"Excuse me, may I say something..." CoLabScience, A Proactive AI Assistant for Biomedical Discovery and LLM-Expert Collaborations
Yang Wu, Jinhong Yu, Jingwei Xiong, Zhimin Tao, Xiaozhong Liu
TLDR
CoLabScience is a proactive AI assistant that uses PULI to intervene in scientific discussions, enhancing biomedical discovery and LLM-expert collaboration.
Key contributions
- Introduces CoLabScience, a proactive LLM assistant for biomedical discovery and expert collaboration.
- Presents PULI, a novel reinforcement learning framework for timely, context-aware interventions.
- Introduces BSDD, a new benchmark dataset of simulated biomedical dialogues for intervention points.
- PULI significantly outperforms baselines in intervention precision and collaborative task utility.
Why it matters
Reactive LLMs limit their utility in dynamic scientific collaboration. CoLabScience introduces a proactive assistant that autonomously intervenes, enhancing human-AI teamwork. This approach could significantly accelerate biomedical discovery by making LLMs more effective partners.
Original Abstract
The integration of Large Language Models (LLMs) into scientific workflows presents exciting opportunities to accelerate biomedical discovery. However, the reactive nature of LLMs, which respond only when prompted, limits their effectiveness in collaborative settings that demand foresight and autonomous engagement. In this study, we introduce CoLabScience, a proactive LLM assistant designed to enhance biomedical collaboration between AI systems and human experts through timely, context-aware interventions. At the core of our method is PULI (Positive-Unlabeled Learning-to-Intervene), a novel framework trained with a reinforcement learning objective to determine when and how to intervene in streaming scientific discussions, by leveraging the team's project proposal and long- and short-term conversational memory. To support this work, we introduce BSDD (Biomedical Streaming Dialogue Dataset), a new benchmark of simulated research discussion dialogues with intervention points derived from PubMed articles. Experimental results show that PULI significantly outperforms existing baselines in both intervention precision and collaborative task utility, highlighting the potential of proactive LLMs as intelligent scientific assistants.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.