paper-with-me

Papers

Are BabyLMs Deaf to Gricean Maxims? A Pragmatic Evaluation of Sample-efficient Language Models

2025-10-06 · Raha Askari, Sina Zarrieß, Özge Alacam, Judith Sieker arxiv

Implicit meanings are integral to human communication, making it essential for language models to be capable of identifying and interpreting them. Grice (1975) proposed a set of conversational maxims that guide cooperative dialogue, noting that speakers may deliberately violate these principles to express meanings beyond literal words, and that listeners, in turn, recognize such violations to draw pragmatic inferences. Building on Surian et al. (1996)'s study of children's sensitivity to violations of Gricean maxims, we introduce a novel benchmark to test whether language models pretrained on less than 10M and less than 100M tokens can distinguish maxim-adhering from maxim-violating utterances. We compare these BabyLMs across five maxims and situate their performance relative to children and a Large Language Model (LLM) pretrained on 3T tokens. We find that overall, models trained on less than 100M tokens outperform those trained on less than 10M, yet fall short of child-level and LLM competence. Our results suggest that modest data increases improve some aspects of pragmatic behavior, leading to finer-grained differentiation between pragmatic dimensions.

📄 PDF Abstract BibTeX arXiv:2510.04764

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Vision-Language Models Are Not Pragmatically Competent in Referring Expression Generation

2025-04-22 · Ziqiao Ma, Jing Ding, Xuejun Zhang, Dezhi Luo 외

Referring Expression Generation (REG) is a core task for evaluating the pragmatic competence of vision-language systems, requiring not only accurate semantic grounding but also adherence to principles of cooperative comm…

Referring ExpressionReferring expression generation

Do Large Language Models Understand Conversational Implicature -- A case study with a chinese sitcom

2024-04-30 · Shisen Yue, Siyuan Song, Xinyuan Cheng, Hai Hu

Understanding the non-literal meaning of an utterance is critical for large language models (LLMs) to become human-like social communicators. In this work, we introduce SwordsmanImp, the first Chinese multi-turn-dialogue…

ImplicaturesMultiple-choice

Emergence of Gricean Maxims from Multi-Agent Decision Theory

2013-06-01 · NAACL 2013 6 · Adam Vogel, Max Bodoia, Christopher Potts, Daniel Jurafsky
Decision MakingSlot FillingSpeech Recognition

Gricean Norms as a Basis for Effective Collaboration

2025-03-18 · Fardin Saad, Pradeep K. Murukannaiah, Munindar P. Singh

Effective human-AI collaboration hinges not only on the AI agent's ability to follow explicit instructions but also on its capacity to navigate ambiguity, incompleteness, invalidity, and irrelevance in communication. Gri…

Large Language ModelNavigate

Evaluating Dialogs based on Grice's Maxims

2017-09-01 · RANLP 2017 9 · Prathyusha Jwalapuram

There is no agreed upon standard for the evaluation of conversational dialog systems, which are well-known to be hard to evaluate due to the difficulty in pinning down metrics that will correspond to human judgements and…