paper-with-me

Papers

Identifying and interpreting non-aligned human conceptual representations using language modeling

2024-03-10 · Wanqian Bao, Uri Hasson

The question of whether people's experience in the world shapes conceptual representation and lexical semantics is longstanding. Word-association, feature-listing and similarity rating tasks aim to address this question but require a subjective interpretation of the latent dimensions identified. In this study, we introduce a supervised representational-alignment method that (i) determines whether two groups of individuals share the same basis of a certain category, and (ii) explains in what respects they differ. In applying this method, we show that congenital blindness induces conceptual reorganization in both a-modal and sensory-related verbal domains, and we identify the associated semantic shifts. We first apply supervised feature-pruning to a language model (GloVe) to optimize prediction accuracy of human similarity judgments from word embeddings. Pruning identifies one subset of retained GloVe features that optimizes prediction of judgments made by sighted individuals and another subset that optimizes judgments made by blind. A linear probing analysis then interprets the latent semantics of these feature-subsets by learning a mapping from the retained GloVe features to 65 interpretable semantic dimensions. We applied this approach to seven semantic domains, including verbs related to motion, sight, touch, and amodal verbs related to knowledge acquisition. We find that blind individuals more strongly associate social and cognitive meanings to verbs related to motion or those communicating non-speech vocal utterances (e.g., whimper, moan). Conversely, for amodal verbs, they demonstrate much sparser information. Finally, for some verbs, representations of blind and sighted are highly similar. The study presents a formal approach for studying interindividual differences in word meaning, and the first demonstration of how blindness impacts conceptual representation of everyday verbs.

📄 PDF Abstract BibTeX arXiv:2403.06204

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingWord Embeddings

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
GloVe GloVe Embeddings are a type of word embedding that encode the co-occurrence probability ratio between two words as vector differences. GloVe uses a weighted least squares…

Similar Papers 제목 키워드 기반

Concept frustration: Aligning human concepts and machine representations

2026-03-31 · Enrico Parisini, Christopher J. Soelistyo, Ahab Isaac, Alessandro Barp 외 arxiv

Aligning human-interpretable concepts with the internal representations learned by modern machine learning systems remains a central challenge for interpretable AI. We introduce a geometric framework for comparing superv…

One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity

2024-11-07 · Sonia K. Murthy, Tomer Ullman, Jennifer Hu

Researchers in social science and psychology have recently proposed using large language models (LLMs) as replacements for humans in behavioral research. In addition to arguments about whether LLMs accurately capture pop…

Diversity

Cross-Modal Alignment Learning of Vision-Language Conceptual Systems

2022-07-31 · Taehyeong Kim, Hyeonseop Song, Byoung-Tak Zhang

Human infants learn the names of objects and develop their own conceptual systems without explicit supervision. In this study, we propose methods for learning aligned vision-language conceptual systems inspired by infant…

cross-modal alignmentRepresentation LearningZero-Shot Learning

Human Evaluation of Conceptual Route Graphs for Interpreting Spoken Route Descriptions

2013-03-01 · WS 2013 3 · Raveesh Meena, Gabriel Skantze, Joakim Gustafson
Autonomous NavigationSpeech RecognitionSpoken Language Understanding

Human-like conceptual representations emerge from language prediction

2025-01-21 · Ningyu Xu, Qi Zhang, Chao Du, Qiang Luo 외

People acquire concepts through rich physical and social experiences and use them to understand the world. In contrast, large language models (LLMs), trained exclusively through next-token prediction over language data, …

PredictionReverse Dictionary