← all papers · overview

Beyond Under-alignment: Atomic Preference Enhanced Factuality Tuning For Large Language Models

Abstract

Large language models (LLMs) have achieved remarkable success but still tend to generate factually erroneous responses, a phenomenon known as hallucination. A recent trend is to use preference learning to fine-tune models to align with factuality. However, existing work primarily evaluates fine-tuned models on in-domain (ID) datasets and the factuality on out-of-domain (OOD) datasets remains under

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).