arXiv (All)
open access
Can You Trust Your Preference Models? Stackelberg Games for Alignment
Language models are frequently aligned to human preferences via imperfect evaluators whose errors can be exploited during optimization. We train policies to search for comparisons on which an evaluator may reverse the underlying preference, providing candidates for additional supervision. Since huma
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
- Model vs. User: Whose Values Prevail? Inference-Time Value Alignment in Multi-Turn Conversations#1354500
- Axiom Satisfiability of Linear Rewards in Alignment#1215974
- Matching Game Preferences Through Dialogical Large Language Models: A Perspective#392028
- Are Human-Aligned Models Models of Humans? A Turing-Test Gap in Preference Alignment#1052296
- Tail Competition Explains Scaling in Best-of-N Sampling for Verifiable Problems#1345185
Record · ID 1325904
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