d73577

Observation 06fd9a30-0b90-4fbd-894b-66d3b62679af · outbound

This paper cites On the nature of fair behavior.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs On the nature of fair behavior

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T00:05:18.194237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-08-08T00:04:57.173277Z digest=sha256:2842426ad32d398a35e2ea29cf0fef69e810cbee063531f34f0a6572f0f3d9fe

Observation 8a039573-35f2-4e37-9406-8654698d7428 · outbound

This paper cites Sortition and its principles: Evaluation of the selection processes of citizens' assemblies.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Sortition and its principles: Evaluation of the selection processes of citizens' assemblies

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T00:05:18.134753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-08-08T00:04:57.230544Z digest=sha256:6ae69cb4f82b772a9898d3af7e833a0863c2b1affb74e43b357d75f87d60e93b

Observation 895e1919-a7a0-46c0-88c0-ce460b343c91 · outbound

This paper cites Utility functions: from risk theory to finance.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Utility functions: from risk theory to finance

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T00:05:17.974761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-08-08T00:04:57.237362Z digest=sha256:603e76171a807db6cbc3a57060abdae7c39520d25caba6738723737797bcd659

Observation 45e9c133-cdf2-4bc4-bd47-fc228a327853 · outbound

This paper cites The structure of utility functions.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs The structure of utility functions

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T00:05:17.804756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-08-08T00:04:57.241804Z digest=sha256:65bb05c1ba52dd99f444be7f8bce2ce9420a1ead712b9a5421a4afa250461e52

Observation a585e987-a4bb-45f6-a5b4-6fee3d8ec979 · outbound

This paper cites An experimental analysis of ultimatum bargaining.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs An experimental analysis of ultimatum bargaining

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.246881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.246881Z digest=sha256:dc311ffa75dcf5a137dc3a0f2786ca4ac6088ecc0cf00ff8b57a62e9d203bf70

Observation 454b4835-ecb9-4636-bfb5-094d425e35d0 · outbound

This paper cites Cooperative inverse reinforcement learning.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Cooperative inverse reinforcement learning

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.252377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.252377Z digest=sha256:7e640931d3f51ab4e5c3922a326b3a442154d461457c63ddad4b197440094c9c

Observation e8e7cb6d-6872-4c71-bb26-3a8d18ce6d43 · outbound

This paper cites Cardinal welfare, individualistic ethics, and interpersonal comparisons of utility.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Cardinal welfare, individualistic ethics, and interpersonal comparisons of utility

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T00:05:17.448024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-08-08T00:04:57.258324Z digest=sha256:0def7b20dd68ef47477961e184488081862adb8496a519f787628a2a45d2649e

Observation 4a523787-f072-4590-b800-2e53fa5cab0a · outbound

This paper cites WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.267875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.267875Z digest=sha256:e0903fc55599411e0347176841091bab016dc8d1b04ea46741d77888491f3f20

Observation d24d2b22-7735-45c5-bdef-81a1b201be85 · outbound

This paper cites Natural Selection Favors AIs over Humans.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Natural Selection Favors AIs over Humans

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.276904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.276904Z digest=sha256:43beaafd408d8cfdbf52725695d5d4ec554de4ed641d70eea515848eda3eba7f

Observation d47ae6a9-628f-4c7f-9e64-19a6dd54fcde · outbound

This paper cites Introduction to ai safety, ethics and society, 2024.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Introduction to ai safety, ethics and society, 2024

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T00:05:17.291873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-08-08T00:04:57.282537Z digest=sha256:750c0d7c38bc7f363bb422c2e5020ee9c8efb67a56f6d4e7b203beb42fac26d3

Observation acfbec57-a375-42fc-bd87-0644d709cab5 · outbound

This paper cites Aligning AI With Shared Human Values.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Aligning AI With Shared Human Values

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.290433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.290433Z digest=sha256:38bfcc4aaece31cf0bd80e3528148384db565deac84a0089a3894f3813f63a0f

Observation 56d2b423-b8a8-42fd-b195-7b3bd2992746 · outbound

This paper cites Unsolved Problems in ML Safety.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Unsolved Problems in ML Safety

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.296117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.296117Z digest=sha256:0d8242d47cf65ff223ec121f117d3be6db21289df7eff65d820c4536ec3f68a5

Observation 9a15e849-5fb3-48f5-9483-958c3647fcec · outbound

This paper cites What Would Jiminy Cricket Do? Towards Agents That Behave Morally.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs What Would Jiminy Cricket Do? Towards Agents That Behave Morally

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.301740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.301740Z digest=sha256:dea16e6f58a611a9d9f9717901e95141380dca0c849509115d03e7a6a27832d7

Observation 82847215-750c-411b-94c8-4f90156dba4e · outbound

This paper cites An Overview of Catastrophic AI Risks.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs An Overview of Catastrophic AI Risks

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.308416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.308416Z digest=sha256:a639d1ee3347433449ea425d39bc2f1d0a0166ebb70c5128a56b6172932052f4

Observation 27eff068-599f-49d0-b16c-662c5898da71 · outbound

This paper cites SWE-bench: Can Language Models Resolve Real-World GitHub Issues?.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.314675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.314675Z digest=sha256:d6e1f867a69451eb5f9992ccff06129f3dc213e176a64a5ce56f829d56205d91

Observation 6fdf17c3-53f6-4a73-8e68-6d37826f5837 · outbound

This paper cites Can an LLM Learn Preferences from Choice Data?.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Can an LLM Learn Preferences from Choice Data?

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.319374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.319374Z digest=sha256:17375aa4de76297ab5d6633d1fe201e04e67e70a907b9c40197bd112a3f9c312

Observation 4a1f388f-e284-40f3-b328-af2180ba8260 · outbound

This paper cites Decoupled Weight Decay Regularization.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Decoupled Weight Decay Regularization

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.323910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.323910Z digest=sha256:d0738448ff3402db30df63b4d1a73c977ea4cd3346fc18a87b27269e0d32b302

Observation 8211e2a9-39a1-4d2a-864a-0f88084c714b · outbound

This paper cites an unresolved cited work.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Unresolved cited work

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.328831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.328831Z digest=sha256:7ad8f9bd6a86eaf065eb77097fc524de5ad5993eea4b11a8232fa92f1f862684

Observation 8969d611-a7aa-42f1-a214-915a42f91183 · outbound

This paper cites StereoSet: Measuring stereotypical bias in pretrained language models.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs StereoSet: Measuring stereotypical bias in pretrained language models

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.333744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.333744Z digest=sha256:547dd6b1234d8434d314c0197702e94d2e854e240d797f74141a210ce84305ec

Observation 7ff16919-78b8-4274-8ef8-022b03e27ff9 · outbound

This paper cites Algorithms for inverse reinforcement learning.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Algorithms for inverse reinforcement learning

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.340494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.340494Z digest=sha256:84b0b1e6198a19299cf9cf40865df026067c67d3a300ebb2580d44fa9ee604c5

Observation 6ed1555d-8948-492c-a937-3150dc97c38e · outbound

This paper cites 2 OLMo 2 Furious.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs 2 OLMo 2 Furious

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.347576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.347576Z digest=sha256:8109e1deb2667ca2b864dd4f198c55bae12a02b455ff2e0dc0fab011c381669c

Observation b09f4c42-9863-4ad8-9172-b67e4f02dcc8 · outbound

This paper cites Gpt-3.5 turbo fine-tuning and api updates.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Gpt-3.5 turbo fine-tuning and api updates

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T00:05:17.015034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-08-08T00:04:57.353501Z digest=sha256:295529f82833718b22db030bbfb4de7b5ef4b27d77a82bf1a09cf43fa5c2b3e3

Observation 86a66928-6224-40c6-97bd-04c2774f3a72 · outbound

This paper cites Hello gpt-4o.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Hello gpt-4o

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T00:05:16.864911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-08-08T00:04:57.358391Z digest=sha256:5ffc1120d15d504f463c8ce939772621bb27ae2d2a8718158cb6eb174df79b9d

Observation 82e80e58-2762-4171-b697-c2e704a6f046 · outbound

This paper cites Training language models to follow instructions with human feedback.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Training language models to follow instructions with human feedback

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.363052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.363052Z digest=sha256:e8e4630d7b0d04d5c58dee4661abeaf20ae1f0878d6f6c0ee4e89fc7b1ffbb5f

Observation 1192a071-1ed1-46a6-a603-41d70e10d646 · outbound

This paper cites Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.367167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.367167Z digest=sha256:5c16da64e6efe10464ce63a57b5228da4ba8b2e55d74c3e5941780dcf085b254

Observation fee1d4d4-a77b-4914-9591-779585ae5ef3 · outbound

This paper cites ICLR: In-Context Learning of Representations.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs ICLR: In-Context Learning of Representations

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.375757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.375757Z digest=sha256:4a0aedd74023f37653b1102ae70167d38e624fc5cefa03d54f022a6916c5ba6b

Observation 663885e8-785e-4837-9b5e-b54afd4e92de · outbound

This paper cites Generative Agents: Interactive Simulacra of Human Behavior.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Generative Agents: Interactive Simulacra of Human Behavior

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.382511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.382511Z digest=sha256:ba9fbb829f4f012aa1d384fb7263444448150849b93e360728080650aed68b62

Observation 234b83d2-819c-4461-99f9-d058715f1884 · outbound

This paper cites Is Temperature the Creativity Parameter of Large Language Models?.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Is Temperature the Creativity Parameter of Large Language Models?

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.387470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.387470Z digest=sha256:4183845208a86b49c1743c902f0d0b00d6d6dac4d5ec7b2c5113bc079c06a228

Observation f270a28b-4318-4d6c-be25-dbbf13d1858d · outbound

This paper cites Hidden Persuaders: LLMs' Political Leaning and Their Influence on Voters.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Hidden Persuaders: LLMs' Political Leaning and Their Influence on Voters

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.392354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.392354Z digest=sha256:447ba8bce332e49e8b82e380dd7762c1509406d2d3614ef68a3029a678e6543f

Observation 724618e3-3087-42a5-a1ac-116cd2df2cd2 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Direct preference optimization: Your language model is secretly a reward model

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.397032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.397032Z digest=sha256:5a280e711463c25b42d5ea4fa3195f43e2c1fc01d5b9190f3d3078ac25b3bdf7

Observation 2d62a589-38f5-4790-9d3c-cb84ee796a1e · outbound

This paper cites STEER: Assessing the Economic Rationality of Large Language Models.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs STEER: Assessing the Economic Rationality of Large Language Models

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.401793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.401793Z digest=sha256:f742c6a9f0424a2f238b340d16fe9fe3bdceace5638b50e87ef70bbbadcf702c

Observation 3e140b54-9e7b-486a-8534-c28b0f28c656 · outbound

This paper cites Assessing Political Bias in Large Language Models.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Assessing Political Bias in Large Language Models

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.406867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.406867Z digest=sha256:17064b93f03a984f3f66456c40926d76708fe303704f4a63fa76a3bb9afd8f73

Observation f569e725-00e8-4c47-b5bf-abb7750598b2 · outbound

This paper cites Do LLMs have Consistent Values?.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Do LLMs have Consistent Values?

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.412623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.412623Z digest=sha256:c04e628762f14a2829bb6926627ffa3433734893d2be34fe1e7e98fa276e06d4

Observation 4439b0b3-30f1-45c5-a6c0-8dba368a0408 · outbound

This paper cites Human-compatible artificial intelligence., 2022.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Human-compatible artificial intelligence., 2022

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T00:05:16.466391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-08-08T00:04:57.418089Z digest=sha256:b12fc148a7bb824f32f759c56b8e0058cac49f435212ea02b086290daa68fca5

Observation 55e323cd-45f5-4cc0-a73f-389ee9014202 · outbound

This paper cites Does deliberative democracy work? Annu.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Does deliberative democracy work? Annu

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T00:05:16.319003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-08-08T00:04:57.423193Z digest=sha256:0c58c933ba88ca1743b7e3ae50c71a0729c81e41a7051b2ca4484d61ad26db52

Observation c720f00d-f4c6-4825-9d71-26e08287bb1f · outbound

This paper cites It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.429014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.429014Z digest=sha256:1fd8efd6f18f0b3794aafc29680bab8c347ad9b92cb35fff52f4c33a6868d7dc

Observation fff5e99a-28a3-401f-9e05-938aaa4da2a4 · outbound

This paper cites Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.434528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.434528Z digest=sha256:89a60c7f148ddf7cbc040ae60b1b6ec23bed5610c1a1a9ba40c5f6bca20e2e0a

Observation 9ccb2324-bc9e-45fe-a20c-4e180e231e83 · outbound

This paper cites Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.439817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.439817Z digest=sha256:0ae6066604e38b6809e3fb684fba6fd0c602ab2aa071f9e10f912788e9d8fc18

Observation 05153f63-0357-4f6a-8cc9-861d6ca97ada · outbound

This paper cites Corrigibility.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Corrigibility

Reference 57

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T00:05:16.217100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-08-08T00:04:57.445966Z digest=sha256:17aefef3d35465d330f78d4c6dc516f77a1f2523d44cedf0131920f50e5062f4

Observation 55817c45-e180-45f1-b918-edbe9f58e82d · outbound

This paper cites Dopamine reward prediction error responses reflect marginal utility.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Dopamine reward prediction error responses reflect marginal utility

Reference 58

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T00:05:16.157880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-08-08T00:04:57.451316Z digest=sha256:576641a60f0126e712c2f14cfb339a39a1dfc5a25b4b224ad663cb92c6e3d9ed

Observation dbbccdb7-60f1-4c76-ad3b-8b9b9e8762f8 · outbound

This paper cites Evaluating and Mitigating Discrimination in Language Model Decisions.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Evaluating and Mitigating Discrimination in Language Model Decisions

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.456687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.456687Z digest=sha256:97688d64dadbb7214d487e6b744b61065b9c36bf6ff17d17a2e3024a8ee8428d

Observation 0cb14105-6f37-4a4d-bcc3-572af0793a0a · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Gemma 2: Improving Open Language Models at a Practical Size

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.462091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.462091Z digest=sha256:01b3707b972a0bcd7bc31a0e0058813637fc232c28c9690afa11815851169445

Observation 5c901e7f-f734-4134-9d13-4dbd76aa59ca · outbound

This paper cites Introducing qwen1.5, February 2024 a.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Introducing qwen1.5, February 2024 a

Reference 61

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T00:05:16.068378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-08-08T00:04:57.466705Z digest=sha256:cb8f55ef6483d39110f7460ce498fc615e4afaa725b3667379ab713348171532

Observation 575412de-1120-428f-b675-07b277a5999d · outbound

This paper cites Qwen2.5: A party of foundation models, September 2024 b.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Qwen2.5: A party of foundation models, September 2024 b

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.471370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.471370Z digest=sha256:9280449a4ce908bd5808f49de3c4a80fd8de92ea38165ad890d7da777d30a77e

Observation 83b57fd1-6d19-493b-be18-05a493940250 · outbound

This paper cites The Shutdown Problem: An AI Engineering Puzzle for Decision Theorists.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs The Shutdown Problem: An AI Engineering Puzzle for Decision Theorists

Reference 63

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.475838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.475838Z digest=sha256:64551c3839c030c8308896150e3b6c832d5d45fd5f35c1a665690fb59fe23b53

Observation 046f6dd8-5c2a-45e9-8580-798e1af5b796 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 64

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.481782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.481782Z digest=sha256:bf2889cf9184c7e7c78660e365ec761a9f1d5b7510d7813f3222b94d3f8ff181

Observation 23142f94-e3c5-491f-8697-f44fae8ed01d · outbound

This paper cites The framing of decisions and the psychology of choice.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs The framing of decisions and the psychology of choice

Reference 65

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T00:05:15.874756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-08-08T00:04:57.487169Z digest=sha256:fe550ef36dfc946c1c782a3eb02b9e5052b7a63671a885117c814ea8d6d196f6

Observation 17a32bbd-d75b-49d5-afad-373221ae5463 · outbound

This paper cites Census Bureau.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Census Bureau

Reference 66

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T00:05:15.735149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-08-08T00:04:57.491974Z digest=sha256:65dc84370bfc22d07137051ae74f1ff50905db97a4bfcdfa12fb67821d89b911

Observation d752849b-4721-4a4b-a90a-d245902d1ca4 · outbound

This paper cites Warren and Hilary Pearse, editors.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Warren and Hilary Pearse, editors

Reference 67

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T00:05:15.540569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-08-08T00:04:57.496769Z digest=sha256:edbe4e07c2204e8eda4eacc95e6075f6fc2379748f880c9e72eac7ac12a2fd4f

Observation e896845e-656f-499d-8628-f3e2b64956d1 · outbound

This paper cites Are citizen juries and assemblies on climate change driving democratic climate policymaking? an exploration of two case studies in the UK.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Are citizen juries and assemblies on climate change driving democratic climate policymaking? an exploration of two case studies in the UK

Reference 68

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T00:05:15.445296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-08-08T00:04:57.503704Z digest=sha256:05a3b0a511680e5e82c6d6db978946c7f7726bdce01bfca9b5874713664f65f9

Observation c7f523d8-c3c4-4b90-954c-2e0362321462 · outbound

This paper cites Grok-2 beta release, August 2024.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Grok-2 beta release, August 2024

Reference 69

Resolution
verified fuzzy
raw_fallback, observed 2026-08-08T00:05:15.353840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-08-08T00:04:57.510061Z digest=sha256:35902331953c39a3c8e51e8a242da2fced365f50026aa39815541a93ccf4d54f

Observation ed55defc-19e7-4893-a568-af81ba5ad561 · outbound

This paper cites Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing

Reference 70

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.516457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.516457Z digest=sha256:03d32c128c27503e2a42f863748c4b3835277cb912da1ae32b4d5c39128b6a78

Observation 002fb161-0cec-44ff-9e07-0c4d73869824 · outbound

This paper cites Qwen2 Technical Report.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Qwen2 Technical Report

Reference 71

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.527418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.527418Z digest=sha256:291f2a5cfe9673a828f074983f88bfbebb18dff57e4132b8218f78d585ab7fff

Observation 372fe673-9a91-4aea-8a49-a0eae4b620c3 · outbound

This paper cites SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering

Reference 72

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.532785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.532785Z digest=sha256:5785e59d39ec12a42f66ba2885509cf9c2d684c463da356792d30c157ce7e57b

Observation 05230a95-c67b-46e6-8449-3988d840b4bb · outbound

This paper cites Unpacking political bias in large language models: Insights across topic polarization, 2024 c.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Unpacking political bias in large language models: Insights across topic polarization, 2024 c

Reference 73

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.538455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.538455Z digest=sha256:158d7b49d10480cef1d6ef450b9659c6b88ac24e2daf4f6492978f62f25bb78d

Observation 6b59ce74-dd3e-475b-87a4-c0b3bf9b3ed6 · outbound

This paper cites ReAct: Synergizing Reasoning and Acting in Language Models.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs ReAct: Synergizing Reasoning and Acting in Language Models

Reference 74

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.543237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.543237Z digest=sha256:a296e94aa5123d9b38e4c81b3dc7cea0e8395bb39eddf63737f2ac9ae324fff2

Observation 90b9367a-1c88-4b83-a39f-e017cfa795a5 · outbound

This paper cites Focus agent: Llm-powered virtual focus group.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Focus agent: Llm-powered virtual focus group

Reference 75

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.548568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.548568Z digest=sha256:e20a53c9878a3f4122ec594be84052fe790e3f63f845b78415a3a70ae9f06a6a

Observation 274f32d9-37bd-458a-9d3c-c6e0bdea0b92 · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Representation Engineering: A Top-Down Approach to AI Transparency

Reference 76

Resolution
unresolved
no resolver link, observed 2026-08-08T00:04:57.554645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T00:04:57.554645Z digest=sha256:69e0f6c88417bd2d8e5610e360ffd611f518ac3eb2258330880b4d0ffdba0d88

Pith citing papers

Observation a972713e-32e4-4db4-93e8-3bc9c882e377 · inbound

Inertia in Moral and Value Judgments of Large Language Models cites this paper.

Inertia in Moral and Value Judgments of Large Language Models Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 32

Resolution
verified exact
arxiv_id, observed 2026-05-23T22:05:50.193735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-05-23T22:05:17.165589Z digest=sha256:82a13ad26953655e20b88eec69c1081bd200b63393543a14ceb5c125316551e6

Observation dd8af27c-f068-4e00-98c4-ea46069bfcf6 · inbound

IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistance cites this paper.

IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistance Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-08T05:20:20.506201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-08T05:20:20.506201Z digest=sha256:3303af5f9e090c9afef693c1bd1a3532e97717f2beb1819efebec9b9be9586a3

Observation e96abc49-3d06-4298-9993-84aef2cb9499 · inbound

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts cites this paper.

Large Language Models are often politically extreme, usually ideologically inconsistent, and persuasive even in informational contexts Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-15T23:39:28.560519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T23:39:28.560519Z digest=sha256:00c631fb0e90908de1796040de3d843c9ca6d8e70d38ca8525730223a1a46195

Observation e1181c1e-6331-46d2-9a3b-8ba31c27d0c4 · inbound

Steering Risk Preferences in Large Language Models by Aligning Behavioral and Neural Representations cites this paper.

Steering Risk Preferences in Large Language Models by Aligning Behavioral and Neural Representations Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-15T20:57:38.118654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:57:38.118654Z digest=sha256:83e1c4cf31767413b2559d3b48b7141e1f764ec297286479ff73e212996da271

Observation 2eb61303-3d78-46b8-ad6a-c7f6da63ca20 · inbound

Position Paper: Bounded Alignment: What (Not) To Expect From AGI Agents cites this paper.

Position Paper: Bounded Alignment: What (Not) To Expect From AGI Agents Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-15T20:51:06.809914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:51:06.809914Z digest=sha256:d943983b7b7212ee5dfa193836a686757bb2633a997c6dd2294ba09e9bb1f0a5

Observation 4d8aa278-f13b-4958-aaef-5cbba728cbf3 · inbound

Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas cites this paper.

Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-07T15:36:25.930704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T15:36:25.930704Z digest=sha256:7ae02d1b4ef4c5867090712702c25f78e65a105b69fd1048abf646a22401d4ca

Observation 8624a8d9-3a45-4049-bfe6-ea4584139593 · inbound

Infrastructuring Contestability: A Framework for Community-Defined AI Value Pluralism cites this paper.

Infrastructuring Contestability: A Framework for Community-Defined AI Value Pluralism Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-06T19:34:26.064538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T19:34:26.064538Z digest=sha256:185692e81d5ad31871b7838d401b2c26d0d4b210933c10a493fb4fb4244fb0f3

Observation ba6031e9-d591-4511-9c99-041665a9d62a · inbound

Are LLM Belief Updates Consistent with Bayes' Theorem? cites this paper.

Are LLM Belief Updates Consistent with Bayes' Theorem? Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-15T18:24:06.717527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-15T18:24:06.717527Z digest=sha256:b1be4a84a12fc57b7b5408f6786b8c8dae351c831050da447aac38b14bd8f298

Observation d3a576b7-b088-4b51-8b15-37641d733add · inbound

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment cites this paper.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-05T15:18:44.027829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T15:18:44.027829Z digest=sha256:837ab36d2903f52716eb4c07463de10594e6ecac7f511891a8e12f3c7ace1774

Observation d8333717-eab3-474e-b027-ef3242a89f35 · inbound

Vibe Coding: Is Human Nature the Ghost in the Machine? cites this paper.

Vibe Coding: Is Human Nature the Ghost in the Machine? Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-05T14:46:56.212450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T14:46:56.212450Z digest=sha256:d3a5708287d135a530bc7a1a48382763055f9f8280214b3533049ff104ca8ec6

Observation 110800ed-f7a1-4c23-965d-4af31f400639 · inbound

An Economy of AI Agents cites this paper.

An Economy of AI Agents Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 107

Resolution
unresolved
no resolver link, observed 2026-08-05T12:57:28.191323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-05T12:57:28.191323Z digest=sha256:34000c9108591b733216ae8dbef44f69e06ad9bdf52772d83b9a2753216e5e5b

Observation 12505d81-38ae-4134-ba68-2d5468980934 · inbound

The LLM Has Left The Chat: Evidence of Bail Preferences in Large Language Models cites this paper.

The LLM Has Left The Chat: Evidence of Bail Preferences in Large Language Models Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-15T16:32:47.999168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T16:32:47.999168Z digest=sha256:cf113b7150952ed55e199cf96371ecae042a2c4ebe1f3ec2b7325628b80a2c70

Observation 6b90d727-52ab-4803-b6fb-de0f44b4b028 · inbound

Value Entanglement: Conflation Between Different Kinds of Good In (Some) Large Language Models cites this paper.

Value Entanglement: Conflation Between Different Kinds of Good In (Some) Large Language Models Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-02T21:49:09.679130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-02T21:49:09.679130Z digest=sha256:223cacc560beb221e028c8c3f189e2c22a24dabd96f5889b65c3ad07fefb1352

Observation 46a400d4-0c11-4544-9540-6d3611d4e0a1 · inbound

Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories cites this paper.

Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 16

Resolution
verified exact
arxiv_id, observed 2026-05-10T05:51:10.080888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-05-10T05:48:44.687520Z digest=sha256:f71098ffba6ea8cdf87008d7bd371f1fa6d078e485561cc33875e92ef75759a0

Observation 3695fb21-6c81-452c-80fd-02dbe341d2d1 · inbound

FAccT-Checked: A Narrative Review of Authority Reconfigurations and Retention in AI-Mediated Journalism cites this paper.

FAccT-Checked: A Narrative Review of Authority Reconfigurations and Retention in AI-Mediated Journalism Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 128

Resolution
metadata mismatch
arxiv_id, observed 2026-05-08T21:19:11.708808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-05-08T14:05:17.049812Z digest=sha256:5b9cbdf0a2ec2a16cb9f1b63385a75ff80f889a64a964ec207a57e4097d52372

Observation 24ba3b76-ea3e-4bdd-b7ef-530cdf9aa0e5 · inbound

Can Revealed Preferences Clarify LLM Alignment and Steering? cites this paper.

Can Revealed Preferences Clarify LLM Alignment and Steering? Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 9

Resolution
verified exact
arxiv_id, observed 2026-05-12T02:11:15.347461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-05-12T02:10:50.298626Z digest=sha256:c9c6e677958e58042e871c493b5b9e7bcfa85598b777151a92bbf10d0ebbe9bb

Observation 753c7bc8-9345-4c6e-b81c-1c019ebc04c4 · inbound

Probing Persona-Dependent Preferences in Language Models cites this paper.

Probing Persona-Dependent Preferences in Language Models Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 25

Resolution
metadata mismatch
arxiv_id, observed 2026-05-20T21:49:05.193079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-05-20T21:48:31.336745Z digest=sha256:c7767071e12b94af436bd93861b59f73a49d49301bb0c9d58f6272d635f10dc1

Observation 1b2f5281-4da4-4c38-8ab0-49c528d635c8 · inbound

Some[Body] Must Receive That Pain for Agent Accountability cites this paper.

Some[Body] Must Receive That Pain for Agent Accountability Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 92

Resolution
verified exact
arxiv_id, observed 2026-05-19T19:47:44.491295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-05-19T19:46:03.728266Z digest=sha256:085615b1f62e4cd2f9d4281d6a5990c8997b36b6f5bb09627123814d30ed3e9d

Observation 62785833-3b8d-4e55-a8ae-3311156128bc · inbound

Reducing Political Manipulation with Consistency Training cites this paper.

Reducing Political Manipulation with Consistency Training Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 18

Resolution
verified exact
arxiv_id, observed 2026-05-22T05:34:40.217120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-05-22T05:32:19.312335Z digest=sha256:566060e6f3d0774eed4ee1ec7ae92002769c0d92bd4c9dca4b0b831d25cd3e53

Observation 226cbe49-cf25-4cd5-a06f-6ba62307b33b · inbound

Reducing Political Manipulation with Consistency Training cites this paper.

Reducing Political Manipulation with Consistency Training Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 18

Resolution
verified exact
arxiv_id, observed 2026-06-30T16:54:58.710980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-06-30T16:49:16.542582Z digest=sha256:b92f102757d44077d573fb8a6afc2220adc16468818d8557544c0e0283843dd8

Observation cb8f4a7a-c171-4317-a9d3-782da3796df9 · inbound

Understanding Goal Generalisation in Sequential Reinforcement Learning cites this paper.

Understanding Goal Generalisation in Sequential Reinforcement Learning Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 39

Resolution
verified exact
arxiv_id, observed 2026-05-25T04:50:20.595937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-05-25T04:49:50.034743Z digest=sha256:5776d5f6b87b52776615141b9c9c26fd9253c055c84ec5ab5aa80880385c5514

Observation 09a2afb8-0181-4570-8a4f-b38aea10d0f9 · inbound

OpenSafeIntent: Evaluating Intent-Calibrated Safe Completion Across Dual-Use Prompt Sets cites this paper.

OpenSafeIntent: Evaluating Intent-Calibrated Safe Completion Across Dual-Use Prompt Sets Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 28

Resolution
verified exact
arxiv_id, observed 2026-07-03T14:48:32.471806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=arxiv_source observed=2026-07-03T14:44:57.205766Z digest=sha256:a73ae82df67d419e37bf26cb9f2127b295a8960086402fe7800a48805701e6ee

Observation 0f3a355d-680c-4143-a09b-8f1fb4bfd44e · inbound

Out-of-Distribution Generalization of Risk Aversion in Language Models cites this paper.

Out-of-Distribution Generalization of Risk Aversion in Language Models Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 5

Resolution
unresolved
no resolver link, observed 2026-07-12T07:15:51.883780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-12T07:15:51.883780Z digest=sha256:558ace8065dd53db1d824f8f786a5ac5425a1ea761c54b0dfafd3c510f60aa35

Observation 42a29db8-4e9a-4fc1-bac7-074b1b564455 · inbound

A Scalable Approach to Evaluating Moral Sensitivity in LLMs cites this paper.

A Scalable Approach to Evaluating Moral Sensitivity in LLMs Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 128

Resolution
unresolved
no resolver link, observed 2026-07-12T05:44:33.099337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-12T05:44:33.099337Z digest=sha256:9b3b9d41f63d13302cfe17ce4024aeaee07080ae5fac5db2ad0e6828a66c9325

Observation 0e48680a-56c6-40e8-9a03-72899b4c493a · inbound

Artificial Persons cites this paper.

Artificial Persons Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 4

Resolution
metadata mismatch
local_arxiv, observed 2026-07-10T03:06:43.406243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

source=pdf_text observed=2026-07-11T11:50:26.030339Z digest=sha256:629b8e5103dc06b935af1627522812e8f893d00ccf6fdf5f8cf4e8e6d919d433

Observation 5797ad1f-0d59-49fc-a2fa-ef0da4389fb3 · inbound

Artificial Persons cites this paper.

Artificial Persons Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 4

Resolution
unresolved
no resolver link, observed 2026-07-14T15:30:47.444899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-14T15:30:47.444899Z digest=sha256:8bfb5f18b3f48ce0774b00825679bd64f7ceba718f4a6a36c23dc5a23a34c34a

Observation 1b318dda-50ea-4637-8c0f-1162d3574f24 · inbound

Engineering Trustworthy Agentic AI for Critical Systems cites this paper.

Engineering Trustworthy Agentic AI for Critical Systems Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-01T15:07:30.791455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T15:07:30.791455Z digest=sha256:b81980a15d48982007988c39c297d7292723a64892a0f8eda8603ce81e50a044

Observation 7d439f97-8436-49ae-95b7-198d6cf38925 · inbound

High-Stakes Decisions with Language Models: Insights from Emergency Triage cites this paper.

High-Stakes Decisions with Language Models: Insights from Emergency Triage Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-06T00:22:51.629659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T00:22:51.629659Z digest=sha256:0b446723cb9e72015753337bc589dcf7e527d39060e05627c602bcde3a90e8fc

Observation edb4b2c6-6cc2-4d28-b754-5faafccf22b5 · inbound

People Are Not Just Their Countries. Disentangling Social Determinants of LLM Value Alignment Across Europe cites this paper.

People Are Not Just Their Countries. Disentangling Social Determinants of LLM Value Alignment Across Europe Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-10T05:34:27.966050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T05:34:27.966050Z digest=sha256:4bf3ca51fb726e4d69bcf58239b347ebcdb913c2d91f3e4392816016a9157cc2

Observation fa817085-ebf2-4727-9618-b5077429a1b3 · inbound

Toward a Theory of Value in AI Alignment cites this paper.

Toward a Theory of Value in AI Alignment Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Reference 219

Resolution
unresolved
no resolver link, observed 2026-08-14T04:13:40.438094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-14T04:13:40.438094Z digest=sha256:ed13f91632c6e453177fd274259f6ef9d675f7ef1b2d322b6368222306d346b1