English
Related papers

Related papers: How to Build User Simulators to Train RL-based Dia…

200 papers

Dialog management (DM) is a crucial component in a task-oriented dialog system. Given the dialog history, DM predicts the dialog state and decides the next action that the dialog agent should take. Recently, dialog policy learning has been…

Computation and Language · Computer Science 2021-10-26 Yinpei Dai , Huihua Yu , Yixuan Jiang , Chengguang Tang , Yongbin Li , Jian Sun

Resources for simulation-based evaluation of conversational recommender systems (CRSs) are scarce. The UserSimCRS toolkit was introduced to address this gap. In this work, we present UserSimCRS v2, a significant upgrade aligning the toolkit…

Information Retrieval · Computer Science 2026-03-18 Nolwenn Bernard , Krisztian Balog

In this study, we explore the application of Large Language Models (LLMs) for generating synthetic users and simulating user conversations with a task-oriented dialogue system and present detailed results and their analysis. We propose a…

Computation and Language · Computer Science 2025-02-19 Adnan Ahmad , Stefan Hillmann , Sebastian Möller

Large language models (LLMs) have achieved remarkable breakthroughs in new dialogue capabilities by leveraging instruction tuning, which refreshes human impressions of dialogue systems. The long-standing goal of dialogue systems is to be…

Computation and Language · Computer Science 2024-04-01 Jiao Ou , Junda Lu , Che Liu , Yihong Tang , Fuzheng Zhang , Di Zhang , Kun Gai

Recommender systems have been widely applied in different real-life scenarios to help us find useful information. In particular, Reinforcement Learning (RL) based recommender systems have become an emerging research topic in recent years,…

Information Retrieval · Computer Science 2023-06-13 Yuanguo Lin , Yong Liu , Fan Lin , Lixin Zou , Pengcheng Wu , Wenhua Zeng , Huanhuan Chen , Chunyan Miao

The recent paradigm shift toward large reasoning models (LRMs) as autonomous agents has intensified the demand for sophisticated, multi-turn tool-use capabilities. Yet, existing datasets and data-generation approaches are limited by static,…

Computation and Language · Computer Science 2026-01-14 Jungho Cho , Minbyul Jeong , Sungrae Park

This paper reports on progress towards building an online language learning tool to provide learners with conversational experience by using dialog systems as conversation practice partners. Our system can adapt to users' language…

Computation and Language · Computer Science 2022-08-02 Yu Li , Chun-Yen Chen , Dian Yu , Sam Davidson , Ryan Hou , Xun Yuan , Yinghua Tan , Derek Pham , Zhou Yu

User simulators are essential to conversational AI, enabling scalable agent development and evaluation through simulated interactions. While current Large Language Models (LLMs) have advanced user simulation capabilities, we reveal that…

Computation and Language · Computer Science 2026-03-10 Shuhaib Mehri , Xiaocheng Yang , Takyoung Kim , Gokhan Tur , Shikib Mehri , Dilek Hakkani-Tür

As the recent Large Language Models(LLM's) become increasingly competent in zero-shot and few-shot reasoning across various domains, educators are showing a growing interest in leveraging these LLM's in conversation-based tutoring systems.…

Human-Computer Interaction · Computer Science 2024-03-22 Minju Park , Sojung Kim , Seunghyun Lee , Soonwoo Kwon , Kyuseok Kim

In this paper, an attempt is made to systematically discuss the development of simulation systems for manufacturing system design. General requirements on manufacturing simulators are formulated and a framework to address the requirements…

Computational Engineering, Finance, and Science · Computer Science 2007-05-23 V. V. Kryssanov , V. A. Abramov , H. Hibino , Y. Fukuda

User simulators (USs) are commonly used to train task-oriented dialogue systems (DSs) via reinforcement learning. The interactions often take place on semantic level for efficiency, but there is still a gap from semantic actions to natural…

Computation and Language · Computer Science 2022-08-24 Hsien-Chin Lin , Christian Geishauser , Shutong Feng , Nurul Lubis , Carel van Niekerk , Michael Heck , Milica Gašić

Learning therapeutic counseling involves significant role-play experience with mock patients, with current manual training methods providing only intermittent granular feedback. We seek to accelerate and optimize counselor training by…

Human-Computer Interaction · Computer Science 2025-02-27 Ian Steenstra , Farnaz Nouraei , Timothy W. Bickmore

While modern dialogue systems heavily rely on large language models (LLMs), their implementation often goes beyond pure LLM interaction. Developers integrate multiple LLMs, external tools, and databases. Therefore, assessment of the…

Artificial Intelligence · Computer Science 2025-07-23 Roman Mayr , Michel Schimpf , Thomas Bohné

Automatic dialogue response evaluator has been proposed as an alternative to automated metrics and human evaluation. However, existing automatic evaluators achieve only moderate correlation with human judgement and they are not robust. In…

Computation and Language · Computer Science 2020-04-27 Tianyu Zhao , Divesh Lala , Tatsuya Kawahara

Accurate and verifiable large language model (LLM) simulations of human research subjects promise an accessible data source for understanding human behavior and training new AI systems. However, results to date have been limited, and few…

Human-Computer Interaction · Computer Science 2025-06-06 Jacy Reese Anthis , Ryan Liu , Sean M. Richardson , Austin C. Kozlowski , Bernard Koch , James Evans , Erik Brynjolfsson , Michael Bernstein

Language models are increasingly being deployed as user simulators, but their memory is far more reliable than that of real users. To measure this gap, we run a series of classic memory experiments from psychology on both humans and…

Computation and Language · Computer Science 2026-05-26 Qihan Wang , Nicholas Tomlin , Michael Hu , Brian Dillon , Tal Linzen

Large language models (LLMs) are essential tools that users employ across various scenarios, so evaluating their performance and guiding users in selecting the suitable service is important. Although many benchmarks exist, they mainly focus…

Computation and Language · Computer Science 2024-09-23 Jiayin Wang , Fengran Mo , Weizhi Ma , Peijie Sun , Min Zhang , Jian-Yun Nie

When assisting human users in reinforcement learning (RL), we can represent users as RL agents and study key parameters, called \emph{user traits}, to inform intervention design. We study the relationship between user behaviors (policy…

Machine Learning · Computer Science 2023-07-18 L. L. Ankile , B. S. Ham , K. Mao , E. Shin , S. Swaroop , F. Doshi-Velez , W. Pan

Effective tool use is essential for large language models (LLMs) to interact with their environment. However, progress is limited by the lack of efficient reinforcement learning (RL) frameworks specifically designed for tool use, due to…

Computation and Language · Computer Science 2026-04-16 Junjie Ye , Changhao Jiang , Zhengyin Du , Yufei Xu , Xuesong Yao , Zhiheng Xi , Xiaoran Fan , Qi Zhang , Tao Gui , Xuanjing Huang , Jiecao Chen

Despite being trained on vast amounts of data, most LLMs are unable to reliably generate well-designed UIs. Designer feedback is essential to improving performance on UI generation; however, we find that existing RLHF methods based on…

Human-Computer Interaction · Computer Science 2026-02-18 Jason Wu , Amanda Swearngin , Arun Krishna Vajjala , Alan Leung , Jeffrey Nichols , Titus Barik