Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
MiRD: Reliable Set-Valued Prediction for Open-Ended Question Answering via Miscoverage Risk Decomposition
Anqi Hu, Zhiyuan Wang, Zijun Jia +1
Reliable set-valued prediction provides a principled way to mitigate hallucinations in open-ended question answering (QA), yet existing conformal approaches typically rely on a fra…
cs.CL2026
BalanceRAG: Joint Risk Calibration for Cascaded Retrieval-Augmented Generation
Zijun Jia, Yuanchang Ye, Sen Jia +6
Large language models (LLMs) can enhance factuality via retrieval-augmented generation (RAG), but applying RAG to every query is unnecessary when the model-only answer is reliable.…