Paper Citation Record · LEDGER

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

As of 22 August 2026, this Paper Citation Record lists 70 of 70 outbound references and 18 inbound Pith citation observations for arXiv:2501.09620.

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

pith.paper-citation-record.v1
2501.09620 v2

Coverage vector

measured 70 of 70 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T19:55:50.816995Z

measured 88 of 88 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 18 of 18 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T14:57:53.946749Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T01:37:30.312996Z

Reference resolution

70 of 70 outbound references displayed

verified exact4
verified fuzzy13
unresolved53
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3a6c421a-c83d-4302-85ea-1f24dc104656 · outbound

This paper cites write newline.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.441701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38b2f93b-ab11-4cdf-9c78-7431c1d62087 · outbound

This paper cites @esa (Ref.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment @esa (Ref

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.450259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82ee2420-aa68-4854-95aa-eb33d8d6a67b · outbound

This paper cites an unresolved cited work.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.456732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63dbe0ca-683c-4034-b2d3-42bb3ea68842 · outbound

This paper cites an unresolved cited work.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-10T19:55:52.099876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8d920591-75fd-4083-9629-c344ede01d84 · outbound

This paper cites Maximum a Posteriori Policy Optimisation.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Maximum a Posteriori Policy Optimisation

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.469992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77dd62a2-c20a-4a1d-a003-6ceb872ac68b · outbound

This paper cites BiasDPO: Mitigating Bias in Language Models through Direct Preference Optimization.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment BiasDPO: Mitigating Bias in Language Models through Direct Preference Optimization

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.475790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b5a344f-138c-4e2f-9a6d-51e9b53018d3 · outbound

This paper cites Concrete Problems in AI Safety.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Concrete Problems in AI Safety

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.481808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e88b23e9-baaa-4345-a6a3-3101215e6698 · outbound

This paper cites Foundational Challenges in Assuring Alignment and Safety of Large Language Models.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.488108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2540dc7-257e-45ac-b316-c2ab19d2dae7 · outbound

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

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.494311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90dd914a-fa80-4438-866d-65a00fbd5eae · outbound

This paper cites Language models are few-shot learners.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Language models are few-shot learners

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:55:52.083876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 769e38ec-1831-4bfe-a1e9-89e1706b2c4f · outbound

This paper cites Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.506817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c15d8687-b085-4eab-a787-d23bd899b104 · outbound

This paper cites ODIN: Disentangled Reward Mitigates Hacking in RLHF.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment ODIN: Disentangled Reward Mitigates Hacking in RLHF

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.512927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46408abd-c50f-4c06-a372-618b79890ef3 · outbound

This paper cites MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.518773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6244ab2f-b6b6-4069-a198-a47a7d4a8d81 · outbound

This paper cites SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.524544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28c74b67-2321-4a39-b155-cd3080f3a81a · outbound

This paper cites AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.530651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cff7834-fa54-4946-a4d0-037075d1eb66 · outbound

This paper cites Safe reinforcement learning via hierarchical adaptive chance-constraint safeguards.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Safe reinforcement learning via hierarchical adaptive chance-constraint safeguards

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:55:52.067315Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation cc70e555-6f66-4030-95a2-4bc0fe774036 · outbound

This paper cites Autoprm: Automating procedural supervision for multi-step reasoning via controllable question decomposition.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Autoprm: Automating procedural supervision for multi-step reasoning via controllable question decomposition

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:55:52.050547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6dd8f194-7b4b-4765-956a-db6620ff9bdd · outbound

This paper cites Deep reinforcement learning from human preferences.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Deep reinforcement learning from human preferences

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.554122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3404ba26-329b-4d9c-837a-3c7f7aaaffc3 · outbound

This paper cites Reward Model Ensembles Help Mitigate Overoptimization.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Reward Model Ensembles Help Mitigate Overoptimization

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.559707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d14dcc32-55e8-4f20-a704-2ab909e015c6 · outbound

This paper cites Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.565621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d999c63-65f3-4590-8f6b-99196f291410 · outbound

This paper cites The Llama 3 Herd of Models.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment The Llama 3 Herd of Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.571884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7338bc79-c272-42ac-9bb1-8b5b832eedf0 · outbound

This paper cites Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.576818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1ba73f6-2bdd-49da-af6a-727bb0eb8a0e · outbound

This paper cites Alpacafarm: A simulation framework for methods that learn from human feedback.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Alpacafarm: A simulation framework for methods that learn from human feedback

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:55:52.023222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 89e1677c-5e42-42ec-bb3a-0f46186df670 · outbound

This paper cites Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.588363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34bfadea-eeeb-4c28-8695-0a95bc61f0eb · outbound

This paper cites Reward tampering problems and solutions in reinforcement learning: A causal influence diagram perspective.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Reward tampering problems and solutions in reinforcement learning: A causal influence diagram perspective

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:55:52.006833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a9433bc1-9081-4d35-9c8c-bc664127606c · outbound

This paper cites Shortcut learning in deep neural networks.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Shortcut learning in deep neural networks

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.598702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbf7c90a-8834-46dc-9ac9-af313b313a79 · outbound

This paper cites Neural networks and the bias/variance dilemma.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Neural networks and the bias/variance dilemma

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:55:51.979172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1deb7543-d357-474e-bfd5-f1cc5cfabb73 · outbound

This paper cites A kernel two-sample test.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment A kernel two-sample test

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.607999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d398aafd-8526-41b6-987f-44d8bb9e7caa · outbound

This paper cites Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:55:51.951609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation cfff32fc-e56d-40b0-8ce9-264e346a4371 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment LoRA: Low-Rank Adaptation of Large Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.618160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e41ad49a-c8ed-4369-ad34-bb25b2c6aecf · outbound

This paper cites OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.623157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17741692-7502-49f9-89e7-24b3d285c676 · outbound

This paper cites Post-hoc reward calibration: A case study on length bias.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Post-hoc reward calibration: A case study on length bias

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.628206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc78dde2-7e0f-4400-bfec-fde963f7e795 · outbound

This paper cites Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.632894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d568f85-6c94-4e6a-b226-9166371c21e7 · outbound

This paper cites A survey of reinforcement learning from human feedback.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment A survey of reinforcement learning from human feedback

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.638057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a70a8d1-eb70-4760-aa90-fb1f2a78ec92 · outbound

This paper cites Learning deep kernels for non-parametric two-sample tests.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Learning deep kernels for non-parametric two-sample tests

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:55:51.935036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 858d4867-4002-40b7-af1b-531e7e2fa7d3 · outbound

This paper cites The flan collection: Designing data and methods for effective instruction tuning.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment The flan collection: Designing data and methods for effective instruction tuning

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:55:51.918390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2047617a-d80c-4de2-92ef-cb094551dda8 · outbound

This paper cites Learning word vectors for sentiment analysis.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Learning word vectors for sentiment analysis

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.652035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ac9bc59-1cd3-4dc9-b197-dc3518ab9b47 · outbound

This paper cites Selection Bias Induced Spurious Correlations in Large Language Models.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Selection Bias Induced Spurious Correlations in Large Language Models

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-08-10T19:55:51.239262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c21f253c-5104-420d-86da-2cc3ba9f3680 · outbound

This paper cites Human-level control through deep reinforcement learning.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Human-level control through deep reinforcement learning

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.661541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbe20df6-8fda-4895-b674-164c01b6e758 · outbound

This paper cites Confronting Reward Model Overoptimization with Constrained RLHF.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Confronting Reward Model Overoptimization with Constrained RLHF

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.666316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd23faf4-4584-414f-a82c-f4b61699f793 · outbound

This paper cites Understanding the Failure Modes of Out-of-Distribution Generalization.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Understanding the Failure Modes of Out-of-Distribution Generalization

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.671247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a65dd5ed-6ebf-4b3a-99a9-bace86b688ce · outbound

This paper cites GPT -4 technical report, 2023.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment GPT -4 technical report, 2023

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:55:51.875257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0833cf30-9ae1-4ac7-8acd-87ebe0c21a76 · outbound

This paper cites an unresolved cited work.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Unresolved cited work

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.680873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 932b32c1-dc43-4b34-a1c5-07d554322208 · outbound

This paper cites The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.685830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ed95578-aa42-4051-afbe-d7589554ecf2 · outbound

This paper cites Discovering Language Model Behaviors with Model-Written Evaluations.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Discovering Language Model Behaviors with Model-Written Evaluations

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.691103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50ffadf8-a737-471c-9530-de0293a994cf · outbound

This paper cites Quantifying Generalization Complexity for Large Language Models.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Quantifying Generalization Complexity for Large Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.696642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69b90a22-bfcb-4f7c-824f-caadc3693d20 · outbound

This paper cites Learning Counterfactually Invariant Predictors.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Learning Counterfactually Invariant Predictors

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-08-10T19:55:51.137086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0cc014de-00bb-47ba-90f6-8da9e69882ea · outbound

This paper cites WARM: On the Benefits of Weight Averaged Reward Models.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment WARM: On the Benefits of Weight Averaged Reward Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.707005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee3b711b-9044-4903-b495-354df54afd59 · outbound

This paper cites When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.712217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 009dd6da-996c-469c-bb53-e8c79b2328ac · outbound

This paper cites why should i trust you?.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment why should i trust you?

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.717585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2be3743c-59f0-4871-b68b-dedf19916374 · outbound

This paper cites The unequal opportunities of large language models: Examining demographic biases in job recommendations by chatgpt and llama.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment The unequal opportunities of large language models: Examining demographic biases in job recommendations by chatgpt and llama

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:55:51.837589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b3f05908-d960-4fd7-94c9-b243523cc1c9 · outbound

This paper cites Trust Region Policy Optimization.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Trust Region Policy Optimization

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.727156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 269aeae3-1825-4c3b-9bb2-c283ee0a828a · outbound

This paper cites Proximal Policy Optimization Algorithms.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Proximal Policy Optimization Algorithms

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.732285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b82dd49e-e50e-46c1-9825-f29f98496273 · outbound

This paper cites Towards Understanding Sycophancy in Language Models.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Towards Understanding Sycophancy in Language Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.737082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f3b8895-aa70-41ab-a6f6-33d222789660 · outbound

This paper cites Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.742656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d594349-e429-4e62-a5f7-ff968947da6e · outbound

This paper cites A Long Way to Go: Investigating Length Correlations in RLHF.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment A Long Way to Go: Investigating Length Correlations in RLHF

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.747644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fd0adb2-76ca-4158-9e6a-3fa3ef21be1b · outbound

This paper cites Length bias in Encoder Decoder Models and a Case for Global Conditioning.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Length bias in Encoder Decoder Models and a Case for Global Conditioning

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-08-10T19:55:51.000468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1ba22360-6a4c-4e71-9329-f12a59134437 · outbound

This paper cites Learning to summarize from human feedback.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Learning to summarize from human feedback

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.757716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ba12e12-63c1-4a06-ac77-e9e2c2d650ac · outbound

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

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Evaluating and Mitigating Discrimination in Language Model Decisions

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.762598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93758d4f-2e7b-4759-8d3b-c2f0be987a06 · outbound

This paper cites Minimax estimation of maximum mean discrepancy with radial kernels.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Minimax estimation of maximum mean discrepancy with radial kernels

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.767422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51606330-7cbb-4b6b-b647-d4c6a93075b4 · outbound

This paper cites Counterfactual invariance to spurious correlations in text classification.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Counterfactual invariance to spurious correlations in text classification

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:55:51.809403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 17a0ddab-9425-4747-922f-b6e90b486444 · outbound

This paper cites Preference Optimization with Multi-Sample Comparisons.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Preference Optimization with Multi-Sample Comparisons

Reference 62

Resolution: verified exact; local_arxiv, observed 2026-08-10T19:55:50.944111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6bfcad3d-662c-401d-a3df-ce6194fb54ba · outbound

This paper cites Reward Hacking in Reinforcement Learning , 11 2024.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Reward Hacking in Reinforcement Learning , 11 2024

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:55:51.791895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 23cf8539-7052-461b-966c-6ec7be5df0a5 · outbound

This paper cites Detecting Machine-Generated Texts by Multi-Population Aware Optimization for Maximum Mean Discrepancy.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Detecting Machine-Generated Texts by Multi-Population Aware Optimization for Maximum Mean Discrepancy

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.786867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b68ea24-ad1f-4bd3-b7e7-2431f6fb10cb · outbound

This paper cites Character-level convolutional networks for text classification.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Character-level convolutional networks for text classification

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.792052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d92e50b6-da95-4b76-a598-0a96b768e662 · outbound

This paper cites GRAPE: Generalizing Robot Policy via Preference Alignment.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment GRAPE: Generalizing Robot Policy via Preference Alignment

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.796899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7d5a7b0-3972-49ef-ab98-408310fb65e8 · outbound

This paper cites Judging llm-as-a-judge with mt-bench and chatbot arena.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Judging llm-as-a-judge with mt-bench and chatbot arena

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.801859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ad59a22-7b4e-4f63-aea7-0ffdbb5787cf · outbound

This paper cites LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.806681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fada9a1-8fd4-4eda-854d-45d8663a82c9 · outbound

This paper cites Explore Spurious Correlations at the Concept Level in Language Models for Text Classification.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Explore Spurious Correlations at the Concept Level in Language Models for Text Classification

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.812045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21d068e7-08ab-4d97-9bf7-ef9a775ddd34 · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment Fine-Tuning Language Models from Human Preferences

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-10T19:55:50.816995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation e1116a38-d5a5-4fda-93dd-2bd5414ad7a1 · inbound

GRAPE: Generalizing Robot Policy via Preference Alignment cites this paper.

GRAPE: Generalizing Robot Policy via Preference Alignment Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-12T10:23:15.764291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a272143-534e-48a8-8fcd-3a0e9f42ce18 · inbound

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective cites this paper.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T12:16:17.355112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f6c9ef9-e9d4-4d1b-8d73-7571e98f163e · inbound

Improving LLM Reasoning for Vulnerability Detection via Group Relative Policy Optimization cites this paper.

Improving LLM Reasoning for Vulnerability Detection via Group Relative Policy Optimization Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T20:32:47.849443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 666bbd5d-4176-40a4-904b-9923fbbc7e61 · inbound

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary cites this paper.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:32.462708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5f310af-a24e-4a49-bc3c-7c61467b464f · inbound

Token-Level LLM Collaboration via FusionRoute cites this paper.

Token-Level LLM Collaboration via FusionRoute Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-22T12:26:31.463111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1652529e-63d4-48c6-b9f1-18c2e2152821 · inbound

Factored Causal Representation Learning for Robust Reward Modeling in RLHF cites this paper.

Factored Causal Representation Learning for Robust Reward Modeling in RLHF Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

Reference 30

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T14:20:13.610834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 179f691f-920f-4e6c-940f-1558f0e63770 · inbound

Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning cites this paper.

Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T07:22:31.155448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation cfc6e527-9550-452b-97d5-ed00910a49c1 · inbound

Robust Reward Modeling for Large Language Models via Causal Decomposition cites this paper.

Robust Reward Modeling for Large Language Models via Causal Decomposition Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-10T14:00:29.618255Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 13eda639-c3b6-4123-b9ec-b038e7e81e47 · inbound

Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders cites this paper.

Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

Reference 37

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T22:49:10.189118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e9c2965c-b75e-43b0-9ebb-2b896aa8d476 · inbound

General Preference Reinforcement Learning cites this paper.

General Preference Reinforcement Learning Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

Reference 50

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T12:48:17.738781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2cb5d842-b19a-408f-ae1c-5c2321cf1067 · inbound

General Preference Reinforcement Learning cites this paper.

General Preference Reinforcement Learning Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

Reference 50

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T07:54:02.919308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6141da83-70ab-495c-873f-1f9cadf5b143 · inbound

General Preference Reinforcement Learning cites this paper.

General Preference Reinforcement Learning Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

Reference 50

Resolution: metadata mismatch; arxiv_id, observed 2026-05-22T09:24:45.673645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1e74ceca-1986-4219-9dab-cf06241319fe · inbound

Causality as the Statistical Conscience of Artificial Intelligence: From Pearl's Ladder to Trustworthy Machines cites this paper.

Causality as the Statistical Conscience of Artificial Intelligence: From Pearl's Ladder to Trustworthy Machines Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T15:14:47.427916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation bcaadb17-13e9-4e69-b5b7-dd25a1675cfd · inbound

Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure cites this paper.

Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

Reference 85

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T12:23:24.235837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 187781a2-cf6c-4319-a5dc-22d5ffae41ed · inbound

Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization cites this paper.

Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

Reference 135

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T01:37:30.314429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0112c743-f68e-4928-a191-06466a8189c1 · inbound

Style over Substance: A Shortcut Audit of Emotion-Description Preference Evaluation cites this paper.

Style over Substance: A Shortcut Audit of Emotion-Description Preference Evaluation Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T15:17:58.970049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 043a5c66-d191-449a-afca-960a7c2be8ca · inbound

What do Reward Models Memorize? cites this paper.

What do Reward Models Memorize? Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-31T13:41:42.895479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f904c68f-6879-4859-8ce7-4640b3670e3c · inbound

SMOPD: Multi-Reward Reinforcement Learning via Specialize-and-Merge Online Policy Distillation cites this paper.

SMOPD: Multi-Reward Reinforcement Learning via Specialize-and-Merge Online Policy Distillation Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-15T14:57:53.946749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.