Recursively summarizing enables long-term dialogue memory in large language models
Qingyue Wang, Yanhe Fu, Yanan Cao, Shuai Wang, Zhiliang Tian, Liang Ding
Who it is from
- Institute of Information Engineeringaffiliation declared by the authors, according to OpenAlex
- National University of Defense Technologyaffiliation declared by the authors, according to OpenAlex
Other papers from the same organizations
- A Survey on Model Compression for Large Language ModelsInstitute of Information Engineering · 817 citations
- Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM ReasoningAlibaba Group · 722 citations
- A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-ModalNational University of Defense Technology · 555 citations
- Logit Standardization in Knowledge DistillationInstitute of Information Engineering · 484 citations
- Large Language Models are Few-Shot Summarizers: Multi-Intent Comment Generation via In-Context LearningNational University of Defense Technology · 296 citations
- Restoring Images in Adverse Weather Conditions via Histogram TransformerInstitute of Information Engineering · 262 citations