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
  • [21] Enhancing diagnostic capability with multi-agents conversational large language models
    Chen, Xi
    Yi, Huahui
    You, Mingke
    Liu, Weizhi
    Wang, Li
    Li, Hairui
    Zhang, Xue
    Guo, Yingman
    Fan, Lei
    Chen, Gang
    Lao, Qicheng
    Fu, Weili
    Li, Kang
    Li, Jian
    NPJ DIGITAL MEDICINE, 2025, 8 (01):
  • [22] Speed and Conversational Large Language Models: Not All Is About Tokens per Second
    Conde, Javier
    Gonzalez, Miguel
    Reviriego, Pedro
    Gao, Zhen
    Liu, Shanshan
    Lombardi, Fabrizio
    COMPUTER, 2024, 57 (08) : 74 - 80
  • [23] Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment
    DeCLaRe Lab, Singapore University of Technology and Design, Singapore
    arXiv, 1600,
  • [24] Instructed Language Models with Retrievers Are Powerful Entity Linkers
    Xiao, Zilin
    Gong, Ming
    Wu, Jie
    Zhang, Xingyao
    Shou, Linjun
    Jiang, Daxin
    2023 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING, EMNLP 2023, 2023, : 2267 - 2282
  • [25] Synthesizing multimodal utterances for conversational agents
    Kopp, S
    Wachsmuth, P
    COMPUTER ANIMATION AND VIRTUAL WORLDS, 2004, 15 (01) : 39 - 52
  • [26] Annotation of Utterances for Conversational Nonverbal Behaviors
    Funkhouser, Allison
    Simmons, Reid
    SOCIAL ROBOTICS, (ICSR 2016), 2016, 9979 : 521 - 530
  • [27] SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities
    Zhang, Dong
    Li, Shimin
    Zhang, Xin
    Zhan, Jun
    Wang, Pengyu
    Zhou, Yaqian
    Qiu, Xipeng
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (EMNLP 2023), 2023, : 15757 - 15773
  • [28] User-Centric Conversational Recommendation: Adapting the Need of User with Large Language Models
    Zhang, Gangyi
    PROCEEDINGS OF THE 17TH ACM CONFERENCE ON RECOMMENDER SYSTEMS, RECSYS 2023, 2023, : 1349 - 1354
  • [29] Developing conversational Virtual Humans for social emotion elicitation based on large language models
    Llanes-Jurado, Jose
    Gomez-Zaragoza, Lucia
    Minissi, Maria Eleonora
    Alcaniz, Mariano
    Marin-Morales, Javier
    EXPERT SYSTEMS WITH APPLICATIONS, 2024, 246
  • [30] Written by ChatGPT: AI, large language models, conversational chatbots, and their place in society and business
    Kietzmann, Jan
    Park, Andrew
    BUSINESS HORIZONS, 2024, 67 (05) : 453 - 459