Papers by Ziwen Li
AMO-Bench: Large Language Models Still Struggle in High School Math Competitions (2026.findings-acl)
Copied to clipboard
Junlin Liu, Shengnan An, Shuang Zhou, Dan Ma, Yehao Lin, Xinxuan Lv, Xuanlin Wang, Xiaoyu Li, Ziwen Wang, Xuezhi Cao, Xunliang Cai
| Challenge: | Existing benchmarks for mathematical reasoning are becoming less effective due to performance saturation. |
| Approach: | They propose to use a mathematical reasoning benchmark with Olympiad difficulty to evaluate top-tier LLMs. |
| Outcome: | The proposed benchmarks are cross-validated by experts to meet IMO difficulty standards and entirely original problems to prevent performance leakages from data memorization. |
GraPPI: A Retrieve-Divide-Solve GraphRAG Framework for Large-scale Protein-protein Interaction Exploration (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models and Retrieval-Augmented Generation frameworks have accelerated drug discovery, but integrating models into workflows remains challenging. |
| Approach: | They propose a large-scale knowledge graph-based retrieve-divide-solve agent pipeline RAG framework to support large-level PPI signaling pathway exploration. |
| Outcome: | The proposed framework is based on large-scale knowledge graphs and can be used to analyze protein-protein interactions. |
EasyInstruct: An Easy-to-use Instruction Processing Framework for Large Language Models (2024.acl-demos)
Copied to clipboard
Yixin Ou, Ningyu Zhang, Honghao Gui, Ziwen Xu, Shuofei Qiao, Runnan Fang, Lei Li, Zhen Bi, Guozhou Zheng, Huajun Chen
| Challenge: | Large Language Models (LLMs) have improved performance across tasks and domains . instruction tuning is a crucial technique to enhance the capabilities of LLMs - but there is no standard open-source instruction processing framework available for the community . |
| Approach: | They propose an open-source instruction tuning framework for Large Language Models that modularizes instruction generation, selection, prompting and their combination and interaction. |
| Outcome: | The proposed framework is open-source and available on Github. |
RAGPPI: Retrieval-Augmented Generation Benchmark for Protein–Protein Interactions in Drug Discovery (2026.eacl-long)
Copied to clipboard
| Challenge: | Large Language Models and Retrieval-Augmented Generation (RAG) frameworks have supported Target ID, but no benchmark exists for identifying biological impacts of PPIs. |
| Approach: | They propose to build a factual question-answer benchmark of 4,420 question-announced pairs that focus on the potential biological impacts of PPIs. |
| Outcome: | The proposed benchmark is based on 4,420 question-answer pairs with expert-driven data annotation. |