arXiv：cs.AI· Yu Hou, Nathaniel Kang, Pengkai Wang, Hua Li·· 5 小时前AI 评分33
PROVE-REC：为 LLM 推荐生成可验证偏好证明，而非仅凭理由
Reasoning with Evidence, Not Merely Rationales: Verifiable Preference Proofs for LLM-Based Recommendation
AI 导读
PROVE-REC 是一个面向 LLM 推荐的可验证偏好推理框架，通过 Pass A 将完整历史转为带证据的偏好证明、Pass B 仅凭证明预测下一物品，以弥合"依据-影响"鸿沟。在多个真实数据集上，它比序列、生成及 LLM 增强基线最高提升 7.45%，消融实验验证了两阶段架构与验证目标的有效性。
正文
Abstract: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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.02968 [cs.AI] |
| (or arXiv:2610.02968v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02968 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yu Hou [view email]
[v1]
Fri, 2 Oct 2026 08:05:43 UTC (3,173 KB)
来源：arXiv：cs.AI · arxiv.org