你会步行去洗车店吗？揭示大语言模型在常识推理中的显著性偏差

摘要

随着大语言模型（LLMs）在复杂推理任务上持续进步，它们学会了高度优先处理输入中提供的显式条件。然而，在日常常识推理中，这一机制暴露出一个关键漏洞，我们称之为“显著性偏差”：模型容易被无用的显式干扰项（如数值）所劫持，从而忽略任务隐含的物理或常识前提。一个关键开放问题是，这种失败究竟反映常识知识的真正缺失，还是仅仅反映其在误导性任务框架下的抑制。为探究此问题，我们构建了SaliTrap基准测试集，这是一个覆盖四个陷阱维度的高质量数据集。通过评估12个最先进的大语言模型，我们发现所有主流模型都显著受到显著性偏差的影响，其严重程度随干扰项密度增加而上升，且检测到陷阱与实际避开陷阱往往相互脱节。至关重要的是，通过在剥离任务框架后重新激发相同模型，我们表明这主要是知识抑制而非知识缺失：仅凭无上下文知识探针便可恢复超过90%的谄媚性顺从失败，揭示所需常识内在地存在，但被显著干扰项主动排挤——这些干扰项诱使模型进行过度顺从的不必要计算。基于这一诊断，我们进一步表明，仅使用轻量级的推理时提示，无需任何重新训练，即可大幅缩小差距。我们的发现将常识推理失败的瓶颈从模型能力重新定位到知识激发，并发布SaliTrap作为针对这一盲点的测试平台。代码可在https://github.com/Wuzheng02/SaliTrap获取。

English

As large language models (LLMs) continue to advance in complex reasoning tasks, they have learned to heavily prioritize explicit conditions provided in the input. However, in everyday commonsense reasoning, this mechanism exposes a critical vulnerability which we term Salience Bias: models become easily hijacked by useless explicit distractors (e.g., numerical values), leading them to ignore the implicit physical or commonsense prerequisites of a task. A critical open question is whether this failure reflects a genuine gap in commonsense knowledge or merely its suppression under misleading task framing. To investigate this, we construct the SaliTrap Benchmark, a high-quality dataset across four trap dimensions. Evaluating 12 state-of-the-art LLMs, we find that all mainstream models suffer significantly from salience bias, with severity scaling with distractor density and detecting the trap often decoupled from actually avoiding it. Crucially, by re-eliciting the same models with the task framing stripped away, we show that this is overwhelmingly a failure of knowledge suppression rather than knowledge absence: a context-free knowledge probe alone recovers over 90\% of sycophantic-compliance failures, revealing that the requisite commonsense is intrinsically present but actively crowded out by salient distractors that lure the model into over-compliant, unnecessary computation. Building on this diagnosis, we further show that lightweight, inference-time prompting alone substantially closes the gap without any retraining. Our findings relocate the bottleneck of commonsense reasoning failures from model competence to elicitation, and we release SaliTrap as a testbed for this blind spot. The codes are available at https://github.com/Wuzheng02/SaliTrap.