← Search

Nancy Guo

2 accepted papers

2026

On the Eligibility of LLMs for Counterfactual Reasoning: A Decompositional Study

ICLR 2026poster

Counterfactual reasoning has emerged as a crucial technique for generalizing the reasoning capabilities of large language models (LLMs). By generating and analyzing counterfactual scenarios, researchers can assess the adaptability and reliability of model decision-making. Although prior work has sho…

Cited by 0Source ↗Scholar ↗
2026

Small Agent Group is the Future of Digital Health

ICML 2026poster

The rapid adoption of large language models (LLMs) in digital health has been driven by a "scaling-first" philosophy, i.e., the assumption that clinical intelligence increases with model size and data. However, real-world clinical needs include not only effectiveness, but also reliability and reason…

Cited by 6Source ↗Scholar ↗