Collaborative Rational Speech Act: Pragmatic Reasoning for Multi-Turn Dialog

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Estienne, Lautaro, Zenou, Gabriel Ben, Naderi, Nona, Cheung, Jackie, Piantanida, Pablo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915505672028160
author Estienne, Lautaro
Zenou, Gabriel Ben
Naderi, Nona
Cheung, Jackie
Piantanida, Pablo
author_facet Estienne, Lautaro
Zenou, Gabriel Ben
Naderi, Nona
Cheung, Jackie
Piantanida, Pablo
contents As AI systems take on collaborative roles, they must reason about shared goals and beliefs-not just generate fluent language. The Rational Speech Act (RSA) framework offers a principled approach to pragmatic reasoning, but existing extensions face challenges in scaling to multi-turn, collaborative scenarios. In this paper, we introduce Collaborative Rational Speech Act (CRSA), an information-theoretic (IT) extension of RSA that models multi-turn dialog by optimizing a gain function adapted from rate-distortion theory. This gain is an extension of the gain model that is maximized in the original RSA model but takes into account the scenario in which both agents in a conversation have private information and produce utterances conditioned on the dialog. We demonstrate the effectiveness of CRSA on referential games and template-based doctor-patient dialogs in the medical domain. Empirical results show that CRSA yields more consistent, interpretable, and collaborative behavior than existing baselines-paving the way for more pragmatic and socially aware language agents.
format Preprint
id arxiv_https___arxiv_org_abs_2507_14063
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Collaborative Rational Speech Act: Pragmatic Reasoning for Multi-Turn Dialog
Estienne, Lautaro
Zenou, Gabriel Ben
Naderi, Nona
Cheung, Jackie
Piantanida, Pablo
Computation and Language
As AI systems take on collaborative roles, they must reason about shared goals and beliefs-not just generate fluent language. The Rational Speech Act (RSA) framework offers a principled approach to pragmatic reasoning, but existing extensions face challenges in scaling to multi-turn, collaborative scenarios. In this paper, we introduce Collaborative Rational Speech Act (CRSA), an information-theoretic (IT) extension of RSA that models multi-turn dialog by optimizing a gain function adapted from rate-distortion theory. This gain is an extension of the gain model that is maximized in the original RSA model but takes into account the scenario in which both agents in a conversation have private information and produce utterances conditioned on the dialog. We demonstrate the effectiveness of CRSA on referential games and template-based doctor-patient dialogs in the medical domain. Empirical results show that CRSA yields more consistent, interpretable, and collaborative behavior than existing baselines-paving the way for more pragmatic and socially aware language agents.
title Collaborative Rational Speech Act: Pragmatic Reasoning for Multi-Turn Dialog
topic Computation and Language
url https://arxiv.org/abs/2507.14063