Papers by Omer Akgul

1 papers
Estimating LLM Consistency: A User Baseline vs Surrogate Metrics (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) are prone to hallucinations and sensitive to prompt perturbations, resulting in inconsistent or unreliable generated text.
Approach: They propose a logit-based ensemble method to measure LLM consistency and propose to use it to evaluate human ratings of LLM reliability.
Outcome: The proposed method matches the best-performing existing metric in estimating human ratings of LLM consistency.

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