conftrace_

honest alignment

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

knowledge quadrant (1) query abstention (1) large language model (1) truthful knowledge (1) noisy retrieval (1) knowledge boundary (1) retrieval-augmented generation (1) weak-to-strong generalization (1) direct preference optimization (1)

Papers

Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG ACL 2025 Weak-to-Strong Honesty Alignment via Learning-to-Rank Supervision ACL 2025