arXiv：cs.AI· Yeo Chan Yoon, Chanjun Park, Kyuhan Koh·· 4 小时前AI 评分33
ASER：通过评论蒸馏表示实现感官感知的序列推荐
Sensory-Aware Sequential Recommendation via Review-Distilled Representations
AI 导读
ASER 是一个离线流水线，通过微调大语言模型从评论文本中提取有证据支撑的感官属性-值记录（如 color: matte black），并蒸馏进紧凑的学生编码器，为每个商品目录生成冻结的五维感官库。
正文
Abstract:Sequential recommenders learn behavioral patterns from item identifiers, while the experiential properties that users describe in reviews, such as how products look, feel, smell, taste, or sound, rarely enter item representations in a controlled, auditable form.
We present ASER (Attribute-based Sensory-Enhanced Representation), an offline pipeline that fine-tunes a large language model to extract evidence-grounded sensory attribute-value records, such as color: matte black or scent: vanilla, from review text and distills them into a compact student encoder that produces a frozen five-facet sensory bank for each item catalog.
At recommendation time the pretrained backbone stays frozen: a lightweight relational metric between the user history and each candidate is learned over the bank, and its correction is applied within a validation-selected magnitude bound.
Across five Amazon domains and four backbones, trained within a common experimental pipeline and evaluated by full-catalog leave-one-out ranking without sampled negatives, this integration improves HR@10 and NDCG@10 in all 20 domain-backbone pairs, with average relative gains of 6.1% and 6.4%.
A matched non-sensory control channel, built with the same seed model, schema, and pipeline, separates the sources of the gain: the hit-rate improvement follows from structured, evidence-grounded extraction as such, whereas the sensory vocabulary yields a ranking-quality advantage in eight of nine matched comparisons.
An audit of the Beauty evaluation catalog finds that 94.8% of retained records are supported by their cited evidence spans, so the extracted signal remains inspectable against its source text.
| Comments: | Accepted for publication in Knowledge-Based Systems. The Version of Record is available at this https URL |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2603.02709 [cs.CL] |
| (or arXiv:2603.02709v4 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2603.02709 arXiv-issued DOI via DataCite |
|
| Related DOI: | https://doi.org/10.1016/j.knosys.2026.117071
DOI(s) linking to related resources |
Submission history
From: Yeochan Yoon [view email]
[v1]
Tue, 3 Mar 2026 08:00:34 UTC (37 KB)
[v2]
Fri, 24 Apr 2026 10:56:08 UTC (717 KB)
[v3]
Tue, 28 Apr 2026 02:34:16 UTC (728 KB)
[v4]
Fri, 2 Oct 2026 10:29:56 UTC (1,358 KB)
来源：arXiv：cs.AI · arxiv.org