arXiv (All)
open access
Correctness Is a Direction: Geometric Answer Selection in Language Models
Answer correctness is encoded as a recoverable geometric direction in the hidden states of language models. We show that the mean displacement from incorrect to correct answer representations, computed at approximately 70\% of model depth from fifty labeled examples with no parameter updates, yields
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
- More than half of recent astronomy papers are written with language-model assistance#997660
- Language models can notice an impossible engineering problem yet still report it as solved#1215760
- Language models can notice an impossible engineering problem yet still report it as solved#1194473
- Beyond the Answer Key: Robustness Evaluation of Large Language Models for Step-Level Mathematical Verification#792971
- Beyond the Answer Key: Robustness Evaluation of Large Language Models for Step-Level Mathematical Verification#788967
Record · ID 1200163
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