Papers by Daniil Korbut

1 papers
Evolutionary Search for Automated Design of Uncertainty Quantification Methods (2026.acl-srw)

Copied to clipboard

Challenge: Qualitative analysis reveals that different LLMs employ qualitatively distinct evolutionary strategies for automating, interpretable hallucination detector design.
Approach: They apply LLM-powered evolutionary search to discover unsupervised UQ methods represented as Python programs and apply them to atomic claim verification.
Outcome: The proposed methods outperform strong manually-designed baselines while generalizing robustly out-of-distribution.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations