Pragmatic Norms Are All You Need - Why The Symbol Grounding Problem Does Not Apply to LLMs
Reto Gubelmann
摘要
Do LLMs fall prey to Harnad’s symbol grounding problem (SGP), as it has recently been claimed? We argue that this is not the case. Starting out with countering the arguments of Bender and Koller (2020), we trace the origins of the SGP to the computational theory of mind (CTM), and we show that it only arises with natural language when questionable theories of meaning are presupposed. We conclude by showing that it would apply to LLMs only if they were interpreted in the manner of how the CTM conceives the mind, i.e., by postulating that LLMs rely on a version of a language of thought, or by adopting said questionable theories of meaning; since neither option is rational, we conclude that the SGP does not apply to LLMs.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper5
- Climbing towards NLU: On Meaning, Form, and Understanding in the Age of DataEmily M. Bender, Alexander KollerACL 2020 · 被引用 914 次
- Adversarial Filters of Dataset BiasesRonan Le Bras, Swabha Swayamdipta, Chandra Bhagavatula, Rowan Zellers 等ICML 2020 · 被引用 242 次
- End-to-End Bias Mitigation by Modelling Biases in CorporaRabeeh Karimi Mahabadi, Yonatan Belinkov, James HendersonACL 2020 · 被引用 136 次
- Experience Grounds LanguageYonatan Bisk, Ari Holtzman, Jesse Thomason, Jacob Andreas 等EMNLP 2020 · 被引用 74 次
- What Do NLP Researchers Believe? Results of the NLP Community MetasurveyJulian Michael, Ari Holtzman, Alicia Parrish, Aaron Mueller 等ACL 2023 · 被引用 16 次
相关 Paper
- The Mechanistic Emergence of Symbol Grounding in Language ModelsShuyu Wu, Ziqiao Ma, Xiaoxi Luo, Yidong Huang 等ICML 2026 · 被引用 4 次
- On Emergent Social World Models - Evidence for Functional Integration of Theory of Mind and Pragmatic Reasoning in Language ModelsPolina Tsvilodub, Jan-Felix Klumpp, Amir Pour, Jennifer Hu 等ACL 2026 · 被引用 1 次
- Think Twice: Perspective-Taking Improves Large Language Models' Theory-of-Mind CapabilitiesAlex Wilf, Sihyun Shawn Lee, Paul Pu Liang, Louis-Philippe MorencyACL 2024
- CogToM: A Comprehensive Theory of Mind Benchmark inspired by Human Cognition for Large Language ModelsHaibo Tong, Zeyang Yue, Feifei Zhao, Erliang Lin 等ACL 2026
- Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief TrackerMelanie Sclar, Sachin Kumar, Peter West, Alane Suhr 等ACL 2023 · 被引用 21 次
