Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
Improved LLM Agents for Financial Document Question Answering
Nelvin Tan, Zian Seng, Liang Zhang +3
Large language models (LLMs) have shown impressive capabilities on numerous natural language processing tasks. However, LLMs still struggle with numerical question answering for fi…
cs.CL2025
AutoMetrics: Approximate Human Judgements with Automatically Generated Evaluators
Michael J. Ryan, Yanzhe Zhang, Amol Salunkhe +3
Evaluating user-facing AI applications remains a central challenge, especially in open-ended domains such as travel planning, clinical note generation, or dialogue. The gold standa…
cs.CL2025
Does Using Counterfactual Help LLMs Explain Textual Importance in Classification?
Nelvin Tan, James Asikin Cheung, Yu-Ching Shih +2
Large language models (LLMs) are becoming useful in many domains due to their impressive abilities that arise from large training datasets and large model sizes. More recently, the…