← Back to all news
arXiv AI By Erfan Shahabi, Amirhossein Roshandel, Mohammad Sadegh Sadeghi, Azadeh Shakery

SimInter: Evidence-Grounded User Simulation with Interview-Based Profile Enrichment for Conversational Recommender Systems

Read the original on arXiv AI →

SimInter is a pipeline that enriches user profiles for conversational recommender systems by conducting synthetic interviews between two large language model agents, grounded in users’ statistical profiles and historical conversational evidence. An audit agent flags potential fabrication and stereotyping at each turn before enrichment. In experiments on movie recommendation, SimInter significantly increases the diversity of expressed preference aspects and improves simulator performance with two recommenders, with high human agreement on enriched attributes and auditor decisions.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 3

The Utility of LLMs in Recommender Systems Explanation Evaluation

The paper investigates how large language models (LLMs) can evaluate explanations in recommender systems. It generates 18 explanation prototypes and has 14 LLMs rate them, comparing the results to human ratings from a user study. Findings show that while LLMs mimic human rating patterns and correlate moderately with human judgments, their absolute agreement is low and varies with model size and evaluation design, leading to four practical recommendations for using LLMs in this context.

By Kathrin Wardatzky, Oana Inel, Luca Rossetto, Abraham Bernstein
llms
More like this →
arXiv Computation and Language
Oct 5

CUEing User Simulators: Calibrated User Embeddings for Multi-Turn Benchmarking

The paper introduces Calibrated User Embeddings (CUE), a framework that encodes real user sessions into continuous representations and decodes them into persona commands to steer large language models (LLMs) as user simulators without additional training. CUE enables user-conditioned replay of past interactions and generates novel personas that better align with real-user success rates and failure patterns. Evaluations on the τ²‑Bench dataset show that CUE‑driven simulators commit fewer simulator‑attributed errors, more accurately reproduce real‑user failure modes, and maintain competitive user fidelity across various tasks and LLMs.

By Anjali Kantharuban, Jonas Mueller
llmsragagentsbenchmarkssafety
More like this →