Paper Citation Record · LEDGER

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF

As of 18 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 4 inbound Pith citation observations for arXiv:2505.12843.

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

pith.paper-citation-record.v1
2505.12843 v2

Coverage vector

measured 51 of 51 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:31:01.415106Z

measured 55 of 55 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T07:28:18.050097Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-06-29T12:23:24.212503Z

Reference resolution

51 of 51 outbound references displayed

verified exact0
verified fuzzy27
unresolved24
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 687059e7-1487-40a1-974e-91027e8af4b3 · outbound

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

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF A General Language Assistant as a Laboratory for Alignment

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.050427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ca65930-4c38-49aa-9e68-b3412f374ba1 · outbound

This paper cites Training a helpful and harmless assistant with reinforcement learning from human feedback, 2022.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Training a helpful and harmless assistant with reinforcement learning from human feedback, 2022

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:02.269453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f12f60ed-7165-4c6e-a46e-98f9aba21d7e · outbound

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

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Rank analysis of incomplete block designs: I

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.100010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8868765d-b6c9-4a2f-b86d-41ada71ae417 · outbound

This paper cites Noise contrastive alignment of language models with explicit rewards, 2024.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Noise contrastive alignment of language models with explicit rewards, 2024

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:02.242923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 68bc6e29-fd45-4f2f-b856-df39cac60120 · outbound

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

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF ODIN: Disentangled reward mitigates hacking in RLHF

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:02.227345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e1febd69-ddd5-41a2-9081-693e79f9f182 · outbound

This paper cites Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning, 2025.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning, 2025

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.126627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbd7e727-5072-40ec-88c6-d92c1175db1b · outbound

This paper cites Deepseek-v3 technical report, 2025.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Deepseek-v3 technical report, 2025

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:02.197954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1d399348-7ffb-40c2-bc44-ac4d26134666 · outbound

This paper cites RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.138963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d96ae6cc-6e97-4c26-b659-3484f7806aa1 · outbound

This paper cites Rlhf workflow: From reward modeling to online rlhf, 2024.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Rlhf workflow: From reward modeling to online rlhf, 2024

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.144235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92b36bd0-66db-4942-a8bb-206cd3b71f28 · outbound

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

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.149460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 895ee927-9f17-4fa9-96fb-e185860aa0ce · outbound

This paper cites Helping or herding? re- ward model ensembles mitigate but do not eliminate reward hacking.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Helping or herding? re- ward model ensembles mitigate but do not eliminate reward hacking

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:02.170133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5175fce3-dbec-4130-828f-6b4db048fca5 · outbound

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

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF KTO: Model Alignment as Prospect Theoretic Optimization

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.162942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00a8a2f2-ff85-4c42-92a9-3563c8715d8c · outbound

This paper cites Scaling laws for reward model overoptimization.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Scaling laws for reward model overoptimization

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:02.153446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9f39062b-9580-4429-8b48-74aa5924b5a6 · outbound

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

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF A general theoretical paradigm to understand learning from human preferences

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:02.136000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 091fd5b7-8e92-4857-99b4-3fe00829aab4 · outbound

This paper cites The llama 3 herd of models, 2024.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF The llama 3 herd of models, 2024

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.183228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd0117c1-6cf9-4226-8cb2-79708f860e0e · outbound

This paper cites BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.188382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe66a8c7-218f-4903-9363-d582253f066f · outbound

This paper cites Deep residual learning for im- age recognition.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Deep residual learning for im- age recognition

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:02.109230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 74341c34-490e-4297-a989-a09a27556a28 · outbound

This paper cites ORPO: Monolithic preference optimization without reference model.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF ORPO: Monolithic preference optimization without reference model

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:02.089711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 461bde1b-68cd-415b-9a4b-068b4cb0c487 · outbound

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

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Post-hoc reward calibra- tion: A case study on length bias

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:02.070083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 78169754-008c-4a47-93ab-923e4ca0c041 · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Gonzalez, Hao Zhang, and Ion Stoica

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.217132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 021ab3bf-76ee-4e76-89d0-184714636678 · outbound

This paper cites Openassistant conversations -democratizing large language model alignment.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Openassistant conversations -democratizing large language model alignment

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:02.037894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2d3a95c6-e250-4a0b-8ff2-59dfa125a0ef · outbound

This paper cites The Alignment Ceiling: Objective Mismatch in Reinforcement Learning from Human Feedback.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF The Alignment Ceiling: Objective Mismatch in Reinforcement Learning from Human Feedback

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.230482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73322ea2-4061-4ac9-aab0-9f0e9fb8f00b · outbound

This paper cites RRM: Robust reward model training mitigates reward hacking.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF RRM: Robust reward model training mitigates reward hacking

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:02.019581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ab8961fa-4a15-4bd6-b065-bbda41a69a15 · outbound

This paper cites Simpo: Simple preference optimization with a reference-free reward.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Simpo: Simple preference optimization with a reference-free reward

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:01.999843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a758781c-ef87-4653-ab11-23cc8fff87c8 · outbound

This paper cites Expanding on what we missed with sycophancy, 2025.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Expanding on what we missed with sycophancy, 2025

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:01.981268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 77de0340-a9e3-4520-94d6-15af306c4b2d · outbound

This paper cites Gpt-4 technical report, 2024.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Gpt-4 technical report, 2024

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:01.964195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5cd313b5-52c4-4f27-a8c4-4934d7f0dab3 · outbound

This paper cites Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744, 2022.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744, 2022

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.271309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a0d94a4-fffc-452d-9a16-c2a02c146196 · outbound

This paper cites Reward gaming in conditional text generation.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Reward gaming in conditional text generation

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:01.937446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2627ea87-679b-48fb-893d-a7fc06ed9222 · outbound

This paper cites PyTorch: An Imperative Style, High-Performance Deep Learning Library.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF PyTorch: An Imperative Style, High-Performance Deep Learning Library

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.283312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d92e127b-ad5e-4f4c-a8c4-19e72c3bb138 · outbound

This paper cites Notes on regression and inheritance in the case of two parents.Proceedings of the Royal Society of London, 58:240–242, 1895.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Notes on regression and inheritance in the case of two parents.Proceedings of the Royal Society of London, 58:240–242, 1895

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:01.922834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 37e87cc3-4853-45bc-90ff-18db27b3ab96 · outbound

This paper cites Qwen2.5 technical report, 2025.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Qwen2.5 technical report, 2025

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:01.906666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9a55eee8-8a33-4a5b-aa8e-d25da946b6d6 · outbound

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

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Direct preference optimization: Your language model is secretly a reward model

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.300971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b0b67e2-78f0-45f2-9c4e-f6777a4f5f11 · outbound

This paper cites Warp: On the benefits of weight averaged rewarded policies, 2024.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Warp: On the benefits of weight averaged rewarded policies, 2024

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.307466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5c25c3d-c1a6-4e36-a4ea-024a25c267d7 · outbound

This paper cites Warm: On the benefits of weight averaged reward models, 2024.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Warm: On the benefits of weight averaged reward models, 2024

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:01.867011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d6da3a41-b5bf-438e-a7b8-50564ac0918e · outbound

This paper cites Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:01.850062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0b795c10-9d72-4afb-9121-51894a263dde · outbound

This paper cites Offline regularised reinforcement learning for large language models alignment, 2024.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Offline regularised reinforcement learning for large language models alignment, 2024

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:01.834087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 18fb0222-e90a-43ce-9ef6-c3ceb3a0cfba · outbound

This paper cites Proximal Policy Optimization Algorithms.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Proximal Policy Optimization Algorithms

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.329871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94b50415-f300-4540-aae8-db9f96f76aee · outbound

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

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF BOND: Aligning LLMs with Best-of-N Distillation

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.335192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a72128c-6975-459e-8d5c-fba75b26620a · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.340582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbd4fdcf-3d6d-4e65-96e9-9abeffdcf289 · outbound

This paper cites Loose lips sink ships: Mitigating length bias in reinforcement learning from human feedback.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Loose lips sink ships: Mitigating length bias in reinforcement learning from human feedback

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:01.817025Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f0ccf053-ec92-44ca-8847-175f6aa45da3 · outbound

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

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF A Long Way to Go: Investigating Length Correlations in RLHF

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.360484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d44421d-76c1-4dc6-94a5-d28e21e8aac4 · outbound

This paper cites Ziegler, Ryan Lowe, Chelsea V oss, Alec Radford, Dario Amodei, and Paul Christiano.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Ziegler, Ryan Lowe, Chelsea V oss, Alec Radford, Dario Amodei, and Paul Christiano

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.365962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6973f78-33e7-4b84-83db-5d1a703a0c78 · outbound

This paper cites Learning to summarize with human feedback.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Learning to summarize with human feedback

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.370763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4a46a08-4386-4d1e-86f5-7e78004053c8 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context, 2024.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context, 2024

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:01.778601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 75dc0f5f-8422-4368-853e-d3a0f1184e20 · outbound

This paper cites Llama 2: Open foundation and fine-tuned chat models, 2023.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Llama 2: Open foundation and fine-tuned chat models, 2023

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.381925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff50780c-1bc8-4d80-824d-ddc9add43235 · outbound

This paper cites Attention is all you need.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Attention is all you need

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.386796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a4b8528-1e2e-42d9-8532-c0aef22b84d4 · outbound

This paper cites Reward hacking in reinforcement learning, Nov 2024.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Reward hacking in reinforcement learning, Nov 2024

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:01.738195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 08881065-5386-42bb-9196-9ca184a1626c · outbound

This paper cites Qwen2 technical report, 2024.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Qwen2 technical report, 2024

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:01.397242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe08b45c-ef18-4e96-8f0e-097c11063e79 · outbound

This paper cites Dapo: An open-source llm reinforcement learning system at scale, 2025.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Dapo: An open-source llm reinforcement learning system at scale, 2025

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:01.707100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 947656c9-9a9e-41d4-9a11-c51b5d8c3a15 · outbound

This paper cites From lists to emojis: How format bias affects model alignment, 2024.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF From lists to emojis: How format bias affects model alignment, 2024

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:01.686042Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b184816d-d7cd-4090-838b-07fa64a1387e · outbound

This paper cites Fine-tuning language models from human preferences, 2020.URL https://arxiv.

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF Fine-tuning language models from human preferences, 2020.URL https://arxiv

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:31:01.668211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Pith citing papers

Observation 83119876-bf91-4161-9c30-bee51499f1ec · inbound

Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges cites this paper.

Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges Bias Fitting to Mitigate Length Bias of Reward Model in RLHF

Reference 130

Resolution: verified exact; arxiv_id, observed 2026-06-25T02:17:29.855075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 01dc5012-628e-4f96-8630-5ab77989de2c · inbound

Rethinking the Comparison Unit in Sequence-Level Reinforcement Learning: An Equal-Length Paired Training Framework from Loss Correction to Sample Construction cites this paper.

Rethinking the Comparison Unit in Sequence-Level Reinforcement Learning: An Equal-Length Paired Training Framework from Loss Correction to Sample Construction Bias Fitting to Mitigate Length Bias of Reward Model in RLHF

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-06-25T02:17:29.855075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a1c70b58-51db-4535-98ad-f9d2cd75863d · inbound

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

Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure Bias Fitting to Mitigate Length Bias of Reward Model in RLHF

Reference 96

Resolution: verified exact; local_arxiv, observed 2026-06-29T12:23:24.213633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 12f1842d-a9bb-4ac9-a585-9b1f71f32c38 · inbound

Test-Time Scaling via Error Localization cites this paper.

Test-Time Scaling via Error Localization Bias Fitting to Mitigate Length Bias of Reward Model in RLHF

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T07:28:18.050097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.