Large language models (LLMs) increasingly serve as general-purpose interfaces to factual knowledge, but their parameters do not automatically reflect information that changes after pretraining. Knowledge editing (KE) provides a targeted alternative to costly retraining by modifying selected knowledge and preserving unr...
A knowledge-aligned multi-hop retriever, KAMR, which distinguishes anchor triplets that are strongly constrained by the query from connected triplets that are weakly aligned yet structurally linked to the anchors, which consistently improves multi-hop retrieval and downstream question answering performance.
Xiaochen Wang, Yuan Zhong, Haoyu Wang et al.· arXiv.org· 0 citations
HPSE is proposed, which builds a hybrid rollout that steps in to place missing facts onto the student's own trajectory precisely where its coverage fails, while staying on-policy elsewhere.
Tian-Ci Liu, Zi-Han Dong, Tian-Chun Li et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.