paper-with-me

홈 › Papers

A fine-grained comparison of pragmatic language understanding in humans and language models

2022-12-13 · Jennifer Hu, Sammy Floyd, Olessia Jouravlev, Evelina Fedorenko, Edward Gibson

Pragmatics and non-literal language understanding are essential to human communication, and present a long-standing challenge for artificial language models. We perform a fine-grained comparison of language models and humans on seven pragmatic phenomena, using zero-shot prompting on an expert-curated set of English materials. We ask whether models (1) select pragmatic interpretations of speaker utterances, (2) make similar error patterns as humans, and (3) use similar linguistic cues as humans to solve the tasks. We find that the largest models achieve high accuracy and match human error patterns: within incorrect responses, models favor literal interpretations over heuristic-based distractors. We also find preliminary evidence that models and humans are sensitive to similar linguistic cues. Our results suggest that pragmatic behaviors can emerge in models without explicitly constructed representations of mental states. However, models tend to struggle with phenomena relying on social expectation violations.

📄 PDF Abstract BibTeX arXiv:2212.06801

Code (1)

jennhu/lm-pragmatics 공식 구현 pytorch

Similar Papers 제목 키워드 기반

The Pragmatic Mind of Machines: Tracing the Emergence of Pragmatic Competence in Large Language Models

2025-05-24 · Kefan Yu, Qingcheng Zeng, Weihao Xuan, Wanxin Li 외

Current large language models (LLMs) have demonstrated emerging capabilities in social intelligence tasks, including implicature resolution (Sravanthi et al. (2024)) and theory-of-mind reasoning (Shapira et al. (2024)), …

Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Input

2024-05-23 · Andi Peng, Yuying Sun, Tianmin Shu, David Abel

Humans use social context to specify preferences over behaviors, i.e. their reward functions. Yet, algorithms for inferring reward models from preference data do not take this social learning view into account. Inspired …

Pragmatically Informative Color Generation by Grounding Contextual Modifiers

2020-10-09 · SCiL 2021 2 · Zhengxuan Wu, Desmond C. Ong

Grounding language in contextual information is crucial for fine-grained natural language understanding. One important task that involves grounding contextual modifiers is color generation. Given a reference color "green…

Natural Language Understanding

Improving Cooperation in Language Games with Bayesian Inference and the Cognitive Hierarchy

2024-12-16 · Joseph Bills, Christopher Archibald, Diego Blaylock

In two-player cooperative games, agents can play together effectively when they have accurate assumptions about how their teammate will behave, but may perform poorly when these assumptions are inaccurate. In language ga…

Bayesian Inference

PUB: A Pragmatics Understanding Benchmark for Assessing LLMs' Pragmatics Capabilities

2024-01-13 · Settaluri Lakshmi Sravanthi, Meet Doshi, Tankala Pavan Kalyan, Rudra Murthy 외

LLMs have demonstrated remarkable capability for understanding semantics, but they often struggle with understanding pragmatics. To demonstrate this fact, we release a Pragmatics Understanding Benchmark (PUB) dataset con…

Instruction FollowingMultiple-choice