测试大模型在质疑下的稳定性，发现部分模型会无理由改答案
Certainty robustness: Evaluating LLM stability under self-challenging prompts
- 设计双轮问答框架，模拟用户质疑场景
- 200道题测试中，30%模型正确答案被错误修改
- 强调模型自信度与回答一致性，适合评估真实对话可靠性
大语言模型常以高置信度输出答案，但缺乏对自身确定性的显式推理机制。现有基准多关注单轮准确率、真实性或置信度校准，未涵盖交互场景下模型面对质疑时的表现。我们提出Certainty Robustness Benchmark，一个两轮评估框架，通过不确定性提问（如“你确定吗？”）和直接反驳（如“你错了！”）等自挑战提示，结合数值置信度获取，评估模型在交互中的稳定性和适应性。基于LiveBench的200道推理与数学题，我们评估了四款前沿LLM，区分了合理自修正与不合理答案变更。结果揭示：模型间交互可靠性差异显著，仅靠基线准确率无法解释；部分模型在对话压力下放弃正确答案，而另一些则表现出强抗质疑能力，且置信度与正确性更一致。这表明，确定性鲁棒性是衡量模型对齐性、可信度及实际部署价值的关键新维度。
原文摘要 · Abstract (English)
Large language models (LLMs) often present answers with high apparent confidence despite lacking an explicit mechanism for reasoning about certainty or truth. While existing benchmarks primarily evaluate single-turn accuracy, truthfulness or confidence calibration, they do not capture how models behave when their responses are challenged in interactive settings. We introduce the Certainty Robustness Benchmark, a two-turn evaluation framework that measures how LLMs balance stability and adaptability under self-challenging prompts such as uncertainty ("Are you sure?") and explicit contradiction ("You are wrong!"), alongside numeric confidence elicitation. Using 200 reasoning and mathematics questions from LiveBench, we evaluate four state-of-the-art LLMs and distinguish between justified self-corrections and unjustified answer changes. Our results reveal substantial differences in interactive reliability that are not explained by baseline accuracy alone: some models abandon correct answers under conversational pressure, while others demonstrate strong resistance to challenge and better alignment between confidence and correctness. These findings identify certainty robustness as a distinct and critical dimension of LLM evaluation, with important implications for alignment, trustworthiness and real-world deployment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。