Papers by Zeliang Li
1+1>2: A Synergistic Sparse and Low-Rank Compression Method for Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Low-rank approximation compresses the model by retaining its essential structure with minimal information loss. |
| Approach: | They propose a method that leverages the strengths of pruning and low-rank approximation for LLMs. |
| Outcome: | The proposed methods surpass the existing methods on LLaMA and Qwen2.5 models. |
Momoka-RAG: MCTS-Organized Mapping of Knowledge Associations for Long-Document Retrieval Augmented Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing frameworks that rely on fixed-length chunking are unsuitable for long-document tasks due to their passive and mechanical approach to knowledge structure. |
| Approach: | They propose a framework that utilizes Monte Carlo Tree Search to proactively uncover connections among chunks and construct optimal semantic information paths with the objective of completing semantic relationships. |
| Outcome: | The proposed framework achieves higher precision while maintaining competitive recall compared to other RAG frameworks. |
SAKI-RAG: Mitigating Context Fragmentation in Long-Document RAG via Sentence-level Attention Knowledge Integration (2025.emnlp-main)
Copied to clipboard
| Challenge: | Traditional Retrieval-Augmented Generation (RAG) frameworks segment documents into larger chunks to preserve contextual coherence . however, such chunking methods lead to fragmented contexts, isolated chunk semantics, and broken inter-chunk relationships . |
| Approach: | They propose a framework that maintains granular chunks while recovering their intrinsic semantic connections. |
| Outcome: | The proposed framework achieves better recall and precision compared to other RAG frameworks in long-document retrieval scenarios. |