让大模型学会“不知道就承认”，用激励机制打造可靠的选择性回答，直击幻觉痛点。
arXiv:2604.03904v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often produce confident but incorrect answers, in part because …
RAG评估新思路：能用确定性检查就绝不用LLM判断，无法验证时大胆弃权，杜绝虚假引用蒙混过关。
Fail-closed groundedness, deterministic corroborators, and a self-test — because an evaluator should be more trustworthy than the thing it grades. The…
提出自我感知RAG方法，解决检索知识与参数知识冲突时的信任与弃权决策问题。
arXiv:2605.18792v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) improves large language models (LLMs) by incorporating external…