LM4Sci Workshop

The workshop on Large Language Modeling for Scientific Discovery - exploring the intersection of artificial intelligence and scientific discovery.

LM4Sci 2026

Language Models for Scientific Discovery

Date: October 9, 2026

Location: San Francisco, USA (co-located with COLM '26)

About the Workshop

Language Models for Scientific Discovery

Significant advancements in Large Language Models (LLMs) have spurred interest in using these frontier AI models to assist researchers in various scientific tasks, such as:

Idea Generation & Brainstorming

Accelerating the research ideation process through AI-assisted brainstorming and concept exploration.

Literature Review & Synthesis

Searching, synthesizing literature reviews and enabling literature-based question-answering.

Data Analysis & Discovery

Using AI for data-driven discovery and complex scientific data analysis.

Research Pipeline Automation

End-to-end research pipeline including experiment execution, ML engineering, and paper generation.

Organizing Committee

Workshop Organizers

Chenglei Si

Stanford University

Shannon Zejiang Shen

MIT

Hanane Nour Moussa

Ohio State University

Yanzhe Zhang

Georgia Institute of Technology

Akari Asai

University of Washington

Mark Yatskar

University of Pennsylvania

Huan Sun

Ohio State University

Diyi Yang

Stanford University

Our Focus

Bringing Communities Together

The focus of our workshop is on developing LLMs and AI systems that can accelerate scientific research in various scientific domains and assist human researchers. We aim to bring together researchers from different communities, including ML, NLP, Human-Computer Interaction, and various scientific disciplines such as biology and chemistry, to work together on the design, development, and evaluation of various forms of scientific LLMs and systems.

Many of these AI systems are shown to be helpful tools for human researchers to accelerate the scientific discovery process. For example, systems like Scideator provide assistance such as key facet extraction from papers and automated novelty assessment with explanations to facilitate ideation. Beyond these simple collaboration modes, there is still a huge under-explored space for building helpful AI tools for accelerating scientific research and fostering more effective human-AI collaboration in science.