Paper Citation Record · LEDGER

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective

As of 8 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2506.00152.

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

pith.paper-citation-record.v1
2506.00152 v1

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:16:17.842335Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

43 of 43 outbound references displayed

verified exact1
verified fuzzy21
unresolved20
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c01c58dc-46a1-4004-9c0b-838f4a9ef487 · outbound

This paper cites How ai outperforms humans at creative idea generation.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective How ai outperforms humans at creative idea generation

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:16:21.862335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f31d8b2a-4c52-4119-add1-707b0bd7539f · outbound

This paper cites Ai–human hybrids for marketing research: Leveraging large language models (llms) as collaborators.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Ai–human hybrids for marketing research: Leveraging large language models (llms) as collaborators

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:16:21.719018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation afd87cce-6043-4ae9-ade5-b60d56f90e14 · outbound

This paper cites Frontiers: Can large language models capture human prefer- ences? Marketing Science, 43(4):709–722, 2024.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Frontiers: Can large language models capture human prefer- ences? Marketing Science, 43(4):709–722, 2024

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:16:21.378710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6846cab9-cc19-47e6-a3ce-bd099f0400b1 · outbound

This paper cites LOLA: LLM-Assisted Online Learning Algorithm for Content Experiments.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective LOLA: LLM-Assisted Online Learning Algorithm for Content Experiments

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T12:16:14.436321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 782aba1f-e6cb-4374-a701-b56451811f89 · outbound

This paper cites Challenges and Future Directions of Data-Centric AI Alignment.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Challenges and Future Directions of Data-Centric AI Alignment

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T12:16:14.584356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27be85ee-4e45-4465-813a-2cb4eaa498c1 · outbound

This paper cites A/b testing: A systematic literature review.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective A/b testing: A systematic literature review

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:16:21.155978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1304c1b3-7cf6-4b4f-b5fc-b527e17c1310 · outbound

This paper cites Causal alignment: Augmenting language models with a/b tests.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Causal alignment: Augmenting language models with a/b tests

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T12:16:14.782289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8653298e-2855-4c80-b5a5-42532f56fab3 · outbound

This paper cites Using advanced llms to enhance smaller llms: An interpretable knowledge distillation approach.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Using advanced llms to enhance smaller llms: An interpretable knowledge distillation approach

Reference 8

Resolution: verified exact; raw_fallback, observed 2026-08-07T12:16:18.468656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f01b1c0a-05a2-43f4-83de-fea84e624f49 · outbound

This paper cites Test & roll: Profit-maximizing a/b tests.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Test & roll: Profit-maximizing a/b tests

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:16:20.952564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 87253cb1-f801-432d-bdea-fbb23aa2948b · outbound

This paper cites An empirical meta-analysis of e-commerce a/b testing strategies.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective An empirical meta-analysis of e-commerce a/b testing strategies

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:16:20.744955Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1395be67-84f5-406e-a8d9-835b1a721668 · outbound

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

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Training language models to follow instructions with human feedback

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T12:16:15.103600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cdda42c-2864-4fcc-98e6-63524a7aad59 · outbound

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

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Direct preference optimization: Your language model is secretly a reward model

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T12:16:15.175631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4fbbd3e-4590-4657-83e2-9b8471d94855 · outbound

This paper cites Lima: Less is more for alignment.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Lima: Less is more for alignment

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T12:16:15.267425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19e5775a-1770-4bdd-b367-a0ee4092b2a6 · outbound

This paper cites The importance of human-labeled data in the era of llms.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective The importance of human-labeled data in the era of llms

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:16:20.458336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d37f9bd2-4b6f-4a95-a0ad-9ad7914a76d4 · outbound

This paper cites Scaling laws for reward model overoptimization.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Scaling laws for reward model overoptimization

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T12:16:15.448497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52856e02-4a99-4368-bd32-d4e6a38b8a78 · outbound

This paper cites Scaling laws for reward model overoptimization in direct alignment algorithms.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Scaling laws for reward model overoptimization in direct alignment algorithms

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:16:20.241078Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation dc2dd242-8485-4e6a-930e-aaca2b364761 · outbound

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

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Fine-Tuning Language Models from Human Preferences

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T12:16:15.576254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3240d1f-c082-4435-8769-cf59db7c3518 · outbound

This paper cites RLAIF: Scal- ing reinforcement learning from human feedback with AI feedback, 2024.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective RLAIF: Scal- ing reinforcement learning from human feedback with AI feedback, 2024

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:16:20.015498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a1ae2e67-47ec-4273-961f-b4052573685a · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T12:16:15.716062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 480d506a-8742-4f8c-8b15-36439fc36f17 · outbound

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

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective A General Language Assistant as a Laboratory for Alignment

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T12:16:15.782738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aaacbc1b-e606-4515-969b-55cc7792ebc4 · outbound

This paper cites The upworthy research archive, a time series of 32,487 experiments in us media.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective The upworthy research archive, a time series of 32,487 experiments in us media

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:16:19.855934Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b83ca2f0-ed9d-4ed0-a290-b717dab7fc04 · outbound

This paper cites Pythia: A suite for analyzing large language models across training and scaling.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Pythia: A suite for analyzing large language models across training and scaling

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T12:16:15.951592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 701f88d8-2126-41e2-b4aa-0934efbfa74d · outbound

This paper cites Double/debiased machine learning for treatment and structural parameters.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Double/debiased machine learning for treatment and structural parameters

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:16:19.753711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 65f8d39b-6f2e-4437-a4f6-2610d9fae4a8 · outbound

This paper cites Minimax estimation of conditional moment models.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Minimax estimation of conditional moment models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:16:19.625610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1100beae-4776-418e-9d8d-4350b6df5d89 · outbound

This paper cites Mind: A large-scale dataset for news recommendation.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Mind: A large-scale dataset for news recommendation

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:16:19.491351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 447989a9-e58f-42f3-8c2c-84d434e6fd98 · outbound

This paper cites Generative brand choice.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Generative brand choice

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:16:19.360338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 873e0199-de5f-45a7-8d8f-68a9106cb74a · outbound

This paper cites Deep neural networks for estimation and inference.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Deep neural networks for estimation and inference

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:16:19.222244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9ee94596-7af0-49a8-9bb8-96f8d995be3a · outbound

This paper cites Deep generalized method of moments for instrumental variable analysis.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Deep generalized method of moments for instrumental variable analysis

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:16:19.159180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 58c9ac13-0bb7-41a8-8aca-77a9ee31969a · outbound

This paper cites Causal regressions for unstructured data.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Causal regressions for unstructured data

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:16:19.093833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c5bc5580-efe2-45b2-973b-4a1e30795853 · outbound

This paper cites Secrets of RLHF in Large Language Models Part I: PPO.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Secrets of RLHF in Large Language Models Part I: PPO

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T12:16:16.728456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e660493-93ab-42cd-a656-900de269cc29 · outbound

This paper cites Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T12:16:16.819602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e951b96-3123-48bf-bcd4-574844319aa9 · outbound

This paper cites Bias in data-driven artificial intelligence systems—an introductory survey.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Bias in data-driven artificial intelligence systems—an introductory survey

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:16:19.003112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3a528559-9b07-4aa3-8710-8ad63f060415 · outbound

This paper cites Causal Confusion and Reward Misidentification in Preference-Based Reward Learning.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Causal Confusion and Reward Misidentification in Preference-Based Reward Learning

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T12:16:17.017683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 364f773c-46c3-4693-bd84-54150435f2ee · outbound

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

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T12:16:17.142465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7e10994-40b2-4706-903f-2421b967a51a · outbound

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

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective ODIN: Disentangled Reward Mitigates Hacking in RLHF

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T12:16:17.249774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

This paper cites Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment.

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 fba57f18-16e5-4fdc-8fa1-71201e39de9e · outbound

This paper cites SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T12:16:17.483713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fee8457-da0a-4969-a6f0-991d87fcb8a6 · outbound

This paper cites Lora: Low-rank adaptation of large language models.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Lora: Low-rank adaptation of large language models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T12:16:17.560917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4df7dea-5854-4d46-b4d2-bbb80f4e4c9f · outbound

This paper cites distilbert-base-multilingual-cased-sentiments-student (re- vision 2e33845), 2023.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective distilbert-base-multilingual-cased-sentiments-student (re- vision 2e33845), 2023

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:16:18.888619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0056c3d5-8694-46ce-9ea5-cb6f7d039276 · outbound

This paper cites A survey on bias and fairness in machine learning.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective A survey on bias and fairness in machine learning

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T12:16:17.647306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16b0d6ec-d405-4c0e-99e9-3877f97d715a · outbound

This paper cites On the adaptive elastic-net with a diverging number of parameters.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective On the adaptive elastic-net with a diverging number of parameters

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:16:18.762006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation eda638d9-805f-4841-b6d1-17268fd0bc0c · outbound

This paper cites Endogeneity in high dimensions.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective Endogeneity in high dimensions

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:16:18.630931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ac285f32-15af-4f0f-9196-dc30448eca56 · outbound

This paper cites packages.

Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective packages

Reference 43

Resolution: metadata mismatch; raw_fallback, observed 2026-08-07T12:16:18.120828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

No inbound Pith citation observations are available.