Rewriting Conversational Utterances with Instructed Large Language Models

被引:1
|
作者
Galimzhanova, Elnara [1 ]
Muntean, Cristina Ioana [2 ]
Nardini, Franco Maria [2 ]
Perego, Raffaele [2 ]
Rocchietti, Guido [2 ]
机构
[1] Univ Pisa, Pisa, Italy
[2] ISTI CNR, Pisa, Italy
关键词
conversational systems; query rewriting; LLMs; ChatGPT; information retrieval;
D O I
10.1109/WI-IAT59888.2023.00014
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Many recent studies have shown the ability of large language models (LLMs) to achieve state-of-the-art performance on many NLP tasks, such as question answering, text summarization, coding, and translation. In some cases, the results provided by LLMs are on par with those of human experts. These models' most disruptive innovation is their ability to perform tasks via zero-shot or few-shot prompting. This capability has been successfully exploited to train instructed LLMs, where reinforcement learning with human feedback is used to guide the model to follow the user's requests directly. In this paper, we investigate the ability of instructed LLMs to improve conversational search effectiveness by rewriting user questions in a conversational setting. We study which prompts provide the most informative rewritten utterances that lead to the best retrieval performance. Reproducible experiments are conducted on publicly-available TREC CAST datasets. The results show that rewriting conversational utterances with instructed LLMs achieves significant improvements of up to 25.2% in MRR, 31.7% in Precision@1, 27% in NDCG@3, and 11.5% in Recall@500 over state-of-the-art techniques.
引用
收藏
页码:56 / 63
页数:8
相关论文
共 50 条
  • [31] A Comparative Analysis of Conversational Large Language Models in Knowledge-Based Text Generation
    Schneider, Phillip
    Klettner, Manuel
    Simperl, Elena
    Matthes, Florian
    PROCEEDINGS OF THE 18TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2: SHORT PAPERS, 2024, : 358 - 367
  • [32] Leveraging Large Language Models for Patient Engagement: The Power of Conversational AI in Digital Health
    Wen, Bo
    Norel, Raquel
    Liu, Julia
    Stappenbeck, Thaddeus
    Zulkernine, Farhana
    Chen, Huamin
    2024 IEEE INTERNATIONAL CONFERENCE ON DIGITAL HEALTH, ICDH 2024, 2024, : 104 - 113
  • [33] Improving Conversational Abilities of Quantized Large Language Models via Direct Preference Alignment
    Leel, Janghwan
    Park, Seongmin
    Hong, Sukjin
    Ki, Minsoo
    Chang, Du-Seong
    Choi, Jungwook
    PROCEEDINGS OF THE 62ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1: LONG PAPERS, 2024, : 11346 - 11364
  • [34] Large Language Models for Symptoms Monitoring on the Basis of Conversational Data from Clinical Encounters
    Davis, J.
    Van Dongen, C.
    Sciacca, K.
    Durieux, B.
    Lindvall, C.
    JOURNAL OF THE AMERICAN GERIATRICS SOCIETY, 2024, 72 : S241 - S241
  • [35] Extracting Implicit User Preferences in Conversational Recommender Systems Using Large Language Models
    Kim, Woo-Seok
    Lim, Seongho
    Kim, Gun-Woo
    Choi, Sang-Min
    MATHEMATICS, 2025, 13 (02)
  • [36] Optimizing Conversational Commerce Involving Multilingual Consumers Through Large Language Models' Natural Language Understanding Abilities
    Ilagan, Joseph Benjamin
    Ilagan, Jose Ramon
    Zulueta, Pia Ysabel
    Rodrigo, Maria Mercedes
    ARTIFICIAL INTELLIGENCE IN HCI, PT III, AI-HCI 2024, 2024, 14736 : 47 - 59
  • [37] MOSS: An Open Conversational Large Language Model
    Sun, Tianxiang
    Zhang, Xiaotian
    He, Zhengfu
    Li, Peng
    Cheng, Qinyuan
    Liu, Xiangyang
    Yan, Hang
    Shao, Yunfan
    Tang, Qiong
    Zhang, Shiduo
    Zhao, Xingjian
    Chen, Ke
    Zheng, Yining
    Zhou, Zhejian
    Li, Ruixiao
    Zhan, Jun
    Zhou, Yunhua
    Li, Linyang
    Yang, Xiaogui
    Wu, Lingling
    Yin, Zhangyue
    Huang, Xuanjing
    Jiang, Yu-Gang
    Qiu, Xipeng
    MACHINE INTELLIGENCE RESEARCH, 2024, 21 (05) : 888 - 905
  • [38] Building Conversational Agents for Stroke Rehabilitation: An Evaluation of Large Language Models and Retrieval Augmented Generation
    Retevoi, Alexandra
    Devittori, Giada
    Kowatsch, Tobias
    Lambercy, Olivier
    PROCEEDINGS OF THE 24TH ACM INTERNATIONAL CONFERENCE ON INTELLIGENT VIRTUAL AGENTS, IVA 2024, 2024,
  • [39] Comparative Analysis of Generic and Fine-Tuned Large Language Models for Conversational Agent Systems
    Villa, Laura
    Carneros-Prado, David
    Dobrescu, Cosmin C.
    Sanchez-Miguel, Adrian
    Cubero, Guillermo
    Hervas, Ramon
    ROBOTICS, 2024, 13 (05)
  • [40] Conversational Agents, Virtual Worlds, and Beyond: A Review of Large Language Models Enabling Immersive Learning
    Pester, Andreas
    Tammaa, Ahmed
    Guetl, Christian
    Steinmaurer, Alexander
    Abou El-Seoud, Samir
    2024 IEEE GLOBAL ENGINEERING EDUCATION CONFERENCE, EDUCON 2024, 2024,