中文
相关论文

相关论文: Expressivity of Emergent Language is a Trade-off b…

200 篇论文

Learning to communicate is considered an essential task to develop a general AI. While recent literature in language evolution has studied emergent language through discrete or continuous message symbols, there has been little work in the…

多智能体系统 · 计算机科学 2021-09-17 Shresth Verma , Joydip Dhar

In this work, we propose a computational framework in which agents equipped with communication capabilities simultaneously play a series of referential games, where agents are trained using deep reinforcement learning. We demonstrate that…

计算与语言 · 计算机科学 2020-03-03 Laura Graesser , Kyunghyun Cho , Douwe Kiela

Computational modeling plays an essential role in the study of language emergence. It aims to simulate the conditions and learning processes that could trigger the emergence of a structured language within a simulated controlled…

计算与语言 · 计算机科学 2024-03-19 Mathieu Rita , Paul Michel , Rahma Chaabouni , Olivier Pietquin , Emmanuel Dupoux , Florian Strub

Large Language Models (LLMs) are leading a new technological revolution as one of the most promising research streams toward artificial general intelligence. The scaling of these models, accomplished by increasing the number of parameters…

机器学习 · 计算机科学 2025-03-17 Leonardo Berti , Flavio Giorgi , Gjergji Kasneci

We study the problem of emergent communication, in which language arises because speakers and listeners must communicate information in order to solve tasks. In temporally extended reinforcement learning domains, it has proved hard to learn…

多智能体系统 · 计算机科学 2019-12-13 Tom Eccles , Yoram Bachrach , Guy Lever , Angeliki Lazaridou , Thore Graepel

Many recent works have discussed the propensity, or lack thereof, for emergent languages to exhibit properties of natural languages. A favorite in the literature is learning compositionality. We note that most of those works have focused on…

计算与语言 · 计算机科学 2020-04-16 Cinjon Resnick , Abhinav Gupta , Jakob Foerster , Andrew M. Dai , Kyunghyun Cho

We propose a model for the evolutionary ecology of words as one attempt to extend evolutionary game theory and agent-based models by utilizing the rich linguistic expressions of Large Language Models (LLMs). Our model enables the emergence…

种群与进化 · 定量生物学 2025-05-12 Reiji Suzuki , Takaya Arita

Artificial agents have been shown to learn to communicate when needed to complete a cooperative task. Some level of language structure (e.g., compositionality) has been found in the learned communication protocols. This observed structure…

人工智能 · 计算机科学 2019-10-30 Fushan Li , Michael Bowling

In this paper, we consider the syntactic properties of languages emerged in referential games, using unsupervised grammar induction (UGI) techniques originally designed to analyse natural language. We show that the considered UGI techniques…

计算与语言 · 计算机科学 2020-10-12 Oskar van der Wal , Silvan de Boer , Elia Bruni , Dieuwke Hupkes

Computational modelling with multi-agent systems is becoming an important technique of studying language evolution. We present a brief introduction into this rapidly developing field, as well as our own contributions that include an…

物理与社会 · 物理学 2010-08-24 Adam Lipowski , Dorota Lipowska

Large Language Models (LLMs) encode vast world knowledge across multiple languages, yet their internal beliefs are often unevenly distributed across linguistic spaces. When external evidence contradicts these language-dependent memories,…

计算与语言 · 计算机科学 2026-01-13 Jiaqi Zhao , Qiang Huang , Haodong Chen , Xiaoxing You , Jun Yu

Language model architectures are predominantly first created for English and subsequently applied to other languages. It is an open question whether this architectural bias leads to degraded performance for languages that are structurally…

计算与语言 · 计算机科学 2025-11-12 Kushal Tatariya , Wessel Poelman , Miryam de Lhoneux

Emergentism and pragmatics are two research fields that study the dynamics of linguistic communication along substantially different timescales and intelligence levels. From the perspective of multi-agent reinforcement learning, they…

人工智能 · 计算机科学 2020-12-16 Yipeng Kang , Tonghan Wang , Gerard de Melo

How do we know if communication is emerging in a multi-agent system? The vast majority of recent papers on emergent communication show that adding a communication channel leads to an increase in reward or task success. This is a useful…

机器学习 · 计算机科学 2019-03-14 Ryan Lowe , Jakob Foerster , Y-Lan Boureau , Joelle Pineau , Yann Dauphin

Grounding responses in external knowledge represents an effective strategy for mitigating hallucinations in Large Language Models (LLMs). However, current LLMs struggle to seamlessly integrate knowledge while simultaneously maintaining…

计算与语言 · 计算机科学 2025-08-27 Chenxu Yang , Qingyi Si , Zheng Lin

Training agents to communicate with one another given task-based supervision only has attracted considerable attention recently, due to the growing interest in developing models for human-agent interaction. Prior work on the topic focused…

计算与语言 · 计算机科学 2019-03-26 Ben Bogin , Mor Geva , Jonathan Berant

Emergent narratives provide a unique and compelling approach to interactive storytelling through simulation, and have applications in games, narrative generation, and virtual agents. However the inherent complexity of simulation makes…

人工智能 · 计算机科学 2020-04-24 Ben Kybartas , Clark Verbrugge , Jonathan Lessard

Languages are shaped by the inductive biases of their users. Using a classical referential game, we investigate how artificial languages evolve when optimised for inductive biases in humans and large language models (LLMs) via Human-Human,…

计算与语言 · 计算机科学 2025-05-29 Tom Kouwenhoven , Max Peeperkorn , Roy de Kleijn , Tessa Verhoef

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…

计算与语言 · 计算机科学 2024-10-29 Olaf Lipinski , Adam J. Sobey , Federico Cerutti , Timothy J. Norman

Written language is complex. A written text can be considered an attempt to convey a meaningful message which ends up being constrained by language rules, context dependence and highly redundant in its use of resources. Despite all these…

计算与语言 · 计算机科学 2019-05-20 E. Estevez-Rams , A. Mesa Rodriguez , D. Estevez-Moya