Publications
FinDVer: Explainable Claim Verification over Long and Hybrid-content Financial Documents
Yilun Zhao, Yitao Long, Tintin Jiang, Weiyuan Chen, Chengye Wang, Hongjun Liu, Xiangru Tang, Yiming Zhang, Chen Zhao, Arman Cohan EMNLP 2024 [code/data]
KnowledgeMath: Knowledge-Intensive Math Word Problem Solving in Finance Domains
Yilun Zhao*, Hongjun Liu*, Yitao Long, Rui Zhang, Chen Zhao, Arman Cohan ACL 2024 (Oral) [code/data] Investigate LLMs' capabilities in solving knowledge-intensive math word problems.
DocMath-Eval: Evaluating Numerical Reasoning Capabilities of LLMs in Understanding Long Documents with Tabular Data
Yilun Zhao*, Yitao Long*, Hongjun Liu, Linyong Nan, Lyuhao Chen, Ryo Kamoi, Yixin Liu, Xiangru Tang, Rui Zhang, Arman Cohan ACL 2024 (Oral) [code/data] Propose a new evaluation benchmark for numerical reasoning in financial documents containing both textual and tabular data.
TaPERA: A Modular Framework for Long-form Table Question Answering
Yilun Zhao, Lyuhao Chen, Arman Cohan, Chen Zhao ACL 2024 Develop modular approach that decomposes the long-form table QA process into three sub-modules: QA-based Content Planner, Execution-based Table Reasoner and Answer Generator to mitigate hallucination issues.
QTSumm: Query-Focused Summarization over Tabular Data
Yilun Zhao, Zhenting Qi, Linyong Nan, Boyu Mi, Yixin Liu, Weijin Zou, Simeng Han, Ruizhe Chen, Xiangru Tang, Yumo Xu, Dragomir Radev, Arman Cohan EMNLP 2023 [code/data] Propose a new query-focused table summarization task where text generation models have to perform human-like reasoning and analysis over the given table to generate a tailored summary.
Investigating Table-to-Text Generation Capabilities of LLMs in Real-World Information Seeking Scenarios
Yilun Zhao*, Haowei Zhang*, Shengyun Si*, Linyong Nan, Xiangru Tang, Arman Cohan EMNLP 2023 industry [code/data] LLM outperforms fine-tuned systems in table-to-text generation, evaluation, and feedback generation.
A Systematic Study of Table QA Robustness Against Human-Annotated Adversarial Perturbations
Yilun Zhao, Chen Zhao, Linyong Nan, Zhenting Qi, Wenlin Zhang, Xiangru Tang, Boyu Mi, Dragomir Radev ACL 2023 [code/data] Analyze robustness of TableQA systems using a human labeled evaluation set of targeted adversarial perturbations.
LOFT: Enhancing Faithfulness and Diversity for Table-to-Text Generation via Logic Form Control
Yilun Zhao*, Zhenting Qi*, Linyong Nan, LJ Yu Flores, Dragomir Radev EACL 2023 (Oral) [code/data] Apply logical form as fact checker and content planner to improve faithfulness and text-diversity of logical table-to-text generation.
ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples
Yilun Zhao, Linyong Nan, Zhenting Qi, Rui Zhang, Dragomir Radev EMNLP 2022 [code/data] Inject table reasoning skills into large language models by synthesizing corresponding QA examples as pre-training corpus.
MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data
Yilun Zhao, Yunxiang Li, Chenying Li, Rui Zhang ACL 2022 [code/data] Construct QA benchmark that requires model to aggregate numerical information from text and hierarchical tables to answer complex questions about financial reports.
|