Hugging Face Trending Papers

Cheap Reward Hacking Detection

Read the original on Hugging Face Trending Papers →

A small transformer encoder is trained to map Terminal-Wrench trajectories onto a unit sphere where embedding distance approximates the $L_1$ distance between reward and metadata signals. A linear probe on top of that embedding detects reward hacking on the cleaned test split with AUC $0.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI
Jun 9

Cheap Reward Hacking Detection

arXiv:2606. 08893v1 Announce Type: cross Abstract: A small transformer encoder is trained to map Terminal-Wrench trajectories onto a unit sphere where embedding distance approximates the $L_1$ distance between reward and metadata signals.

By Iv\'an Belenky, Joaqu\'in Itria, Steven Johns
arXiv Machine Learning
Jun 25

Do Prompt-Elicited Trajectories Reflect Training-Time Reward Hacking? A Systematic Study on Monitoring Trainig-Time Reward Hacking in Code Generation

arXiv:2604. 23488v2 Announce Type: replace Abstract: Reward hacking in code generation, where models exploit evaluation loopholes to obtain high reward without correctly solving the intended task, poses a critical challenge for Reinforcement Learning (RL) and the deployment of reasoning models.

By Lichen Li, Hengguang Zhou, Yijun Liang, Tianyi Zhou, Cho-Jui Hsieh
arXiv Machine Learning
Aug 4

Do Prompt-Elicited Trajectories Reflect Training-Time Reward Hacking? A Systematic Study on Monitoring Training-Time Reward Hacking in Code Generation

arXiv:2604. 23488v3 Announce Type: replace Abstract: Reward hacking in code generation, where models exploit evaluation loopholes to obtain high reward without correctly solving the intended task, poses a critical challenge for Reinforcement Learning (RL) and the deployment of reasoning models.

By Lichen Li, Hengguang Zhou, Yijun Liang, Tianyi Zhou, Cho-Jui Hsieh
Hugging Face Trending Papers
Jul 29

Borrowed Strength: Best-of-N Search over a Code EncodingBreaks Self-Check Jailbreak Defenses

A self-check defense asks the target model to assess a request before answering it; SAGE, the strongest published instance, reports an average 99% defense success rate. We show it can be breached by composing two attacks that are individually harmless against it: an established code-completion encoding and an established best-of-N search, neither of which exceeds 4.