3 papers
cs.HC2026
Just-In-Time Objectives: A General Approach for Specialized AI Interactions
Michelle S. Lam, Omar Shaikh, Hallie Xu +5
Large language models promise a broad set of functions, but when not given a specific objective, they default to generic results. We demonstrate that inferring the user's in-the-mo…
cs.CL2025
BLADE: Benchmarking Language Model Agents for Data-Driven Science
Ken Gu, Ruoxi Shang, Ruien Jiang +13
Data-driven scientific discovery requires the iterative integration of scientific domain knowledge, statistical expertise, and an understanding of data semantics to make nuanced an…
cs.HC2024
Designing LLM Chains by Adapting Techniques from Crowdsourcing Workflows
Madeleine Grunde-McLaughlin, Michelle S. Lam, Ranjay Krishna +2
LLM chains enable complex tasks by decomposing work into a sequence of subtasks. Similarly, the more established techniques of crowdsourcing workflows decompose complex tasks into…