Ziyuan Zhuang — accepted AI-conference papers

2024

Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments

Sitao Cheng, Ziyuan Zhuang, Yong Xu, Fangkai Yang, Chaoyun Zhang, Xiaoting Qin +6

ACL 2024findings

Large Language Models (LLMs) have shown potential in reasoning over structured environments, e.g., knowledge graphs and tables. Such tasks typically require multi-hop reasoning, i.e., match natural language utterance with instances in the environment. Previous works adopt LLMs to incrementally build…

Cited by 18 Source ↗PDF ↗code ↗Scholar ↗

2024

EfficientRAG: Efficient Retriever for Multi-Hop Question Answering

Ziyuan Zhuang, Zhiyang Zhang, Sitao Cheng, Fangkai Yang, Jia Liu, Shujian Huang +4

EMNLP 2024main

Retrieval-augmented generation (RAG) methods encounter difficulties when addressing complex questions like multi-hop queries.While iterative retrieval methods improve performance by gathering additional information, current approaches often rely on multiple calls of large language models (LLMs).In t…

Cited by 8 Source ↗PDF ↗code ↗Scholar ↗