Flipping the Dialogue: Training and Evaluating User Language Models

• URL: http://arxiv.org/abs/2510.06552v1
• Date: Wed, 08 Oct 2025 01:04:36 GMT
• Title: Flipping the Dialogue: Training and Evaluating User Language Models
• Authors: Tarek Naous, Philippe Laban, Wei Xu, Jennifer Neville,
• Abstract summary: We introduce purpose-built User Language Models (User LMs)<n>User LMs are models post-trained to simulate human users in multi-turn conversations.<n>We show how User LMs align better with human behavior and achieve better simulation robustness than existing simulation methods.
• Score: 31.119620506835677
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Conversations with LMs involve two participants: a human user leading the conversation, and an LM assistant responding to the user's request. To satisfy this specific role, LMs are post-trained to be helpful assistants -- optimized to produce exhaustive and well-structured responses, free of ambiguity and grammar errors. User utterances, on the other hand, are rarely perfected, with each user phrasing requests in unique ways, sometimes putting in partial effort at each turn and refining on the fly. To evaluate LM performance in realistic settings, prior work simulated users in multi-turn conversations, often prompting an LLM originally trained to be a helpful assistant to act as a user. However, we show that assistant LMs make for poor user simulators, with the surprising finding that better assistants yield worse simulators. Instead, we introduce purpose-built User Language Models (User LMs) - models post-trained to simulate human users in multi-turn conversations. Through various evaluations, we show how User LMs align better with human behavior and achieve better simulation robustness than existing simulation methods. When leveraging User LMs to simulate coding and math conversations, the performance of a strong assistant (GPT-4o) drops from 74.6% to 57.4%, confirming that more realistic simulation environments lead to assistant struggles as they fail to cope with the nuances of users in multi-turn setups.

Related papers

• Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning [52.07170679746533]
  Large Language Models (LLMs) are increasingly used to simulate human users in interactive settings such as therapy, education, and social role-play.<n>We introduce a unified framework for evaluating and improving persona consistency in LLM-generated dialogue.<n>We define three automatic metrics: prompt-to-line consistency, line-to-line consistency, and Q&A consistency, that capture different types of persona drift and validate each against human annotations.
  arXiv  Detail & Related papers  (2025-10-31T19:40:41Z)
• SimulatorArena: Are User Simulators Reliable Proxies for Multi-Turn Evaluation of AI Assistants? [61.07963107032645]
  Large language models (LLMs) are increasingly used in interactive applications.<n>Human evaluation remains the gold standard for assessing their performance in multi-turn conversations.<n>We introduce SimulatorArena, a benchmark of 909 annotated human-LLM conversations on two interactive tasks.
  arXiv  Detail & Related papers  (2025-10-06T23:17:44Z)
• Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles [37.43150003866563]
  We introduce the User Simulator with Implicit Profiles (USP), a framework that infers implicit user profiles from human-machine interactions to simulate personalized and realistic dialogues.<n>USP outperforms strong baselines in terms of authenticity and diversity while maintaining comparable consistency.
  arXiv  Detail & Related papers  (2025-02-26T09:26:54Z)
• DuetSim: Building User Simulator with Dual Large Language Models for Task-Oriented Dialogues [7.765092134290888]
  This paper introduces DuetSim, a novel framework designed to address the intricate demands of task-oriented dialogues by leveraging large language models. DuetSim stands apart from conventional approaches by employing two LLMs in tandem: one dedicated to response generation and the other focused on verification. We validate the efficacy of our method through extensive experiments conducted on the MultiWOZ dataset, highlighting improvements in response quality and correctness.
  arXiv  Detail & Related papers  (2024-05-16T06:24:31Z)
• How Reliable is Your Simulator? Analysis on the Limitations of Current LLM-based User Simulators for Conversational Recommendation [14.646529557978512]
  We analyze the limitations of using Large Language Models in constructing user simulators for Conversational Recommender System. Data leakage, which occurs in conversational history and the user simulator's replies, results in inflated evaluation results. We propose SimpleUserSim, employing a straightforward strategy to guide the topic toward the target items.
  arXiv  Detail & Related papers  (2024-03-25T04:21:06Z)
• MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback [78.60644407028022]
  We introduce MINT, a benchmark that evaluates large language models' ability to solve tasks with multi-turn interactions. LLMs generally benefit from tools and language feedback, with performance gains of 1-8% for each turn of tool use. LLMs evaluated, supervised instruction-finetuning (SIFT) and reinforcement learning from human feedback (RLHF) generally hurt multi-turn capabilities.
  arXiv  Detail & Related papers  (2023-09-19T15:25:42Z)
• Unlocking the Potential of User Feedback: Leveraging Large Language Model as User Simulator to Enhance Dialogue System [65.93577256431125]
  We propose an alternative approach called User-Guided Response Optimization (UGRO) to combine it with a smaller task-oriented dialogue model. This approach uses LLM as annotation-free user simulator to assess dialogue responses, combining them with smaller fine-tuned end-to-end TOD models. Our approach outperforms previous state-of-the-art (SOTA) results.
  arXiv  Detail & Related papers  (2023-06-16T13:04:56Z)
• User Behavior Simulation with Large Language Model based Agents [116.74368915420065]
  We propose an LLM-based agent framework and design a sandbox environment to simulate real user behaviors. Based on extensive experiments, we find that the simulated behaviors of our method are very close to the ones of real humans.
  arXiv  Detail & Related papers  (2023-06-05T02:58:35Z)
• Metaphorical User Simulators for Evaluating Task-oriented Dialogue Systems [80.77917437785773]
  Task-oriented dialogue systems ( TDSs) are assessed mainly in an offline setting or through human evaluation. We propose a metaphorical user simulator for end-to-end TDS evaluation, where we define a simulator to be metaphorical if it simulates user's analogical thinking in interactions with systems. We also propose a tester-based evaluation framework to generate variants, i.e., dialogue systems with different capabilities.
  arXiv  Detail & Related papers  (2022-04-02T05:11:03Z)
• Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition [64.06167416127386]
  We propose Multi-Agent Dialog Policy Learning, which regards both the system and the user as the dialog agents. Two agents interact with each other and are jointly learned simultaneously. Results show that our method can successfully build a system policy and a user policy simultaneously.
  arXiv  Detail & Related papers  (2020-04-08T04:51:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.