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

• URL: http://arxiv.org/abs/2507.14063v1
• Date: Fri, 18 Jul 2025 16:42:22 GMT
• Title: Collaborative Rational Speech Act: Pragmatic Reasoning for Multi-Turn Dialog
• Authors: Lautaro Estienne, Gabriel Ben Zenou, Nona Naderi, Jackie Cheung, Pablo Piantanida,
• Abstract summary: We introduce Collaborative Rational Speech Act (CRSA), an information-theoretic (IT) extension of Rational Speech Act (RSA)<n> CRSA models multi-turn dialog by optimizing a gain function adapted from rate-distortion theory.<n>We demonstrate the effectiveness of CRSA on referential games and template-based doctor-patient dialogs in the medical domain.
• Score: 22.299209176253655
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentations [65.11348389219887]
  We introduce Dialectic-RAG (DRAG), a modular approach that evaluates retrieved information by comparing, contrasting, and resolving conflicting perspectives.<n>We show the impact of our framework both as an in-context learning strategy and for constructing demonstrations to instruct smaller models.
  arXiv  Detail & Related papers  (2025-04-07T06:55:15Z)
• Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning [49.3242278912771]
  We introduce a novel multimodal RAG framework named RMR (Retrieval Meets Reasoning) The RMR framework employs a bi-modal retrieval module to identify the most relevant question-answer pairs. It significantly boosts the performance of various vision-language models across a spectrum of benchmark datasets.
  arXiv  Detail & Related papers  (2024-05-31T14:23:49Z)
• Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents [80.5213198675411]
  Large language models (LLMs) have dramatically enhanced the field of language intelligence. LLMs leverage the intriguing chain-of-thought (CoT) reasoning techniques, obliging them to formulate intermediate steps en route to deriving an answer. Recent research endeavors have extended CoT reasoning methodologies to nurture the development of autonomous language agents.
  arXiv  Detail & Related papers  (2023-11-20T14:30:55Z)
• DiPlomat: A Dialogue Dataset for Situated Pragmatic Reasoning [89.92601337474954]
  Pragmatic reasoning plays a pivotal role in deciphering implicit meanings that frequently arise in real-life conversations. We introduce a novel challenge, DiPlomat, aiming at benchmarking machines' capabilities on pragmatic reasoning and situated conversational understanding.
  arXiv  Detail & Related papers  (2023-06-15T10:41:23Z)
• Pragmatic Reasoning in Structured Signaling Games [2.28438857884398]
  We introduce a structured signaling game, an extension of the classical signaling game with a similarity structure between meanings in the context. We show that pragmatic agents using sRSA on top of semantic representations attain efficiency very close to the information theoretic limit. We also explore the interaction between pragmatic reasoning and learning in multi-agent reinforcement learning framework.
  arXiv  Detail & Related papers  (2023-05-17T12:43:29Z)
• Exhaustivity and anti-exhaustivity in the RSA framework: Testing the effect of prior beliefs [68.8204255655161]
  We focus on cases when sensitivity to priors leads to counterintuitive predictions of the Rational Speech Act (RSA) framework. We show that in the baseline RSA model, under certain conditions, anti-exhaustive readings are predicted. We find no anti-exhaustivity effects, but observed that message choice is sensitive to priors, as predicted by the RSA framework overall.
  arXiv  Detail & Related papers  (2022-02-14T20:35:03Z)
• Scalable pragmatic communication via self-supervision [14.01704261285015]
  We propose an architecture and learning process in which agents acquire pragmatic policies via self-supervision instead of imitating human data. This work suggests a new principled approach for equipping artificial agents with pragmatic skills via self-supervision.
  arXiv  Detail & Related papers  (2021-08-12T15:28:30Z)
• Learning to refer informatively by amortizing pragmatic reasoning [35.71540493379324]
  We explore the idea that speakers might learn to amortize the cost of Rational Speech Acts over time. We find that our amortized model is able to quickly generate language that is effective and concise across a range of contexts.
  arXiv  Detail & Related papers  (2020-05-31T02:52:22Z)
• Emergence of Pragmatics from Referential Game between Theory of Mind Agents [64.25696237463397]
  We propose an algorithm, using which agents can spontaneously learn the ability to "read between lines" without any explicit hand-designed rules. We integrate the theory of mind (ToM) in a cooperative multi-agent pedagogical situation and propose an adaptive reinforcement learning (RL) algorithm to develop a communication protocol.
  arXiv  Detail & Related papers  (2020-01-21T19:37:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.