Paper Citation Record · LEDGER

Self-Generated Critiques Boost Reward Modeling for Language Models

As of 21 August 2026, this Paper Citation Record lists 69 of 69 outbound references and 13 inbound Pith citation observations for arXiv:2411.16646.

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

pith.paper-citation-record.v1
2411.16646 v3

Coverage vector

measured 69 of 69 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T12:58:31.026570Z

measured 82 of 82 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 13 of 13 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T06:04:14.616880Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T12:25:43.079840Z

Reference resolution

69 of 69 outbound references displayed

verified exact0
verified fuzzy30
unresolved39
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ffe186cc-3c5b-4c67-a231-575c198eb217 · outbound

This paper cites write newline.

Self-Generated Critiques Boost Reward Modeling for Language Models write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:29.260257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be74fe89-6d27-403d-90e7-8c9b03a9fafc · outbound

This paper cites GPT-4 Technical Report.

Self-Generated Critiques Boost Reward Modeling for Language Models GPT-4 Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:29.265220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdc67657-8d22-4276-bdcf-5dccef2e053b · outbound

This paper cites Nemotron-4 340B Technical Report.

Self-Generated Critiques Boost Reward Modeling for Language Models Nemotron-4 340B Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:29.269006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2da54106-6976-473d-9860-52191c7b82fd · outbound

This paper cites On-policy distillation of language models: Learning from self-generated mistakes.

Self-Generated Critiques Boost Reward Modeling for Language Models On-policy distillation of language models: Learning from self-generated mistakes

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:34.017921Z

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 7692ca6f-1e13-4ddc-b1df-f6598b6d6efd · outbound

This paper cites Critique-out-Loud Reward Models.

Self-Generated Critiques Boost Reward Modeling for Language Models Critique-out-Loud Reward Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:29.291482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5495ec06-07b3-4dc0-b3cf-22ea57457e7e · outbound

This paper cites LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks.

Self-Generated Critiques Boost Reward Modeling for Language Models LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:29.387291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10718ebf-7c38-4deb-ab5a-493340d7fa5e · outbound

This paper cites Rank analysis of incomplete block designs: I.

Self-Generated Critiques Boost Reward Modeling for Language Models Rank analysis of incomplete block designs: I

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:29.467193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d881a421-a2f7-4499-aefa-9bc0ce2211a7 · outbound

This paper cites ODIN : Disentangled reward mitigates hacking in RLHF.

Self-Generated Critiques Boost Reward Modeling for Language Models ODIN : Disentangled reward mitigates hacking in RLHF

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:33.981992Z

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 0ed77cfe-6af7-476f-9be6-77b567048768 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Self-Generated Critiques Boost Reward Modeling for Language Models Training Verifiers to Solve Math Word Problems

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:29.475517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9439820-ed0a-43d8-948e-53aee259aec3 · outbound

This paper cites Reward model ensembles help mitigate overoptimization.

Self-Generated Critiques Boost Reward Modeling for Language Models Reward model ensembles help mitigate overoptimization

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:33.962505Z

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 ebdcdafe-36ad-42ac-abc8-873f127fe448 · outbound

This paper cites ULTRAFEEDBACK : Boosting language models with scaled AI feedback.

Self-Generated Critiques Boost Reward Modeling for Language Models ULTRAFEEDBACK : Boosting language models with scaled AI feedback

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:33.942146Z

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 99a51931-811e-4536-8d67-03eec6ed9b91 · outbound

This paper cites Safe RLHF : Safe reinforcement learning from human feedback.

Self-Generated Critiques Boost Reward Modeling for Language Models Safe RLHF : Safe reinforcement learning from human feedback

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:33.793759Z

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 1df86ae6-5bf9-477a-ab99-5f9324186052 · outbound

This paper cites The Llama 3 Herd of Models.

Self-Generated Critiques Boost Reward Modeling for Language Models The Llama 3 Herd of Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:29.490464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdd7b0af-553f-4e15-b4fe-a755fbbfd4b8 · outbound

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

Self-Generated Critiques Boost Reward Modeling for Language Models Alpacafarm: A simulation framework for methods that learn from human feedback

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:33.643273Z

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 ab384553-124d-4260-bf41-f028c093f2b9 · outbound

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

Self-Generated Critiques Boost Reward Modeling for Language Models Understanding dataset difficulty with V -usable information

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:33.621702Z

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 d7c37332-c054-4d80-8180-4cab9d7947a4 · outbound

This paper cites Reinforced Self-Training (ReST) for Language Modeling.

Self-Generated Critiques Boost Reward Modeling for Language Models Reinforced Self-Training (ReST) for Language Modeling

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:29.612122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b937e7ea-ae3b-41b2-839d-4f7d69ec706d · outbound

This paper cites Measuring mathematical problem solving with the MATH dataset.

Self-Generated Critiques Boost Reward Modeling for Language Models Measuring mathematical problem solving with the MATH dataset

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:33.596360Z

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 9167072b-59c6-403d-bb6a-f0beff333e73 · outbound

This paper cites Large language models are reasoning teachers.

Self-Generated Critiques Boost Reward Modeling for Language Models Large language models are reasoning teachers

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:33.582108Z

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 e3d3cfd2-2f93-47f0-a5a9-4c76d2050892 · outbound

This paper cites GPT-4o System Card.

Self-Generated Critiques Boost Reward Modeling for Language Models GPT-4o System Card

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:29.621988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df515ede-6881-4dc0-883c-228befcbe788 · outbound

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

Self-Generated Critiques Boost Reward Modeling for Language Models Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:29.625399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccfdbcb1-a093-42bb-882b-351bde9e5176 · outbound

This paper cites Prometheus: Inducing fine-grained evaluation capability in language models.

Self-Generated Critiques Boost Reward Modeling for Language Models Prometheus: Inducing fine-grained evaluation capability in language models

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:33.564193Z

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 4952cc09-d83e-42c5-8f0c-60f732d50cf1 · outbound

This paper cites Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models.

Self-Generated Critiques Boost Reward Modeling for Language Models Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:29.634019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b1a55d5-82df-4bee-a113-6fffd0b28b8c · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Self-Generated Critiques Boost Reward Modeling for Language Models Adam: A Method for Stochastic Optimization

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:29.698430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6826f4ad-82ca-4a33-befc-a9094d6f0b12 · outbound

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

Self-Generated Critiques Boost Reward Modeling for Language Models RewardBench: Evaluating Reward Models for Language Modeling

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:29.782781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca8cdb4b-64be-4003-824b-f6a7f005b014 · outbound

This paper cites RLAIF vs.

Self-Generated Critiques Boost Reward Modeling for Language Models RLAIF vs

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:33.543902Z

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 ead8f73b-a27e-49a0-a4c1-4f6efa6ad336 · outbound

This paper cites Generative judge for evaluating alignment.

Self-Generated Critiques Boost Reward Modeling for Language Models Generative judge for evaluating alignment

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:33.333152Z

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 8b2bad33-2fdb-4f3d-a422-e48cd5c4495b · outbound

This paper cites Self-alignment with instruction backtranslation.

Self-Generated Critiques Boost Reward Modeling for Language Models Self-alignment with instruction backtranslation

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:33.249300Z

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 1ebf980e-f036-43f8-9ae6-cddbb62346d3 · outbound

This paper cites Alpacaeval: An automatic evaluator of instruction-following models, 2023.

Self-Generated Critiques Boost Reward Modeling for Language Models Alpacaeval: An automatic evaluator of instruction-following models, 2023

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:29.798012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0914b2ba-0d33-4926-badd-596a3b042408 · outbound

This paper cites C ritic B ench: Benchmarking LLM s for critique-correct reasoning.

Self-Generated Critiques Boost Reward Modeling for Language Models C ritic B ench: Benchmarking LLM s for critique-correct reasoning

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:33.228047Z

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 23ba04f1-cdbe-4813-9a5e-c25a3f1e13c7 · outbound

This paper cites RRM: Robust Reward Model Training Mitigates Reward Hacking.

Self-Generated Critiques Boost Reward Modeling for Language Models RRM: Robust Reward Model Training Mitigates Reward Hacking

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:29.805299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 487d4a13-6e52-441d-a9e3-11fe3b6751c3 · outbound

This paper cites Self-refine: Iterative refinement with self-feedback.

Self-Generated Critiques Boost Reward Modeling for Language Models Self-refine: Iterative refinement with self-feedback

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:33.217052Z

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 9aed85a1-f604-4f0f-b5ab-0e65a84fceda · outbound

This paper cites Generative Reward Models.

Self-Generated Critiques Boost Reward Modeling for Language Models Generative Reward Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:29.812439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bba815f-51b3-421d-a58c-56362845ad24 · outbound

This paper cites LLM Critics Help Catch LLM Bugs.

Self-Generated Critiques Boost Reward Modeling for Language Models LLM Critics Help Catch LLM Bugs

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:29.816635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ddc2213-a8b0-4b6e-9aea-33b298231266 · outbound

This paper cites Introducing ChatGPT , 2022.

Self-Generated Critiques Boost Reward Modeling for Language Models Introducing ChatGPT , 2022

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:33.206464Z

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 5194ba0e-c31a-44f4-85d5-75a67c2e0cf9 · outbound

This paper cites Chatterji, Faisal Ladhak, and Tatsunori Hashimoto.

Self-Generated Critiques Boost Reward Modeling for Language Models Chatterji, Faisal Ladhak, and Tatsunori Hashimoto

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:33.195224Z

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 dff5371a-f534-47f2-8100-5053755232a0 · outbound

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

Self-Generated Critiques Boost Reward Modeling for Language Models Training language models to follow instructions with human feedback

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:30.008331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f83f81e4-53fb-4b58-bc24-dc87258681b0 · outbound

This paper cites West-of-N: Synthetic Preferences for Self-Improving Reward Models.

Self-Generated Critiques Boost Reward Modeling for Language Models West-of-N: Synthetic Preferences for Self-Improving Reward Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:30.027648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe18b1f5-4420-43cc-9fa1-796a0d13cab2 · outbound

This paper cites Iterative reasoning preference optimization.

Self-Generated Critiques Boost Reward Modeling for Language Models Iterative reasoning preference optimization

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:33.173968Z

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 3a3ae537-c3f5-4657-af8a-3492ada82995 · outbound

This paper cites Self-Consistency Preference Optimization.

Self-Generated Critiques Boost Reward Modeling for Language Models Self-Consistency Preference Optimization

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:30.052464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a344517-4d59-4bf7-acb0-701819fa96b1 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

Self-Generated Critiques Boost Reward Modeling for Language Models Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:30.056903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bae4a46-f07d-4305-adf9-30f3e4002ff6 · outbound

This paper cites Self-critiquing models for assisting human evaluators.

Self-Generated Critiques Boost Reward Modeling for Language Models Self-critiquing models for assisting human evaluators

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:30.061143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3241364-a4d7-4f55-9ece-e712e0410b41 · outbound

This paper cites BOND: Aligning LLMs with Best-of-N Distillation.

Self-Generated Critiques Boost Reward Modeling for Language Models BOND: Aligning LLMs with Best-of-N Distillation

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:30.107501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2073dceb-9bcd-4492-bdee-b4b33894bd74 · outbound

This paper cites Boosting Reward Model with Preference-Conditional Multi-Aspect Synthetic Data Generation.

Self-Generated Critiques Boost Reward Modeling for Language Models Boosting Reward Model with Preference-Conditional Multi-Aspect Synthetic Data Generation

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:30.214477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01e1fd14-dc31-425c-8d7e-69470379eebb · outbound

This paper cites The trickle-down impact of reward inconsistency on RLHF.

Self-Generated Critiques Boost Reward Modeling for Language Models The trickle-down impact of reward inconsistency on RLHF

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:33.163720Z

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 34899596-ca26-4c55-96fb-253fc2dd3352 · outbound

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

Self-Generated Critiques Boost Reward Modeling for Language Models A Long Way to Go: Investigating Length Correlations in RLHF

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:30.292523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9e3cab9-e24f-474d-a7aa-1fdb5f9518e3 · outbound

This paper cites an unresolved cited work.

Self-Generated Critiques Boost Reward Modeling for Language Models Unresolved cited work

Reference 46

Resolution: unresolved; raw_fallback, observed 2026-08-12T12:58:33.151959Z

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 3646890f-9ca2-4e2c-a6b3-a73bdd7e84b4 · outbound

This paper cites Learning to summarize with human feedback.

Self-Generated Critiques Boost Reward Modeling for Language Models Learning to summarize with human feedback

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:30.301418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3ddc1eb-74cf-4886-95f6-612dd368a724 · outbound

This paper cites Large Language Models are Inconsistent and Biased Evaluators.

Self-Generated Critiques Boost Reward Modeling for Language Models Large Language Models are Inconsistent and Biased Evaluators

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:30.306126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03829fd2-a518-4681-a276-726bdbe383ed · outbound

This paper cites SALMON : Self-alignment with instructable reward models.

Self-Generated Critiques Boost Reward Modeling for Language Models SALMON : Self-alignment with instructable reward models

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:33.003980Z

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 87774883-6e0d-499c-b615-1a7ab9dd2eae · outbound

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

Self-Generated Critiques Boost Reward Modeling for Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:30.503198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a75f3008-98fd-41c2-9d5e-f1395e529a24 · outbound

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

Self-Generated Critiques Boost Reward Modeling for Language Models Interpretable preferences via multi-objective reward modeling and mixture-of-experts

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:32.816979Z

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 68f3bf2c-00b1-44bc-a2b4-bf32d29cbcd0 · outbound

This paper cites Self-Taught Evaluators.

Self-Generated Critiques Boost Reward Modeling for Language Models Self-Taught Evaluators

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:30.525152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db5b1d9e-0179-4254-8595-3c1d171a551a · outbound

This paper cites Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou.

Self-Generated Critiques Boost Reward Modeling for Language Models Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:32.763179Z

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 ae03238b-bd98-4a39-b8f1-4f0487bc72da · outbound

This paper cites HelpSteer2-Preference: Complementing Ratings with Preferences.

Self-Generated Critiques Boost Reward Modeling for Language Models HelpSteer2-Preference: Complementing Ratings with Preferences

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:30.532006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5277e0aa-39f4-4e3d-9cdb-0541f6c20deb · outbound

This paper cites HelpSteer2: Open-source dataset for training top-performing reward models.

Self-Generated Critiques Boost Reward Modeling for Language Models HelpSteer2: Open-source dataset for training top-performing reward models

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:30.536214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 462bf89c-54f7-4454-8d6b-7376217d64f3 · outbound

This paper cites H elp S teer: Multi-attribute helpfulness dataset for S teer LM.

Self-Generated Critiques Boost Reward Modeling for Language Models H elp S teer: Multi-attribute helpfulness dataset for S teer LM

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:32.707233Z

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 3be7e336-c88e-4252-8529-764dd791fde2 · outbound

This paper cites Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge.

Self-Generated Critiques Boost Reward Modeling for Language Models Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:30.652167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0a009cb-092a-4642-9c3f-d7f0457bafc0 · outbound

This paper cites Smith, Mari Ostendorf, and Hannaneh Hajishirzi.

Self-Generated Critiques Boost Reward Modeling for Language Models Smith, Mari Ostendorf, and Hannaneh Hajishirzi

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:32.482742Z

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 fe73cde1-93d5-4685-850c-a737b1a660a5 · outbound

This paper cites WizardLM: Empowering large pre-trained language models to follow complex instructions.

Self-Generated Critiques Boost Reward Modeling for Language Models WizardLM: Empowering large pre-trained language models to follow complex instructions

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:30.721911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92f1ac4a-af66-4441-a1e6-c82f7e85207d · outbound

This paper cites The Perfect Blend: Redefining RLHF with Mixture of Judges.

Self-Generated Critiques Boost Reward Modeling for Language Models The Perfect Blend: Redefining RLHF with Mixture of Judges

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:30.725632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d441469-538a-448d-97c9-7de403a71d73 · outbound

This paper cites Predicting text preference via structured comparative reasoning.

Self-Generated Critiques Boost Reward Modeling for Language Models Predicting text preference via structured comparative reasoning

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:32.471803Z

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 c085e414-9992-48f3-a9ba-74ff99df1479 · outbound

This paper cites Improving Reward Models with Synthetic Critiques.

Self-Generated Critiques Boost Reward Modeling for Language Models Improving Reward Models with Synthetic Critiques

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:30.870757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bf6c7bb-daa5-409e-8f91-038ad55d8786 · outbound

This paper cites Self-rewarding language models.

Self-Generated Critiques Boost Reward Modeling for Language Models Self-rewarding language models

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:32.412079Z

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 37055a91-22f2-4359-b46f-04cdc0d4c6e6 · outbound

This paper cites ST ar: Bootstrapping reasoning with reasoning.

Self-Generated Critiques Boost Reward Modeling for Language Models ST ar: Bootstrapping reasoning with reasoning

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:32.344182Z

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 bdbc6414-9384-429c-921d-2bcaafe35f5f · outbound

This paper cites Evaluating large language models at evaluating instruction following.

Self-Generated Critiques Boost Reward Modeling for Language Models Evaluating large language models at evaluating instruction following

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:32.291325Z

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 87930707-cc45-4c6a-b59d-14439ba24ee1 · outbound

This paper cites Generative Verifiers: Reward Modeling as Next-Token Prediction.

Self-Generated Critiques Boost Reward Modeling for Language Models Generative Verifiers: Reward Modeling as Next-Token Prediction

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:31.011359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd504e4e-fc1e-4e42-864f-f59ca8389635 · outbound

This paper cites Gonzalez, and Ion Stoica.

Self-Generated Critiques Boost Reward Modeling for Language Models Gonzalez, and Ion Stoica

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:32.213472Z

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 c5263d52-72f4-4547-965e-7db28e34b226 · outbound

This paper cites Law of the Weakest Link: Cross Capabilities of Large Language Models.

Self-Generated Critiques Boost Reward Modeling for Language Models Law of the Weakest Link: Cross Capabilities of Large Language Models

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-12T12:58:31.022253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b5d11c8-4154-4cfe-b795-fb9bb11cc8c9 · outbound

This paper cites Iterative data smoothing: Mitigating reward overfitting and overoptimization in RLHF.

Self-Generated Critiques Boost Reward Modeling for Language Models Iterative data smoothing: Mitigating reward overfitting and overoptimization in RLHF

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T12:58:31.736219Z

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.

Pith citing papers

Observation 4d8777be-64db-4555-bd5a-c50a6fe447bf · inbound

In Context Learning and Reasoning for Symbolic Regression with Large Language Models cites this paper.

In Context Learning and Reasoning for Symbolic Regression with Large Language Models Self-Generated Critiques Boost Reward Modeling for Language Models

Reference 95

Resolution: verified exact; arxiv_id, observed 2026-05-23T18:53:21.144572Z

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 11b227f3-7a53-48b0-a279-df007f79eb27 · inbound

AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling cites this paper.

AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling Self-Generated Critiques Boost Reward Modeling for Language Models

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-11T11:43:24.850756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 199020c2-2a2a-4000-8eb8-0509df32500a · inbound

Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs cites this paper.

Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs Self-Generated Critiques Boost Reward Modeling for Language Models

Reference 278

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T15:51:29.406469Z

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 860b6c67-1087-476e-b6cd-f5f4d8e47482 · inbound

CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis cites this paper.

CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis Self-Generated Critiques Boost Reward Modeling for Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-10T22:26:46.683078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bf10488-a08d-454a-a18f-e96d366e2c8e · inbound

LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Information cites this paper.

LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Information Self-Generated Critiques Boost Reward Modeling for Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-09T13:25:52.136038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4229abe-225d-4a77-996c-286beb3372a5 · inbound

MM-RLHF: The Next Step Forward in Multimodal LLM Alignment cites this paper.

MM-RLHF: The Next Step Forward in Multimodal LLM Alignment Self-Generated Critiques Boost Reward Modeling for Language Models

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-07T18:23:50.481768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e96f158f-e359-4e4f-bac7-52b63dee4c60 · inbound

SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning cites this paper.

SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning Self-Generated Critiques Boost Reward Modeling for Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-16T06:04:14.616880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13be2a22-8da4-46b1-9941-d6d1fb329489 · inbound

J1: Exploring Simple Test-Time Scaling for LLM-as-a-Judge cites this paper.

J1: Exploring Simple Test-Time Scaling for LLM-as-a-Judge Self-Generated Critiques Boost Reward Modeling for Language Models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-15T20:50:10.757228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation faf6a9ce-0c08-4f47-8de0-a77a1dec0b40 · inbound

Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models cites this paper.

Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models Self-Generated Critiques Boost Reward Modeling for Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T15:09:54.445894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a978274c-3e04-4b41-9561-e696d770c2d0 · inbound

RewardAnything: Generalizable Principle-Following Reward Models cites this paper.

RewardAnything: Generalizable Principle-Following Reward Models Self-Generated Critiques Boost Reward Modeling for Language Models

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:07.139918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 422ef1bf-506e-4adc-bdba-de513b822b03 · inbound

Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges cites this paper.

Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges Self-Generated Critiques Boost Reward Modeling for Language Models

Reference 282

Resolution: unresolved; no resolver link, observed 2026-08-06T14:13:07.294496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58c58590-3bd8-48e6-b25b-a0b1448d2c79 · inbound

Building a Precise Video Language with Human-AI Oversight cites this paper.

Building a Precise Video Language with Human-AI Oversight Self-Generated Critiques Boost Reward Modeling for Language Models

Reference 83

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:46:04.461763Z

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 0dfaad6f-0025-45e8-99fb-15e8ced842ba · inbound

Test-Time Verification for Text-to-SQL via Outcome Reward Models cites this paper.

Test-Time Verification for Text-to-SQL via Outcome Reward Models Self-Generated Critiques Boost Reward Modeling for Language Models

Reference 83

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T12:25:43.081624Z

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.