AI RESEARCH
When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation
arXiv CS.LG
•
ArXi:2602.11908v3 Announce Type: replace-cross LLMs are widely used, yet they remain prone to factual errors that erode user trust and limit adoption in high-risk settings. One approach to mitigate this risk is to equip models with uncertainty estimation mechanisms that abstain when confidence is low. However, this binary "all-or-nothing" approach is excessively restrictive in long-form settings, often discarding valuable information. We