4 papers
Exploring Generative Process Reward Modeling for Semi-Structured Data: A Case Study of Table Question Answering
Lei Tang, Wei Zhou, Mohsen Mesgar
Process reward models (PRMs) enhance complex reasoning in large language models (LLMs) by evaluating candidate solutions step-by-step and selecting answers based on aggregated step…
Texts or Images? A Fine-grained Analysis on the Effectiveness of Input Representations and Models for Table Question Answering
Wei Zhou, Mohsen Mesgar, Heike Adel +1
In table question answering (TQA), tables are encoded as either texts or images. Prior work suggests that passing images of tables to multi-modal large language models (MLLMs) perf…
p2-TQA: A Process-based Preference Learning Framework for Self-Improving Table Question Answering Models
Wei Zhou, Mohsen Mesgar, Heike Adel +1
Table question answering (TQA) focuses on answering questions based on tabular data. Developing TQA systems targets effective interaction with tabular data for tasks such as cell r…
Efficient Multi-Agent Collaboration with Tool Use for Online Planning in Complex Table Question Answering
Wei Zhou, Mohsen Mesgar, Annemarie Friedrich +1
Complex table question answering (TQA) aims to answer questions that require complex reasoning, such as multi-step or multi-category reasoning, over data represented in tabular for…