Papers by Jieran Li

1 papers
Beyond Output Confidence: Epistemic-Aware Hallucination Detection with Answer-Level Signals (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for detecting hallucinations are confounded by epistemic uncertainty and cannot distinguish genuine uncertainty from fabricated content.
Approach: They propose a model-agnostic metric that captures epistemic boundary deviations by measuring answer-level stability across multiple stochastic forward passes.
Outcome: The proposed metric outperforms strong uncertainty-only baselines and can be used to detect hallucinations on open-domain question answering, dialogue generation, and code completion.

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