Papers by Changkai Ji

2 papers
RoBGuard: Enhancing LLMs to Assess Risk of Bias in Clinical Trial Documents (2025.coling-main)

Copied to clipboard

Challenge: Existing approaches to assess the risk of bias in RCTs focus on manually crafted prompts and a restricted set of simple questions, limiting their accuracy and generalizability.
Approach: They propose a framework for enhancing Large Language Models to assess the risk of bias in RCTs by reformulation, document parsing and multi-expert collaboration.
Outcome: The proposed framework outperforms existing methods on the RoB-Item and RoB domains.
Large Language Models are Complex Table Parsers (2023.emnlp-main)

Copied to clipboard

Challenge: Extensive experiments and results on Complex Table QA datasets, i.e., the open-domain dataset HiTAB and the aviation domain dataset AIT-QA show that our approach significantly outperforms previous work on both datasets.
Approach: They propose to incorporate Generative Pre-trained Transformer 3.5 to address the specific challenges posed by Complex Table QA by reconstructing tables into tuples and using prompt templates to create dialogues.
Outcome: The proposed approach outperforms previous work on complex table parsing datasets and leads to state-of-the-art (SOTA) performance.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations