Paper Citation Record · LEDGER

Reward Shaping to Mitigate Reward Hacking in RLHF

As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 22 inbound Pith citation observations for arXiv:2502.18770.

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

pith.paper-citation-record.v1
2502.18770 v6

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 22 of 22 standing notices

One-hop event checks from named stored sources.

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

measured 22 of 22 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:21:41.769204Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation d48a086d-209a-4c6b-8926-5cf6b54b797e · inbound

Supervising the search process produces reliable and generalizable information-seeking agents cites this paper.

Supervising the search process produces reliable and generalizable information-seeking agents Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-08-07T01:35:47.288139Z

Source-reported events for the cited work

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

Observation 58c6321b-7665-4423-8b27-86437a460e6d · inbound

From System 1 to System 2: A Survey of Reasoning Large Language Models cites this paper.

From System 1 to System 2: A Survey of Reasoning Large Language Models Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 170

Resolution: verified exact; arxiv_id, observed 2026-08-07T01:35:47.288139Z

Source-reported events for the cited work

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

Observation e947c3dd-4fd3-4e12-876b-9d57f2af9dbf · inbound

Enhancing Tool Learning in Large Language Models with Hierarchical Error Checklists cites this paper.

Enhancing Tool Learning in Large Language Models with Hierarchical Error Checklists Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:41.769204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c3df9b4-277a-4135-b4c4-75ffb9785030 · inbound

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

RewardAnything: Generalizable Principle-Following Reward Models Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T11:04:06.897214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1f2f615-d4f8-4f43-a686-c92943506c4b · inbound

Self-Rewarding Vision-Language Model via Reasoning Decomposition cites this paper.

Self-Rewarding Vision-Language Model via Reasoning Decomposition Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-08-07T01:35:47.288139Z

Source-reported events for the cited work

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

Observation 1e5c7b63-c8d2-41ef-ba7f-41347e6abf8c · inbound

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

Factored Causal Representation Learning for Robust Reward Modeling in RLHF Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-08-07T01:35:47.288139Z

Source-reported events for the cited work

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

Observation f423b48c-8cd7-4e5b-85fb-08c49e2b8e17 · 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 Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-08-07T01:35:47.288139Z

Source-reported events for the cited work

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

Observation e0aa7ce6-4486-46d5-b0d7-cff2b43fe244 · inbound

Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding cites this paper.

Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 31

Resolution: metadata mismatch; arxiv_id, observed 2026-08-07T01:35:47.288139Z

Source-reported events for the cited work

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

Observation a496afa7-0edb-44c0-95fa-ff04bd50f10b · inbound

Towards Robust LLM Post-Training: Automatic Failure Management for Reinforcement Fine-Tuning cites this paper.

Towards Robust LLM Post-Training: Automatic Failure Management for Reinforcement Fine-Tuning Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-08-07T01:35:47.288139Z

Source-reported events for the cited work

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

Observation 31879369-3523-4a1d-82b4-7a711302bdb3 · inbound

Optimal Transport for LLM Reward Modeling from Noisy Preference cites this paper.

Optimal Transport for LLM Reward Modeling from Noisy Preference Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 260

Resolution: metadata mismatch; arxiv_id, observed 2026-08-07T01:35:47.288139Z

Source-reported events for the cited work

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

Observation 28cb54ed-920c-419c-8d23-2482c8cc6dad · inbound

Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms cites this paper.

Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-08-07T01:35:47.288139Z

Source-reported events for the cited work

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

Observation 4409e985-2190-4e31-b2d7-ef560d706b26 · inbound

Variance-aware Reward Modeling with Anchor Guidance cites this paper.

Variance-aware Reward Modeling with Anchor Guidance Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 49

Resolution: metadata mismatch; arxiv_id, observed 2026-08-07T01:35:47.288139Z

Source-reported events for the cited work

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

Observation b3fc049c-ece3-453c-8748-63065fc9883b · inbound

Reward Hacking in Rubric-Based Reinforcement Learning cites this paper.

Reward Hacking in Rubric-Based Reinforcement Learning Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-08-07T01:35:47.288139Z

Source-reported events for the cited work

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

Observation c98675b8-a2c6-45e8-bd29-ddb4c5b20399 · inbound

Diagnosing Training Inference Mismatch in LLM Reinforcement Learning cites this paper.

Diagnosing Training Inference Mismatch in LLM Reinforcement Learning Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 51

Resolution: metadata mismatch; arxiv_id, observed 2026-08-07T01:35:47.288139Z

Source-reported events for the cited work

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

Observation f03a1e6c-f8f9-45b8-b88b-552164449677 · inbound

General Preference Reinforcement Learning cites this paper.

General Preference Reinforcement Learning Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-08-07T01:35:47.288139Z

Source-reported events for the cited work

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

Observation c4ec532b-ea35-4495-8772-1c98695e82ae · inbound

General Preference Reinforcement Learning cites this paper.

General Preference Reinforcement Learning Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-08-07T01:35:47.288139Z

Source-reported events for the cited work

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

Observation 67adf7ce-7aa5-4b17-8c48-c0279bdd6785 · inbound

General Preference Reinforcement Learning cites this paper.

General Preference Reinforcement Learning Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-08-07T01:35:47.288139Z

Source-reported events for the cited work

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

Observation 23180915-ff3b-4ee9-a737-6d9700bc46a9 · inbound

Representation-Aware Advantage Estimation: Your Reward Model Provides More Than A Scalar Output cites this paper.

Representation-Aware Advantage Estimation: Your Reward Model Provides More Than A Scalar Output Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 32

Resolution: metadata mismatch; arxiv_id, observed 2026-08-07T01:35:47.288139Z

Source-reported events for the cited work

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

Observation 542a30f0-8e1a-428d-8eaf-16dd502c6c43 · inbound

Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It cites this paper.

Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-08-07T01:35:47.288139Z

Source-reported events for the cited work

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

Observation f25422c1-50d3-4e78-8a25-94556b030c76 · inbound

From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning cites this paper.

From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-08-07T01:35:47.288139Z

Source-reported events for the cited work

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

Observation ae675e5a-4070-45e6-a112-598783ebdaa7 · inbound

Uncertainty-Aware Reward Modeling for Stable RLHF cites this paper.

Uncertainty-Aware Reward Modeling for Stable RLHF Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-08-07T01:35:47.288139Z

Source-reported events for the cited work

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

Observation 0c0ba185-f333-4895-adb9-702110f2cef1 · inbound

OPERA: Aligning Open-Ended Reasoning via Objective Perplexity-based Reinforcement Learning cites this paper.

OPERA: Aligning Open-Ended Reasoning via Objective Perplexity-based Reinforcement Learning Reward Shaping to Mitigate Reward Hacking in RLHF

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-08-07T01:35:47.288139Z

Source-reported events for the cited work

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