Long-term memory enables Large Language Models (LLMs) to maintain coherent and personalized interactions across extended conversations. However, existing memory systems face two key challenges: (1) Information Entanglement, where heterogeneous information is mixed within coarse-grained memory units; and (2) Organizatio...
Xin-Ying Qian, Ying Zhang, Yu Zhao et al.· 0 citations
Think Checklist Reward (TCR), a process-oriented reward for RL-based preference alignment that converts preference pairs into sample-specific thinking checklists and uses them to evaluate whether the generated reasoning trace addresses the preference-implied considerations.
Xu-Bo Liu, Wenya Guo, Ruxue Yan et al.· arXiv.org· 0 citations
SSR, a Structured Subgraph Retrieval framework for TKGQA with Large Language Models, demonstrates that SSR consistently outperforms strong baselines by a clear margin, achieving state-of-the-art performance.
Ying Zhang, Li Zhang, Wenya Guo et al.· Annual International ACM SIG...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.