Lei Ding
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes a method to correct biased language models by aligning human-verified positives with unlabelled outputs in a fixed embedding space.
This paper proposes FinSAgent, an evidence-grounded multi-agent framework for financial question answering over SEC filings, which improves retrieval coverage and answer correctness through corpus-side conditioning.
Papers
FinSAgent: Corpus-Aligned Multi-Agent RAG Framework for Evidence-Grounded SEC Filing Question Answering
Jijun Chi, Zhenghan Tai, Hanwei Wu, Tung Sum Thomas Kwok +19 more
This paper proposes FinSAgent, an evidence-grounded multi-agent framework for financial question answering over SEC filings, which improves retrieval coverage and answer correctness through corpus-sid…