4 papers
K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks
Gil Pasternak
Recursive Feature Machines (RFMs) are a class of kernel machines that utilize the Average Gradient Outer Product (AGOP) as a mechanism for feature learning. They have been shown to…
Beyond Reactivity: Measuring Proactive Problem Solving in LLM Agents
Gil Pasternak, Dheeraj Rajagopal, Julia White +4
LLM-based agents are increasingly moving towards proactivity: rather than awaiting instruction, they exercise agency to anticipate user needs and solve them autonomously. However,…
GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface
Urchade Zaratiana, Gil Pasternak, Oliver Boyd +2
Information extraction (IE) is fundamental to numerous NLP applications, yet existing solutions often require specialized models for different tasks or rely on computationally expe…
Measuring Risk of Bias in Biomedical Reports: The RoBBR Benchmark
Jianyou Wang, Weili Cao, Longtian Bao +6
Systems that answer questions by reviewing the scientific literature are becoming increasingly feasible. To draw reliable conclusions, these systems should take into account the qu…