ACL 2025short0 citations
Towards LLM-powered Attentive Listener: A Pragmatic Approach through Quantity Self-Repair
Junlin Li, Peng Bo, Yu-Yin Hsu
Abstract
Grice’s Quantity Maxims dictate that human speakers aim for the optimal quantity of information during conversation. To empower LLMs to self-repair their responses toward optimal quantity and improve their attentive listening skills, we propose Q-Tuning and Q-Traveling, which draw on heuristic path-finding to enable decoder-only LLMs to travel among multiple “Q-alternatives” (Quantity Alternatives) and search for the optimal quantity in coordination with a conversation goal. Automatic and human evaluations demonstrate the effectiveness of Q-Tuning and Q-Traveling in constructing human-like, user-centered conversation agents.
BibTeX
@inproceedings{li-etal-2025-towards-llm,
title = "Towards {LLM}-powered Attentive Listener: A Pragmatic Approach through Quantity Self-Repair",
author = "Li, Junlin and
Bo, Peng and
Hsu, Yu-Yin",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-short.1/",
doi = "10.18653/v1/2025.acl-short.1",
pages = "1--13",
ISBN = "979-8-89176-252-7"
}