Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? | Paper Citation Record

Observation dba8227b-b72d-479f-bde8-1c13692362b6 · outbound

This paper cites Aligning Large Language Models with Human: A Survey.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Aligning Large Language Models with Human: A Survey

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.155225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d2ed43c-03db-40a8-bb27-85e3106ca46d · outbound

This paper cites Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.159882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cd1976d-7b7e-4604-8e5c-92cb51178a8f · outbound

This paper cites UltraFeedback: Boosting Language Models with Scaled AI Feedback.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? UltraFeedback: Boosting Language Models with Scaled AI Feedback

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.165537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d28a6798-21be-4253-ae69-eba4f9d6140c · outbound

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

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? A General Language Assistant as a Laboratory for Alignment

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.171527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88d0f485-409f-4db0-9ac5-9536f135504c · outbound

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

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.176534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf6db343-9acf-4e71-8fe9-75b41c3e3b86 · outbound

This paper cites an unresolved cited work.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:15:47.074771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 90b915a2-73f1-4b6a-b678-03d3275cabb1 · outbound

This paper cites Manning, Stefano Ermon, and Chelsea Finn.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Manning, Stefano Ermon, and Chelsea Finn

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:47.064401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation bdd6cb4c-e052-4261-b266-da5ac02872ac · outbound

This paper cites From Lists to Emojis: How Format Bias Affects Model Alignment.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? From Lists to Emojis: How Format Bias Affects Model Alignment

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.189911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78f9a988-9b9a-4100-9941-4c68a102176d · outbound

This paper cites Offsetbias: Leveraging debiased data for tuning evaluators.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Offsetbias: Leveraging debiased data for tuning evaluators

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:47.054824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0c05f996-aa3d-40b2-97b6-ba0cb90335e9 · outbound

This paper cites Disentangling length from quality in direct preference optimization.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Disentangling length from quality in direct preference optimization

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:47.043879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation aaa623f8-5777-4bc0-9e76-25b3c7eaf379 · outbound

This paper cites KTO: Model Alignment as Prospect Theoretic Optimization.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? KTO: Model Alignment as Prospect Theoretic Optimization

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.203797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14be7723-3d69-4534-914b-b17772787e2b · outbound

This paper cites RewardBench: Evaluating Reward Models for Language Modeling.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? RewardBench: Evaluating Reward Models for Language Modeling

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.208143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36fbaf91-6663-49fb-bc1a-4bf3cc467387 · outbound

This paper cites Predictive pipelined decoding: A compute-latency trade-off for exact LLM decoding.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Predictive pipelined decoding: A compute-latency trade-off for exact LLM decoding

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:47.026558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 80188a3d-4398-4158-af0d-294f3c38082b · outbound

This paper cites Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.217676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b8f2045-d632-41d8-8738-8ebcedfca088 · outbound

This paper cites SAM Decoding: Speculative Decoding via Suffix Automaton.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? SAM Decoding: Speculative Decoding via Suffix Automaton

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.221364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42994f2b-78f4-42ef-a002-ba94498ea71e · outbound

This paper cites S2D: Sorted Speculative Decoding For More Efficient Deployment of Nested Large Language Models.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? S2D: Sorted Speculative Decoding For More Efficient Deployment of Nested Large Language Models

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-08-07T15:15:46.667015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 29734963-f7b4-4944-8d9e-0e41c3a07c99 · outbound

This paper cites The unlocking spell on base llms: Rethinking alignment via in-context learning.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? The unlocking spell on base llms: Rethinking alignment via in-context learning

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:47.015026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 70a963a9-1809-427e-9e7d-f6048fc901e8 · outbound

This paper cites Safety Alignment Should Be Made More Than Just a Few Tokens Deep.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Safety Alignment Should Be Made More Than Just a Few Tokens Deep

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.235543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5578633-572c-42b3-8172-d6d7d4b49a57 · outbound

This paper cites Christiano, Jan Leike, Tom B.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Christiano, Jan Leike, Tom B

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.241872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57406553-5096-4b3f-8ebd-d538567bbf03 · outbound

This paper cites GPT-4o System Card.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? GPT-4o System Card

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.247561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e0cc3c2-ba1f-4e04-b503-9cce0e585656 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Gemini: A Family of Highly Capable Multimodal Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.252669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51ed382d-c3ad-4485-a917-b07d40cdee5e · outbound

This paper cites The Llama 3 Herd of Models.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? The Llama 3 Herd of Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.267359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be6848b4-31e8-4f5b-8cb2-4ba3225c8f7c · outbound

This paper cites On the weaknesses of reinforcement learning for neural machine translation.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? On the weaknesses of reinforcement learning for neural machine translation

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:46.996196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation dc0ec6a0-0fe7-4e1f-8560-d83ff9f57534 · outbound

This paper cites Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.288418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2cf9eaa-5d02-454e-91db-cc41a6877c14 · outbound

This paper cites SLiC-HF: Sequence Likelihood Calibration with Human Feedback.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? SLiC-HF: Sequence Likelihood Calibration with Human Feedback

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.299308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0afdf0d-fc39-4f31-92dc-09b17d5d8606 · outbound

This paper cites A general theoretical paradigm to understand learning from human preferences.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? A general theoretical paradigm to understand learning from human preferences

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:46.983769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0fa5c61f-94c3-481a-8301-bcdcf867e642 · outbound

This paper cites Generalized preference optimization: A unified approach to offline alignment.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Generalized preference optimization: A unified approach to offline alignment

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:46.971851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation cbfe94fd-9683-4d9b-802f-3a45d98322da · outbound

This paper cites TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.338984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 096646df-cbfe-410b-b49b-a168e2289500 · outbound

This paper cites MaxMin-RLHF: Alignment with Diverse Human Preferences.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? MaxMin-RLHF: Alignment with Diverse Human Preferences

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.346809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5adc1e2e-aa18-4435-b8a5-63735f194c7e · outbound

This paper cites an unresolved cited work.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.352530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4303cc5-e39a-460a-9445-18eeca19d7b1 · outbound

This paper cites Enabling Language Models to Implicitly Learn Self-Improvement.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Enabling Language Models to Implicitly Learn Self-Improvement

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.356346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e723c431-617a-4fe5-b356-22ad22a55e18 · outbound

This paper cites Mankowitz, Doina Precup, and Bilal Piot.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Mankowitz, Doina Precup, and Bilal Piot

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:46.955912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 9c33439b-9166-4d30-a133-cedb8c35ee48 · outbound

This paper cites A minimaximalist approach to reinforcement learning from human feedback.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? A minimaximalist approach to reinforcement learning from human feedback

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:46.938379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4a78435b-0abb-422c-95b9-2722526d7a4a · outbound

This paper cites Online Iterative Reinforcement Learning from Human Feedback with General Preference Model.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Online Iterative Reinforcement Learning from Human Feedback with General Preference Model

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.376259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b1df7d4-fdc7-47fe-b973-4912033fa0a3 · outbound

This paper cites Llm-blender: Ensembling large language models with pairwise ranking and generative fusion.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Llm-blender: Ensembling large language models with pairwise ranking and generative fusion

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:46.928505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a75a1773-5596-48cf-9023-c22a84bf438f · outbound

This paper cites Liu, and Jialu Liu.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Liu, and Jialu Liu

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:46.918214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f9c63e0b-c0fc-4171-ac2c-44ef9c55fbb5 · outbound

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

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.395903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f425f02-a243-48fb-a7ec-28fd60e427b8 · outbound

This paper cites Helpsteer: Multi-attribute helpfulness dataset for steerlm.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Helpsteer: Multi-attribute helpfulness dataset for steerlm

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:46.908635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3b914cc7-38cc-4cf4-b2d8-134cc42f01bd · outbound

This paper cites Interpretable preferences via multi- objective reward modeling and mixture-of-experts.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Interpretable preferences via multi- objective reward modeling and mixture-of-experts

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:46.898167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 213384ad-82ee-49b3-a8c8-1caa91b66d9e · outbound

This paper cites WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.407046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28d70d3c-5a72-4fb9-9e3d-950c56eeb9cc · outbound

This paper cites Let’s verify step by step.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Let’s verify step by step

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.410419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e0e3dc3-97e1-4e1e-b2b4-f66c1636120f · outbound

This paper cites Process Reward Model with Q-Value Rankings.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Process Reward Model with Q-Value Rankings

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.413629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd190bca-f36f-4e72-8ff7-572712098a4d · outbound

This paper cites Glore: When, where, and how to improve LLM reasoning via global and local refinements.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Glore: When, where, and how to improve LLM reasoning via global and local refinements

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:46.880460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 03ae14d6-fb94-4686-9f1a-5dde4f332355 · outbound

This paper cites Defining and Characterizing Reward Hacking.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Defining and Characterizing Reward Hacking

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.420808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d438329-22eb-47fd-abbe-59d554aa8208 · outbound

This paper cites Arjona-Medina, Michael Gillhofer, Michael Widrich, Thomas Unterthiner, Johannes Brandstetter, and Sepp Hochreiter.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Arjona-Medina, Michael Gillhofer, Michael Widrich, Thomas Unterthiner, Johannes Brandstetter, and Sepp Hochreiter

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:46.870280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8590a2c0-5e40-4575-bbc1-f14ab7ba74da · outbound

This paper cites The effects of reward misspecification: Mapping and mitigating misaligned models.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? The effects of reward misspecification: Mapping and mitigating misaligned models

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:46.858649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 54f46a91-c27d-4127-9d08-f25b3ce50ebb · outbound

This paper cites Ball, Oleh Rybkin, Stephen Roberts, Tim Rocktäschel, and Edward Grefenstette.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Ball, Oleh Rybkin, Stephen Roberts, Tim Rocktäschel, and Edward Grefenstette

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:46.847364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 406f1a71-0f7a-4a3b-89d3-d2544b369b2a · outbound

This paper cites Correlated proxies: A new definition and improved mitigation for reward hacking, 2024.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Correlated proxies: A new definition and improved mitigation for reward hacking, 2024

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.433343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cea58e23-3821-423b-96db-e25b04135b23 · outbound

This paper cites Inform: Mitigating reward hacking in RLHF via information-theoretic reward modeling.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Inform: Mitigating reward hacking in RLHF via information-theoretic reward modeling

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:46.829352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 80e08e02-5c8f-49fd-9790-1f82d1c7f942 · outbound

This paper cites When Can Proxies Improve the Sample Complexity of Preference Learning?.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? When Can Proxies Improve the Sample Complexity of Preference Learning?

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-08-07T15:15:46.510460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d803e9ca-2919-40ff-b1af-1d9199def227 · outbound

This paper cites RLHF Workflow: From Reward Modeling to Online RLHF.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? RLHF Workflow: From Reward Modeling to Online RLHF

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.442619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be2fa502-7c37-4c8e-8f45-2e9ed6e3baf4 · outbound

This paper cites an unresolved cited work.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Unresolved cited work

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.446051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e11cece-30f0-48d4-9926-ead2d5b0d7e2 · outbound

This paper cites Patterson, Joseph Gonzalez, Urs Hölzle, Quoc V.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Patterson, Joseph Gonzalez, Urs Hölzle, Quoc V

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:46.809151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 17ab31b6-f920-40fa-8e10-4b4deff297ea · outbound

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

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.451629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc602100-b4fc-47c2-9193-c4e43c8c19b9 · outbound

This paper cites Iterative preference learning from human feedback: Bridging theory and practice for rlhf under kl-constraint, 2024.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Iterative preference learning from human feedback: Bridging theory and practice for rlhf under kl-constraint, 2024

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.455296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75172685-d121-4f34-a808-f78df1158f0f · outbound

This paper cites Hashimoto.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Hashimoto

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.458257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6032cc0-7331-424c-9e6d-7ad104a6d1c8 · outbound

This paper cites Hashimoto.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Hashimoto

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:46.462329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1aa69f0-b56e-4868-ab57-addb7a5ebd00 · outbound

This paper cites Understanding dataset difficulty with V-usable information.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Understanding dataset difficulty with V-usable information

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:15:46.773272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0f4afe28-e1cd-4cad-a579-c1e49c088abb · outbound

This paper cites an unresolved cited work.

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data? Unresolved cited work

Reference 2024

Resolution: parse uncertain; no resolver link, observed 2026-08-07T15:15:46.364907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers