arXiv (All)
open access
Consistency Training Suppresses Cue Following Without Teaching Cue Selectivity
Language models often change answers because of a cue, a hint such as "I believe the answer is B" that gives no valid evidence. Consistency training (CT) trains a model to answer the same with and without the cue. Four CT methods apply this idea to output tokens (BCT), residual activations (ACT), at
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
- Locating Answer-Correctness Signals in Frozen Large Language Models#1142012
- Detectable Only Where It Is Confounded: What Verified Duplication Counts Say About Membership Evidence in Language Models#997811
- Detectable Only Where It Is Confounded: What Verified Duplication Counts Say About Membership Evidence in Language Models#673430
- Imagining Recovery: Inference-Time Counterfactual Realignment for Vision-Language-Action Models#609245
- SkillApt: Learning When to Activate Agent Skills from Counterfactual Evidence#1063074
Record · ID 1400472
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