6 papers
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,…
Correcting Stochastic Update Bias in Preconditioned Language Model Optimizers
Nikhil Nayak, Julia White, Urchade Zaratiana +7
Preconditioned optimizers are central to language model training, but their stochastic update rules are usually treated as direct approximations to population preconditioned descen…
GLiNER2-PII: A Multilingual Model for Personally Identifiable Information Extraction
Urchade Zaratiana, Ash Lewis, George Hurn-Maloney
Reliable detection of personally identifiable information (PII) is increasingly important across modern data-processing systems, yet the task remains difficult: PII spans are heter…
GLiGuard: Schema-Conditioned Classification for LLM Safeguard
Urchade Zaratiana, Mary Newhauser, George Hurn-Maloney +1
Ensuring safe, policy-compliant outputs from large language models requires real-time content moderation that can scale across multiple safety dimensions. However, state-of-the-art…
Pioneer Agent: Continual Improvement of Small Language Models in Production
Dhruv Atreja, Julia White, Nikhil Nayak +5
Small language models are attractive for production deployment due to their low cost, fast inference, and ease of specialization. However, adapting them to a specific task remains…
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…