HarmThoughts: A Benchmark for Fine-Grained Harmful Behavior Detection in Reasoning Traces
Large reasoning models (LRMs) produce complex, multi-step reasoning traces, yet safety evaluation remains focused on final outputs, overlooking how harm emerges during reasoning. When jailbroken, harm does not appear instantaneously but unfolds through distinct behavioral steps such as suppressing refusal, rationalizing compliance, decomposing harmful tasks, and concealing risk. However, no existing benchmark captures this process at sentence-level granularity within reasoning traces -- a key step toward reliable safety monitoring, interventions, and systematic failure diagnosis. To address this gap, we introduce HarmThoughts, a benchmark for step-wise safety evaluation of reasoning trace...
| Authors | Ishita Kakkar, Enze Zhang, Rheeya Uppaal et al. |
|---|---|
| Primary category | cs.CL |
| Published | 21 April 2026 |
| Last updated at source | 11 August 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.