Related papers: Success and Cost Elicit Convention Formation for E…
A common training approach for language models involves using a large-scale language model to expand a human-provided dataset, which is subsequently used for model training.This method significantly reduces training costs by eliminating the…
Recently, emergence of signaling conventions, among which language is a prime example, draws a considerable interdisciplinary interest ranging from game theory, to robotics to evolutionary linguistics. Such a wide spectrum of research is…
Non-binding communication is common in daily life and crucial for fostering cooperation, even though it has no direct payoff consequences. However, despite robust empirical evidence, its evolutionary basis remains poorly understood. Here,…
We improve the informativeness of models for conditional text generation using techniques from computational pragmatics. These techniques formulate language production as a game between speakers and listeners, in which a speaker should…
Large Language Models (LLMs) often exhibit pronounced context-dependent variability that undermines predictable multi-agent behavior in tasks requiring strategic thinking. Focusing on models that range from 7 to 9 billion parameters in size…
During spontaneous conversations, speakers collaborate on novel referring expressions, which they can then re-use in subsequent conversations. Understanding such referring expressions is an important ability for an embodied agent, so that…
Response generation for task-oriented dialogues implicitly optimizes two objectives at the same time: task completion and language quality. Conditioned response generation serves as an effective approach to separately and better optimize…
Conversational systems relying on text-based large language models (LLMs) often overlook paralinguistic cues, essential for understanding emotions and intentions. Speech-language models (SLMs), which use speech as input, are emerging as a…
How do people talk about things they've never talked about before? One view suggests that a new shared naming system establishes an arbitrary link to a specific target, like proper names that cannot extend beyond their bearers. An…
When training a model on referential dialogue guessing games, the best model is usually chosen based on its task success. We show that in the popular end-to-end approach, this choice prevents the model from learning to generate…
While most machine translation systems to date are trained on large parallel corpora, humans learn language in a different way: by being grounded in an environment and interacting with other humans. In this work, we propose a communication…
Effective communication requires the ability to refer to specific parts of an observation in relation to others. While emergent communication literature shows success in developing various language properties, no research has shown the…
Simple reference games are of central theoretical and empirical importance in the study of situated language use. Although language provides rich, compositional truth-conditional semantics to facilitate reference, speakers and listeners may…
This paper studies the organization of communication between biased senders and a receiver. Senders can misreport their private information at a cost. Efficiency is achieved by clearing information asymmetries without incurring costs.…
Recently, large language models (LLMs), such as GPT-4, stand out remarkable conversational abilities, enabling them to engage in dynamic and contextually relevant dialogues across a wide range of topics. However, given a long conversation,…
People employ expressive behaviors to effectively communicate and coordinate their actions with others, such as nodding to acknowledge a person glancing at them or saying "excuse me" to pass people in a busy corridor. We would like robots…
Neural conversation models tend to generate safe, generic responses for most inputs. This is due to the limitations of likelihood-based decoding objectives in generation tasks with diverse outputs, such as conversation. To address this…
Conversational modeling is an important task in natural language understanding and machine intelligence. Although previous approaches exist, they are often restricted to specific domains (e.g., booking an airline ticket) and require…
If language evolved by sexual selection to display superior intelligence, then we require conversational skills, to impress other people, gain high social status, and get a mate. Conversational skills include a Theory of Mind, a sense of…
The study of emergent communication has been dedicated to interactive artificial intelligence. While existing work focuses on communication about single objects or complex image scenes, we argue that communicating relationships between…