Research map / Large language models / Language, safety and interpretability
LLM-based Embeddings: Attention Values Encode Sentence Semantics Better Than Hidden States
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Closest papers by meaning
- NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models (ICLR 2025 · similarity 0.89)
- Attention with Trained Embeddings Provably Selects Important Tokens (NeurIPS 2025 · similarity 0.87)
- Narrowing the Gap between Supervised and Unsupervised Sentence Representation Learning with Large Language Model (AAAI 2024 · similarity 0.87)
- Attention Sinks: A 'Catch, Tag, Release' Mechanism for Embeddings (NeurIPS 2025 · similarity 0.86)
- LoFiT: Localized Fine-tuning on LLM Representations (NeurIPS 2024 · similarity 0.86)
- Crafting Interpretable Embeddings for Language Neuroscience by Asking LLMs Questions (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.