What computational principles underlie human pragmatic reasoning? A prominent approach to pragmatics is the Rational Speech Act (RSA) framework, which formulates pragmatic reasoning as probabilistic speakers and listeners recursively reasoning about each other. While RSA enjoys broad empirical support, it is not yet clear whether the dynamics of such recursive reasoning may be governed by a general optimization principle. Here, we present a novel analysis of the RSA framework that addresses this question. First, we show that RSA recursion implements an alternating maximization for optimizing a tradeoff between expected utility and communicative effort. On that basis, we study the dynamics of RSA recursion and disconfirm the conjecture that expected utility is guaranteed to improve with recursion depth. Second, we show that RSA can be grounded in Rate-Distortion theory, while maintaining a similar ability to account for human behavior and avoiding a bias of RSA toward random utterance production. This work furthers the mathematical understanding of RSA models, and suggests that general information-theoretic principles may give rise to human pragmatic reasoning.
Tsinghua University（清华大学）；Hasso Plattner Institute（哈索·普拉特纳研究所）；University of Potsdam（波茨坦大学）
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 correspond to stochastic games with reinforcement training and stage games with opponent awareness. Given that their combination has been explored in linguistics, we propose computational models that combine short-term mutual reasoning-based pragmatics with long-term language emergentism. We explore this for agent communication referential games as well as in Star…
Massachusetts Institute of Technology（麻省理工学院）；Center for Brains Minds and Machines, Massachusetts Institute of Technology（麻省理工学院脑、心智与机器中心）
Models of context-sensitive communication often use the Rational Speech Act framework (RSA; Frank & Goodman, 2012), which formulates listeners and speakers in a cooperative reasoning process. However, the standard RSA formulation can only be applied to small domains, and large-scale applications have relied on imitating human behavior. Here, we propose a new approach to scalable pragmatics, building upon recent theoretical results (Zaslavsky et al., 2020) that characterize pragmatic reasoning in terms of general information-theoretic principles. Specifically, we propose an architecture and lea…
From Training to Generalization: Improving Moral Reasoning Through Pragmatic Inference
Indiana University Indianapolis（印第安纳大学印第安纳波利斯分校）；Nanyang Technological University（南洋理工大学）；University of Mississippi（密苏里大学）；Northeastern University（东北大学）；Qualcomm（高通公司）；Michigan State University（密歇根州立大学）
A hallmark of human language is the ability to effectively and efficiently convey contextually relevant information. One theory for how humans reason about language is presented in the Rational Speech Acts (RSA) framework, which captures pragmatic phenomena via a process of recursive social reasoning (Goodman & Frank, 2016). However, RSA represents ideal reasoning in an unconstrained setting. We explore the idea that speakers might learn to amortize the cost of RSA computation over time by directly optimizing for successful communication with an internal listener model. In simulations with gro…
Max Planck Institute for Informatics Saarland Campus（马克斯·普朗克信息研究所萨尔兰州分校）；Computer Science Saarland University（萨尔兰州大学计算机科学系）；Max Planck Institute for Software Systems Saarland Campus（马克斯·普朗克软件系统研究所萨尔兰州分校）
DiPlomat: A Dialogue Dataset for Situated Pragmatic Reasoning
Beijing Institute for General Artificial Intelligence (BIGAI)（北京通用人工智能研究院）；Yuanpei College, Peking University（北京大学元培学院）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）；School of Intelligence Science and Technology, Peking University（北京大学智能学院）；Department of Automation, Tsinghua University（清华大学自动化系）
Computer Science Division（计算机科学系）；University of California, Berkeley（加州大学伯克利分校）
We present a model for pragmatically describing scenes, in which contrastive behavior results from a combination of inference-driven pragmatics and learned semantics. Like previous learned approaches to language generation, our model uses a simple feature-driven architecture (here a pair of neural "listener" and "speaker" models) to ground language in the world. Like inference-driven approaches to pragmatics, our model actively reasons about listener behavior when selecting utterances. For training, our approach requires only ordinary captions, annotated _without_ demonstration of the pragmati…
Speakers' referential expressions often depart from communicative ideals in ways that help illuminate the nature of pragmatic language use. Patterns of overmodification, in which a speaker uses a modifier that is redundant given their communicative goal, have proven especially informative in this regard. It seems likely that these patterns are shaped by the environment a speaker is exposed to in complex ways. Unfortunately, systematically manipulating these factors during human language acquisition is impossible. In this paper, we propose to address this limitation by adopting neural networks …
Tracing the ongoing emergence of human-like reasoning in Large Language Models
Departament de Filologia Catalana, Universitat Autònoma de Barcelona（加泰罗尼亚语言系系，巴塞罗那自治大学）；Institut für Psychologie, Humboldt-Universitat zu Berlin（柏林洪堡大学心理学研究所）；Institució Catalana de Recerca i Estudis Avançats (ICREA)（加泰罗尼亚高级研究与高级教育研究所）
We present a model of pragmatic referring expression interpretation in a grounded communication task (identifying colors from descriptions) that draws upon predictions from two recurrent neural network classifiers, a speaker and a listener, unified by a recursive pragmatic reasoning framework. Experiments show that this combined pragmatic model interprets color descriptions more accurately than the classifiers from which it is built, and that much of this improvement results from combining the speaker and listener perspectives. We observe that pragmatic reasoning helps primarily in the hardest…
Pragmatic Theories Enhance Understanding of Implied Meanings in LLMs
Nara Institute of Science and Technology（奈良科学技術大學）；RIKEN（理化学研究所）；Guardian Robot Project（守護機器人專案）；Kyoto Institute of Technology（京都科技大學）；Institute of Science Tokyo（東京科學研究所）
Collaborative Rational Speech Act: Pragmatic Reasoning for Multi-Turn Dialog
International Laboratory on Learning Systems (ILLS)（国际学习系统实验室）；Laboratoire Interdisciplinaire des Sciences du Numérique (LISN)（跨学科数字科学实验室）；Mila - Quebec AI Institute（魁北克人工智能研究所）；CNRS（法国国家科学研究中心）；CentraleSupélec（中央超导研究所）；Université Paris-Saclay（巴黎萨克雷大学）；McGill University（麦吉尔大学）
MUStReason: A Benchmark for Diagnosing Pragmatic Reasoning in Video-LMs for Multimodal Sarcasm Detection
Max Planck Institute for Informatics, Saarland Informatics Campus（马克斯·普朗克研究所信息学研究所，萨尔兰州信息学校园）；Saarland University（萨尔兰州大学）；The University of Edinburgh（爱丁堡大学）；Samsung AI Center, Cambridge（三星人工智能中心，剑桥）
Presupposition and Reasoning in Conditionals: A Theory-Based Study of Humans and LLMs
Department of Cognitive Science, Carleton University（卡尔顿大学认知科学系）；School of Computer Science, McGill University（麦吉尔大学计算机科学学院）；Mila – Quebec AI Institute（魁北克人工智能研究所）
Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning
University of Washington（华盛顿大学）；University of California, Los Angeles（加州大学洛杉矶分校）；Samaya AI（Samaya人工智能）；Mistral AI（Mistral人工智能）；Allen Institute for AI（人工智能研究所）
Non-literal Understanding of Number Words by Language Models
Department of Linguistics, University of Tübingen（语言学系，图宾根大学）；Department of Computer Science, Stanford University（计算机科学系，斯坦福大学）；University of Washington（华盛顿大学）；Department of Psychology, Stanford University（心理学系，斯坦福大学）；Departments of Psychology & Computer Science, Stanford University（心理学与计算机科学系，斯坦福大学）
Interpretable Cross-Lingual Alignment in Small Language Models: Probing Cultural and Pragmatic Reasoning in Japanese-English Bilingual LLMs
Sakaguchi–Inui Laboratory (Tohoku University)（东北大学坂口–乾实验室）；Natural Language Understanding Team at RIKEN AIP（理化学研究所先进智能项目中心自然语言理解团队）；Swallow Project at the Institute of Science Tokyo（东京科学大学Swallow项目）；Sakana AI；Tohoku University（东北大学）；RIKEN AIP（理化学研究所先进智能项目中心）；Institute of Science Tokyo（东京科学大学）
University of Washington（华盛顿大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Stanford University（斯坦福大学）
Warning: this paper contains content that may be offensive or upsetting. Language has the power to reinforce stereotypes and project social biases onto others. At the core of the challenge is that it is rarely what is stated explicitly, but rather the implied meanings, that frame people's judgments about others. For example, given a statement that "we shouldn't lower our standards to hire more women," most listeners will infer the implicature intended by the speaker -- that "women (candidates) are less qualified." Most semantic formalisms, to date, do not capture such pragmatic implications in…
