AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis

Darshan Girish Deshpande, Anand Kannappan, Rebecca Qian

ICML 2026 · Large language models › Language, safety and interpretability · approach: Data and hallucination detection · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
evaluate in contrastive cluster setting instead of isolated classification (ablation)GPT-5.2 · TRACEDetection Rate: 45% -> 63%Improved
increase cluster size from N=1 to N=10 (ablation)Claude-4.5-Opus · TRACEDetection Rate: 34% absolute differenceImproved
increase cluster size from N=1 to N=5 (ablation)all evaluated LLMs · TRACEMatch Rate: approximately 35% Match Rate improvementImproved
increase cluster size from N=5 to N=10 (ablation)all evaluated LLMs · TRACEMatch RateNo clear effect
increase benign ratio from 25% to 90% (ablation)all evaluated LLMs · TRACEMatch RateImproved
semantic rather than syntactic reward hack categoriesevaluated LLMs · TRACEMatch Rate: 0.6-0.95 -> 0.0-0.4Hurt
provide ground truth to the LLM judge instead of comparative matching (ablation)LLM judge · TRACEMatch Rate (judge)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy