arXiv：cs.AI· Erfan Shahabi, Amirhossein Roshandel, Mohammad Sadegh Sadeghi, Azadeh Shakery·· 20 小时前
SimInter：基于访谈式画像增强的证据接地用户模拟，用于对话推荐系统
SimInter: Evidence-Grounded User Simulation with Interview-Based Profile Enrichment for Conversational Recommender Systems
AI 导读
SimInter 通过两个 LLM 智能体之间的合成访谈，结合用户统计画像与历史对话证据，补全决策风格、方面级偏好和领域专长等隐式行为特征，并在画像增强前由审计智能体逐轮标记潜在的编造与刻板印象。
正文
Abstract:Conversational Recommender Systems (CRSs) require reliable user simulators for cost-effective evaluation. LLM-based simulators have made realistic simulation possible but typically condition on profiles derived from explicit ratings, demographics, and static sources capturing surface preferences while omitting implicit behavioral characteristics such as decision-making style, aspect-level preferences, and domain expertise. We propose SimInter, a pipeline that elicits these attributes via synthetic interviews between two LLM agents, grounded in the user's statistical profile and historical conversational evidence. Before profile enrichment, an audit agent explicitly flags potential fabrication and stereotyping at the turn level. We instantiate and evaluate SimInter on movie recommendation. We simulate 300 ReDial users and, on a matched subset of 100 users, compare SimInter with a statistics-only baseline: SimInter significantly increases the diversity of expressed preference aspects (filtered aspect entropy: 1.619 vs. 0.859; paired d = 0.96, Holm-adjusted p < 0.001). This gain persists when the simulator converses with two trained recommenders, KBRD and UniCRS, under two independent evaluation judges (+0.28 to +0.56 nats; all p < 0.001). Human evaluation finds 94.3% of enriched-attribute claims supported or partially supported, while human judgments agree with 95.2% of the auditor's binary filtering decisions on a stratified sample.
| Comments: | 25 pages, 11 figures, 12 tables. Erfan Shahabi and Amirhossein Roshandel contributed equally |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR) |
| ACM classes: | I.2.7; H.3.3 |
| Cite as: | arXiv:2610.18308 [cs.CL] |
| (or arXiv:2610.18308v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18308 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Amirhossein Roshandel [view email]
[v1]
Tue, 13 Oct 2026 12:52:35 UTC (651 KB)
来源：arXiv：cs.AI · arxiv.org