Semantic Structure of Feature Space in Large Language Models
We show that the geometric relations between semantic features in large language models' hidden states closely mirror human psychological associations. We construct feature vectors corresponding to 360 words and project them on 32 semantic axes (e.g. beautiful-ugly, soft-hard), and find that these projections correlate highly with human ratings of those words on the respective semantic scales. Second, we find that the cosine similarities between the semantic axes themselves are highly predictive of the correlations between these scales in the survey. Third, we show that substantial variance across the 32 semantic axes lies on a low-dimensional subspace, reproducing patterns typical of human semantic associations. Finally, we demonstrate that steering a word on one semantic axis causes spillover effects on the model's rating of that word on other semantic scales proportionate to the cosine similarity between those semantic axes. These findings suggest that features should be understood not only in isolation but through their geometric relations and the meaningful subspaces they form.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Invariant Features in Language Models: Geometric Characterization and Model Attribution
Language models exhibit strong robustness to paraphrasing, suggesting that semantic information may be encoded through stable internal representations, yet the structure and origin of such invariance remain unclear. We p…
Semantic Structure in Large Language Model Embeddings
Psychological research consistently finds that human ratings of words across diverse semantic scales can be reduced to a low-dimensional form with relatively little information loss. We find that the semantic association…
FILS: Self-Supervised Video Feature Prediction In Semantic Language Space
This paper demonstrates a self-supervised approach for learning semantic video representations. Recent vision studies show that a masking strategy for vision and natural language supervision has contributed to developing…
Action RecognitionDecoderText-Queried Audio Source Separation via Hierarchical Modeling
Target audio source separation with natural language queries presents a promising paradigm for extracting arbitrary audio events through arbitrary text descriptions. Existing methods mainly face two challenges, the diffi…
Audio Source SeparationNatural Language QueriesTowards Unsupervised Image Captioning with Shared Multimodal Embeddings
Understanding images without explicit supervision has become an important problem in computer vision. In this paper, we address image captioning by generating language descriptions of scenes without learning from annotat…
Image CaptioningLanguage ModelingLanguage ModellingSentence+2