← Search

Emily Dodwell

2 accepted papers

2026

Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping

ICLR 2026poster

Large language models (LLMs) often exhibit flawed reasoning ability that undermines reliability. Existing approaches to improving reasoning typically treat it as a general and monolithic skill, applying broad training that is inefficient and unable to target specific reasoning errors. We introduce R…

Cited by 0SourcecodeScholar
2026

Unifying and Optimizing Data Values for Selection via Sequential Decision-Making

ICML 2026spotlight

Data selection has emerged as a crucial downstream application of data valuation, yet the theoretical foundations for using data values in selection remain underexplored. We reformulate data selection as a sequential decision-making problem where the optimal selection sequence arises from dynamic pr…

Cited by 0SourceScholar