5 papers
CLARity: Reasoning Consistency Alone Can Teach Reinforced Experts
Jiuheng Lin, Cong Jiang, Zirui Wu +2
Training expert LLMs in domains with scarce data is difficult, often relying on multiple-choice questions (MCQs). However, standard outcome-based reinforcement learning (RL) on MCQ…
RefTool: Reference-Guided Tool Creation for Knowledge-Intensive Reasoning
Xiao Liu, Da Yin, Zirui Wu +1
Large Language Models (LLMs) can enhance their reasoning capabilities by using external tools. However, many tasks lack predefined tools. Prior works have explored instructing LLMs…
ProTrix: Building Models for Planning and Reasoning over Tables with Sentence Context
Zirui Wu, Yansong Feng
Tables play a crucial role in conveying information in various domains. We propose a Plan-then-Reason framework to answer different types of user queries over tables with sentence…
Haste Makes Waste: Evaluating Planning Abilities of LLMs for Efficient and Feasible Multitasking with Time Constraints Between Actions
Zirui Wu, Xiao Liu, Jiayi Li +2
While Large Language Model-based agents have demonstrated substantial progress in task completion, existing evaluation benchmarks tend to overemphasize single-task performance, wit…
Automated Annotation of Evolving Corpora for Augmenting Longitudinal Network Data: A Framework Integrating Large Language Models and Expert Knowledge
Xiao Liu, Zirui Wu, Jiayi Li +3
Longitudinal network data are essential for analyzing political, economic, and social systems and processes. In political science, these datasets are often generated through human…