答案中心还是推理驱动？揭示大语言模型中的潜在记忆锚点
Answer-Centric or Reasoning-Driven? Uncovering the Latent Memory Anchor in LLMs
AI总结：
本研究通过五级答案可见性提示框架，实证揭示大语言模型推理主要锚定于最终答案而非推理链，掩盖答案导致性能下降26.90%，表明其推理多为事后合理化。
摘要：
尽管大语言模型（LLMs）展示了令人印象深刻的推理能力，但越来越多的证据表明，它们的成功很大程度上源于记忆化的答案-推理模式，而非真正的推理。在这项工作中，我们研究了一个核心问题：LLMs主要锚定于最终答案还是推理链的文本模式？我们提出了一个五级答案可见性提示框架，通过间接的行为分析系统地操纵答案线索并探测模型行为。在最新的大语言模型上的实验揭示了对显式答案的强烈且一致的依赖。当答案线索被掩盖时，即使推理链完整，性能也下降了26.90%。这些发现表明，LLMs展示的许多推理可能反映的是事后合理化而非真正的推理，这对其推理深度提出了质疑。我们的研究通过严格的实证验证揭示了答案锚定现象，并强调需要更细致地理解LLMs中推理的构成要素。
英文摘要：
While Large Language Models (LLMs) demonstrate impressive reasoning capabilities, growing evidence suggests much of their success stems from memorized answer-reasoning patterns rather than genuine inference. In this work, we investigate a central question: are LLMs primarily anchored to final answers or to the textual pattern of reasoning chains? We propose a five-level answer-visibility prompt framework that systematically manipulates answer cues and probes model behavior through indirect, behavioral analysis. Experiments across state-of-the-art LLMs reveal a strong and consistent reliance on explicit answers. The performance drops by 26.90\% when answer cues are masked, even with complete reasoning chains. These findings suggest that much of the reasoning exhibited by LLMs may reflect post-hoc rationalization rather than true inference, calling into question their inferential depth. Our study uncovers the answer-anchoring phenomenon with rigorous empirical validation and underscores the need for a more nuanced understanding of what constitutes reasoning in LLMs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
