思考慣性：大型語言模型在被要求不要思考時仍持續思考

Thinking Inertia: LLMs Keep Thinking When Told Not To

October 8, 2026

作者: Dianqiao Lei, Kevin Qinghong Lin, Pan Lu, Philip Torr, James Zou

cs.AI

摘要

大型語言模型（LLMs）日益配備明確的「思考模式」，但其對應的「不思考」卻鮮少受到關注。我們從兩個軸向研究 LLMs 的不思考行為。 a. 如何衡量不思考？先前研究通常透過代理指標來定義不思考，例如停用思考模式或缺乏長軌跡。這些代理指標並不可靠：停用的思考模式仍可能產生推理，而長軌跡可能包含填充內容而非真正的推理。我們改為將每個回應正規化為答案前軌跡與最終答案，並從三個層級進行評估：(i) 空思考率，用於評估嚴格的僅答案遵循度；(ii) 指令感知的問題-答案前軌跡相關性，用於衡量問題與答案前軌跡之間的相似度；以及 (iii) LLM 作為評審的顯式推理率，用於評估可見的顯式推理。這些指標共同區分僅答案輸出、相關但非推理的文本，以及顯式推理。 b. 不思考在不同任務與模型之間如何變化？我們在六個 LLMs 上評估六種提示干預，涵蓋布林、選擇題和開放式問題。我們發現，明確的不思考控制無法可靠地消除可見的推理。模型反而表現出「思考慣性」：即使在嚴格控制下，顯式推理仍然存在，並且隨著答案空間開放而變得更加普遍。在布林和選擇題任務上，準確率保持穩定，而開放式任務則揭示了僅答案遵循度與任務準確率之間的取捨。在不同答案空間重寫相同問題顯示，提供候選答案可使僅答案回應更容易產生。這些發現確立了不思考是一項非平凡的能力：停止顯式推理不能僅從模型設定或指令中假定，並且值得與推理能力一併進行系統性評估。

English

Large Language Models (LLMs) increasingly ship with explicit "thinking modes", yet their counterpart, "no-thinking", has received far less attention. We study LLMs' no-thinking behavior along two axes. a. How to measure no-thinking? Prior work typically defines no-thinking through proxies such as a disabled thinking mode or the absence of long traces. These proxies are unreliable: disabled thinking modes may still emit reasoning, while long traces may contain filler rather than genuine inference. We instead normalize each response into a pre-answer trace and final answer, and evaluate it at three levels: (i) Empty-Thinking Rate for strict answer-only compliance; (ii) instruction-aware Question-Pre-answer Relevance for similarity between the question and pre-answer trace; and (iii) LLM-as-judge Explicit Inference Rate for visible explicit inference. Together, these metrics distinguish answer-only output, relevant but non-inferential text, and explicit inference. b. How does no-thinking vary across tasks and models? We evaluate six prompting interventions on six LLMs across Boolean, multiple-choice, and open-ended questions. We find that explicit no-think controls cannot reliably eliminate visible inference. Models instead exhibit "Thinking Inertia": explicit inference persists even under strict controls and becomes more prevalent as the answer space opens. Accuracy remains stable on Boolean and multiple-choice tasks, whereas open-ended tasks reveal a trade-off between answer-only compliance and task accuracy. Rewriting the same questions across answer spaces shows that supplying candidate answers makes answer-only responses easier to produce. These findings establish no-thinking as a non-trivial capability: stopping explicit reasoning cannot be assumed from model settings or instructions alone and deserves systematic evaluation alongside reasoning ability.