arXiv (All)
open access
Measuring Concept Content in Text from LLM Activations: ESG Evidence from Concept Vectors and Linear Probes
artificial-intelligencecomputation-and-languageeconomicsgeneral-economicsi-2-6i-2-7j-4machine-learning
Recent work shows that Large Language Models (LLMs) encode more information in their activations than they show in their responses. We ask whether the information contained in activations could be used as a source of measurement for the presence of concepts. We compare two algorithms for extraction
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Measuring Concept Content in Text from LLM Activations: ESG Evidence from Concept Vectors and Linear Probes#440381
- When Nouns Turn Negative: The Evaluative Absorption Model#204039
- Learning, Fast and Slow: Towards LLMs That Adapt Continually#1354157
- Evaluating LLMs on Conversational Text-to-SQL under Chain Ambiguity and Intent Drift#798188
- Evaluating LLMs on Conversational Text-to-SQL under Chain Ambiguity and Intent Drift#796775
Record · ID 1326378
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive