Shengjie Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Shengjie Liu has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Christopher G. Healey
Department of Computer Science and the Institute for Advanced Analytics, North Carolina State University, Raleigh, NC, USA
1 shared publication - Jing Wu
98121 20171 55414 Seattle Herndon Minneapolis WA VA MN
1 shared publication - Jingyuan Bao
North Carolina State University University of Illinois Urbana-Champaign Northwestern University North Carolina State University University of Illinois Urbana-Champaign North Carolina State University
1 shared publication - Naira Hovakimyan
Department of Mechanical Science and Engineering, University of Illinois Urbana-Champaign, Urbana, IL, USA
1 shared publication - Wenyi Wang
Department of Statistics North Carolina State University Raleigh North Carolina USA
1 shared publication
Latest Publications
- Open Access
Towards a Robust Retrieval-Based Summarization System
This paper describes an investigation of the robustness of large language models (LLMs) for retrieval augmented generation (RAG)-based summarization tasks. While LLMs provide summarization capabilities, their performance in complex, real-world scenarios remains under-explored. Our first contribution is LogicSumm, an innovative evaluation framework incorporating realistic scenarios to assess LLM robustness during RAG-based summarization. Based on limitations identified by LogiSumm, we then developed SummRAG, a comprehensive system to create training dialogues and fine-tune a model to enhance robustness within LogicSumm's scenarios. SummRAG is an example of our goal of defining structured methods to test the capabilities of an LLM, rather than addressing issues in a one-off fashion. Experimental results confirm the power of SummRAG, showcasing improved logical coherence and summarization quality. Data, corresponding model weights, and Python code are available online.
Open AccessTowards a Robust Retrieval-Based Summarization System
This paper describes an investigation of the robustness of large language models (LLMs) for retrieval augmented generation (RAG)-based summarization tasks. While LLMs provide summarization capabilities, their performance in complex, real-world scenarios remains under-explored. Our first contribution is LogicSumm, an innovative evaluation framework incorporating realistic scenarios to assess LLM robustness during RAG-based summarization. Based on limitations identified by LogiSumm, we then developed SummRAG, a comprehensive system to create training dialogues and fine-tune a model to enhance robustness within LogicSumm's scenarios. SummRAG is an example of our goal of defining structured methods to test the capabilities of an LLM, rather than addressing issues in a one-off fashion. Experimental results confirm the power of SummRAG, showcasing improved logical coherence and summarization quality. Data, corresponding model weights, and Python code are available online.