为什么思考有害：诊断并纠正大型语言模型在推荐中的语言惯性
Why Thinking Hurts: Diagnosing and Rectifying Linguistic Inertia in Large Language Models for Recommendation
AI总结：
本文发现链式思维推理在推荐模型中会导致性能下降，归因于语言惯性，并提出无需训练的语言惯性校准解码（LICD）框架，通过推理链压缩和偏差相减对比推理来缓解该问题。
摘要：
链式思维（CoT）推理被广泛用于提高LLM性能，最近的基础推荐模型通过在生成由语义ID（SID）表示的目标项目之前生成文本推理来采用它。然而，我们观察到在OpenOneRec等模型中启用思考模式会使推荐质量下降高达25%。我们调查了这一失败并确定了语言惯性：当在SID生成之前插入文本CoT段时，模型更依赖自然语言上下文，而较少依赖历史SID证据。进一步分析表明，这种效应因历史信息访问减少和CoT长度增加而放大。为了缓解它，我们提出了语言惯性校准解码（LICD），这是一个无需训练的框架，结合了推理链压缩和偏差相减对比推理。在三个大规模基准上的实验表明，LICD始终优于无思考和原始思考基线。我们的代码可在https://anonymous.4open.science/r/LICD-4573获取。
英文摘要：
Chain-of-Thought (CoT) reasoning is widely used to improve LLM performance, and recent foundation recommender models adopt it by generating textual reasoning before predicting target items represented by Semantic IDs (SIDs). However, we observe that enabling thinking mode in models such as OpenOneRec can degrade recommendation quality by up to 25%. We investigate this failure and identify Linguistic Inertia: when a textual CoT segment is inserted before SID generation, the model relies more on natural-language context and less on historical SID evidence. Further analyses show that this effect is amplified by reduced access to historical information and longer CoT lengths. To mitigate it, we propose Linguistic-Inertia-Calibrated Decoding (LICD), a training-free framework that combines Reasoning-Chain Compression and Bias-Subtracted Contrastive Inference. Experiments on three large-scale benchmarks show that LICD consistently outperforms both no-thinking and original-thinking baselines. Our code is available at https://github.com/USTC-StarTeam/LICD.
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。
