paper-with-me

홈 › Papers

Semantic Structure of Feature Space in Large Language Models

2026-04-29 · Austin C. Kozlowski, Andrei Boutyline arxiv

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.

📄 PDF Abstract BibTeX arXiv:2604.27169

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Invariant Features in Language Models: Geometric Characterization and Model Attribution

2026-05-07 · Agnibh Dasgupta, Abdullah Tanvir, Xin Zhong arxiv

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

2025-08-04 · Austin C. Kozlowski, Callin Dai, Andrei Boutyline arxiv

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

2024-06-05 · Mona Ahmadian, Frank Guerin, Andrew Gilbert

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 RecognitionDecoder

Text-Queried Audio Source Separation via Hierarchical Modeling

2025-05-27 · Xinlei Yin, Xiulian Peng, Xue Jiang, Zhiwei Xiong 외

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 Queries

Towards Unsupervised Image Captioning with Shared Multimodal Embeddings

2019-08-25 · ICCV 2019 10 · Iro Laina, Christian Rupprecht, Nassir Navab

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