3 papers
cs.AI2025
WebLists: Extracting Structured Information From Complex Interactive Websites Using Executable LLM Agents
Arth Bohra, Manvel Saroyan, Danil Melkozerov +5
Most recent web agent research has focused on navigation and transaction tasks, with little emphasis on extracting structured data at scale. We present WebLists, a benchmark of 200…
cs.CL2024
WILBUR: Adaptive In-Context Learning for Robust and Accurate Web Agents
Michael Lutz, Arth Bohra, Manvel Saroyan +2
In the realm of web agent research, achieving both generalization and accuracy remains a challenging problem. Due to high variance in website structure, existing approaches often f…
cs.CL2023
BYOC: Personalized Few-Shot Classification with Co-Authored Class Descriptions
Arth Bohra, Govert Verkes, Artem Harutyunyan +2
Text classification is a well-studied and versatile building block for many NLP applications. Yet, existing approaches require either large annotated corpora to train a model with…