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
  • [41] Rethinking Conversational Agents in the Era of Large Language Models: Proactivity, Non-collaborativity, and Beyond
    Deng, Yang
    Lei, Wenqiang
    Huang, Minlie
    Chua, Tat-Seng
    ANNUAL INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL IN THE ASIA PACIFIC REGION, SIGIR-AP 2023, 2023, : 298 - 301
  • [42] Hybrid language models for out of vocabulary word detection in large vocabulary conversational speech recognition
    Yazgan, A
    Saraclar, M
    2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS: SPEECH PROCESSING, 2004, : 745 - 748
  • [43] From Passive to Active: Towards Conversational In-Vehicle Navigation Through Large Language Models
    Du, Huifang
    Tao, Shiyu
    Feng, Xuejing
    Ma, Jun
    Wang, Haofen
    DESIGN, USER EXPERIENCE, AND USABILITY, DUXU 2024, PT II, 2024, 14713 : 159 - 172
  • [44] ChatGPT Versus Modest Large Language Models: An Extensive Study on Benefits and Drawbacks for Conversational Search
    Rocchietti, Guido
    Rulli, Cosimo
    Maria Nardini, Franco
    Ioana Muntean, Cristina
    Perego, Raffaele
    Frieder, Ophir
    IEEE ACCESS, 2025, 13 : 15253 - 15271
  • [45] Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Search
    Mao, Kelong
    Dou, Zhicheng
    Mo, Fengran
    Hou, Jiewen
    Chen, Haonan
    Qian, Hongjin
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS - EMNLP 2023, 2023, : 1211 - 1225
  • [46] BEYOND ISOLATED UTTERANCES: CONVERSATIONAL EMOTION RECOGNITION
    Pappagari, Raghavendra
    Zelasko, Piotr
    Villalba, Jesus
    Moro-Velazquez, Laureano
    Dehak, Najim
    2021 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU), 2021, : 39 - 46
  • [47] Small Language Models Improve Giants by Rewriting Their Outputs
    Vernikos, Giorgos
    Brazinskas, Arthur
    Adamek, Jakub
    Mallinson, Jonathan
    Severyn, Aliaksei
    Malmi, Eric
    PROCEEDINGS OF THE 18TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1: LONG PAPERS, 2024, : 2703 - 2718
  • [48] Adaptive utterance rewriting for conversational search
    Mele, Ida
    Muntean, Cristina Ioana
    Nardini, Franco Maria
    Perego, Raffaele
    Tonellotto, Nicola
    Frieder, Ophir
    INFORMATION PROCESSING & MANAGEMENT, 2021, 58 (06)
  • [49] Question Rewriting for Conversational Question Answering
    Vakulenko, Svitlana
    Longpre, Shayne
    Tu, Zhucheng
    Anantha, Raviteja
    WSDM '21: PROCEEDINGS OF THE 14TH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING, 2021, : 355 - 363
  • [50] Hierarchical Bayesian Language Models for Conversational Speech Recognition
    Huang, Songfang
    Renals, Steve
    IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2010, 18 (08): : 1941 - 1954