发现大模型推理会降低推荐效果，提出新方法解决语言惯性问题
Why Thinking Hurts: Diagnosing and Rectifying Linguistic Inertia in Large Language Models for Recommendation
- 通过压缩推理链并去除语言偏见提升推荐准确性
- 在三大数据集上使推荐效果提升最高达25%
- 适合关注大模型推荐性能优化的研究者与工程师
链式思维（CoT）推理广泛用于提升大语言模型性能，近期基础推荐模型通过生成文本推理后预测目标项目（以语义ID表示）。然而我们发现，在OpenOneRec等模型中启用思考模式可使推荐质量下降高达25%。经分析，这源于‘语言惯性’：当插入文本推理段落后，模型更依赖自然语言上下文，而忽视历史语义ID证据。进一步分析显示，该现象在历史信息访问受限及推理链过长时被加剧。为此，我们提出无需训练的LICD框架，结合推理链压缩与偏见消除对比推理。在三个大规模基准测试上，LICD始终优于无思考和原始思考基线。
原文摘要 · Abstract (English)
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://anonymous.4open.science/r/LICD-4573.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。