The reviewed record of science sign in
Pith

arxiv: 2505.19690 · v1 · pith:3ZLJYRNO · submitted 2025-05-26 · cs.AI

Beyond Safe Answers: A Benchmark for Evaluating True Risk Awareness in Large Reasoning Models

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:3ZLJYRNOrecord.jsonopen to challenge →

classification cs.AI
keywords reasoningsafetymodelsrisksafebenchmarklrmsanswers
0
0 comments X
read the original abstract

Despite the remarkable proficiency of \textit{Large Reasoning Models} (LRMs) in handling complex reasoning tasks, their reliability in safety-critical scenarios remains uncertain. Existing evaluations primarily assess response-level safety, neglecting a critical issue we identify as \textbf{\textit{Superficial Safety Alignment} (SSA)} -- a phenomenon where models produce superficially safe outputs while internal reasoning processes fail to genuinely detect and mitigate underlying risks, resulting in inconsistent safety behaviors across multiple sampling attempts. To systematically investigate SSA, we introduce \textbf{Beyond Safe Answers (BSA)} bench, a novel benchmark comprising 2,000 challenging instances organized into three distinct SSA scenario types and spanning nine risk categories, each meticulously annotated with risk rationales. Evaluations of 19 state-of-the-art LRMs demonstrate the difficulty of this benchmark, with top-performing models achieving only 38.0\% accuracy in correctly identifying risk rationales. We further explore the efficacy of safety rules, specialized fine-tuning on safety reasoning data, and diverse decoding strategies in mitigating SSA. Our work provides a comprehensive assessment tool for evaluating and improving safety reasoning fidelity in LRMs, advancing the development of genuinely risk-aware and reliably safe AI systems.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments

    cs.CL 2025-08 unverdicted novelty 6.0

    ReasoningGuard is an inference-time method that uses attention mechanisms to inject safety aha moments and scaling sampling to defend large reasoning models against jailbreak attacks.