Towards LLM-powered Attentive Listener: A Pragmatic Approach through Quantity Self-Repair

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 Al-ternatives) 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. Our repository is open-sourced via https://github.com/ CN-Eyetk/QTraveling .