arXiv (All)
open access
Unlearning Deceptive Behaviors in LLMs with Contrastive Forget Sets
Large language models often know the truth and say otherwise: a model that answers correctly when asked neutrally will affirm a user's mistaken belief, or misstate a fact its system prompt wants hidden, once the context rewards it. Such deception is a behavior conditioned on context, not knowledge,
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
- Confidently Deceptive: On the Relationship Between Confidence and Deception in LLMs#1118657
- The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstaining#1117676
- LLMs learn different forms of metacognition when trained to predict their own accuracy#1118959
- BiasGym: A Simple and Generalizable Framework for Analyzing and Removing Biases through Injection#820232
- How LLMs Are Persuaded: A Few Attention Heads, Rerouted#1128593
Record · ID 1143510
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