基于证据而非仅凭理由进行推理：面向基于LLM的推荐的可验证偏好证明

中文摘要 AI 辅助

大型语言模型（LLM）能够从交互历史和评论中推断用户偏好，然而它们生成的推理理由可能并未反映实际用于推荐的信息。一个偏好声明可能缺乏其所选证据的有力支持，或者对最终排序几乎没有影响。我们将这两种失败称为“基础-影响差距”。我们提出了PROVE-REC，一个用于基于LLM的推荐中可验证偏好推理的通用框架。Pass A将完整的预目标历史转换为一个紧凑的偏好证明，该证明由与所选证据条目相关联的正面声明和回避声明组成。Pass B仅使用该证明及其所选证据来预测下一个项目，从而防止推荐器绕过推理路径。为了验证证据到证明的基础性，我们比较了遮蔽所选证据与遮蔽一个可比较的对照条目的效果。为了验证证明到推荐的影响性，我们移除一个偏好声明并测量目标项目排序边距的相应下降。一个排序保持目标进一步从完整历史中保留有用信息。在广泛真实世界数据集上的全面实验表明，PROVE-REC始终优于强大的序列、生成式和LLM增强基线，改进幅度最高达7.45%。受控消融实验确认了两阶段架构和验证目标的有效性。此外，PROVE-REC生成的声明更牢固地基于历史证据，对推荐更具影响力，同时保持了排序质量。

英文摘要

Large language models (LLMs) can infer user preferences from interaction histories and reviews, yet the rationales they generate may not reflect the information actually used for recommendation. A preference claim may be weakly supported by its selected evidence, or may have little effect on the final ranking. We refer to these two failures as the grounding-influence gap. We introduce PROVE-REC, a general framework for verifiable preference reasoning in LLM-based recommendation. Pass A converts the complete pre-target history into a compact preference proof consisting of positive and avoidance claims linked to selected evidence entries. Pass B predicts the next item using only the proof and its selected evidence, preventing the recommender from bypassing the reasoning path. To verify evidence-to-proof grounding, we compare the effect of masking selected evidence with masking a comparable control entry. To verify proof-to-recommendation influence, we remove a preference claim and measure the resulting decrease in the target item's ranking margin. A ranking-preservation objective further retains useful information from the complete history. Comprehensive experiments on wide-ranging real-world datasets demonstrate that PROVE-REC consistently outperforms strong sequential, generative, and LLM-enhanced baselines, with improvements of up to 7.45%. Controlled ablations confirm the effectiveness of the two-pass architecture and verification objectives. Moreover, PROVE-REC produces claims that are more strongly grounded in historical evidence and more influential to recommendation while preserving ranking quality.

发表机构

• Yonsei University（延世大学）
• Kyungpook National University（庆北国立大学）
• Sungkyunkwan University（成均馆大学）

机构由 AI 辅助整理，请以论文原文为准。