Answer or Reasoning: Where is the LLM's Memory Anchor?

ACL ARR 2025 May Submission6908 Authors

Abstract: 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.

Paper Type: Long

Research Area: Interpretability and Analysis of Models for NLP

Research Area Keywords: Memorization or Reasoning; Reasoning LLMs

Contribution Types: Model analysis & interpretability

Languages Studied: Chinese; English

Submission Number: 6908