Dissociating language and thought in large language models
- URL: http://arxiv.org/abs/2301.06627v3
- Date: Sat, 23 Mar 2024 19:52:33 GMT
- Title: Dissociating language and thought in large language models
- Authors: Kyle Mahowald, Anna A. Ivanova, Idan A. Blank, Nancy Kanwisher, Joshua B. Tenenbaum, Evelina Fedorenko,
- Abstract summary: Large Language Models (LLMs) have come closest among all models to date to mastering human language.
We ground this distinction in human neuroscience, which has shown that formal and functional competence rely on different neural mechanisms.
Although LLMs are surprisingly good at formal competence, their performance on functional competence tasks remains spotty.
- Score: 52.39241645471213
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large Language Models (LLMs) have come closest among all models to date to mastering human language, yet opinions about their linguistic and cognitive capabilities remain split. Here, we evaluate LLMs using a distinction between formal linguistic competence - knowledge of linguistic rules and patterns - and functional linguistic competence - understanding and using language in the world. We ground this distinction in human neuroscience, which has shown that formal and functional competence rely on different neural mechanisms. Although LLMs are surprisingly good at formal competence, their performance on functional competence tasks remains spotty and often requires specialized fine-tuning and/or coupling with external modules. We posit that models that use language in human-like ways would need to master both of these competence types, which, in turn, could require the emergence of mechanisms specialized for formal linguistic competence, distinct from functional competence.
Related papers
- Large Models of What? Mistaking Engineering Achievements for Human Linguistic Agency [0.11510009152620666]
We argue that claims regarding linguistic capabilities of Large Language Models (LLMs) are based on at least two unfounded assumptions.
Language completeness assumes that a distinct and complete thing such as a natural language' exists.
The assumption of data completeness relies on the belief that a language can be quantified and wholly captured by data.
arXiv Detail & Related papers (2024-07-11T18:06:01Z) - Language Guided Skill Discovery [56.84356022198222]
We introduce Language Guided Skill Discovery (LGSD) to maximize semantic diversity between skills.
LGSD takes user prompts as input and outputs a set of semantically distinctive skills.
We demonstrate that LGSD enables legged robots to visit different user-intended areas on a plane by simply changing the prompt.
arXiv Detail & Related papers (2024-06-07T04:25:38Z) - Comuniqa : Exploring Large Language Models for improving speaking skills [2.8227892155844088]
We investigate the potential of Large Language Models (LLMs) to improve English speaking skills.
Recent advancements in Artificial Intelligence (AI) offer promising solutions to overcome limitations.
We propose Comuniqa, a novel LLM-based system designed to enhance English speaking skills.
arXiv Detail & Related papers (2024-01-28T07:37:33Z) - How Proficient Are Large Language Models in Formal Languages? An In-Depth Insight for Knowledge Base Question Answering [52.86931192259096]
Knowledge Base Question Answering (KBQA) aims to answer natural language questions based on facts in knowledge bases.
Recent works leverage the capabilities of large language models (LLMs) for logical form generation to improve performance.
arXiv Detail & Related papers (2024-01-11T09:27:50Z) - Think Before You Speak: Cultivating Communication Skills of Large Language Models via Inner Monologue [73.69510478736483]
Large language models (LLMs) can generate fluent, coherent, and diverse responses.
However, they lack a crucial ability: communication skills.
This article aims to empower LLMs with communication skills through inner monologues.
Experimental results show that the proposed CSIM strategy improves the backbone models and outperforms the baselines.
arXiv Detail & Related papers (2023-11-13T16:19:42Z) - Unveiling A Core Linguistic Region in Large Language Models [49.860260050718516]
This paper conducts an analogical research using brain localization as a prototype.
We have discovered a core region in large language models that corresponds to linguistic competence.
We observe that an improvement in linguistic competence does not necessarily accompany an elevation in the model's knowledge level.
arXiv Detail & Related papers (2023-10-23T13:31:32Z) - Overcoming Barriers to Skill Injection in Language Modeling: Case Study
in Arithmetic [14.618731441943847]
We develop a novel framework that enables language models to be mathematically proficient while retaining their linguistic prowess.
Specifically, we offer information-theoretic interventions to overcome the catastrophic forgetting of linguistic skills that occurs while injecting non-linguistic skills into language models.
arXiv Detail & Related papers (2022-11-03T18:53:30Z) - Testing the Ability of Language Models to Interpret Figurative Language [69.59943454934799]
Figurative and metaphorical language are commonplace in discourse.
It remains an open question to what extent modern language models can interpret nonliteral phrases.
We introduce Fig-QA, a Winograd-style nonliteral language understanding task.
arXiv Detail & Related papers (2022-04-26T23:42:22Z) - Language Models as a Knowledge Source for Cognitive Agents [9.061356032792954]
Language models (LMs) are sentence-completion engines trained on massive corpora.
This paper outlines the challenges and opportunities for using language models as a new knowledge source for cognitive systems.
It also identifies possible ways to improve knowledge extraction from language models using the capabilities provided by cognitive systems.
arXiv Detail & Related papers (2021-09-17T01:12:34Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.