Papers with hallucination detection method

2 papers
Light-Weight Hallucination Detection using Contrastive Learning for Conditional Text Generation (2025.acl-srw)

Copied to clipboard

Challenge: Existing methods for hallucination detection are limited to the scenario where we can access the LLMs that have generated the outputs.
Approach: They propose a hallucination detection method that uses contrastive learning to pull faithful outputs and input contexts together while pushing hallucinous outputs apart.
Outcome: The proposed method outperforms GPT-4o prompting in binary hallucination detection.
ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for hallucination detection rely on static and isolated representations, overlooking their dynamic evolution across layers.
Approach: They propose a method which captures the cross-layer evolution of hidden states and propose 'ICR Probe' which capture the evolution of the hidden states.
Outcome: The proposed method achieves superior performance with significantly fewer parameters and ablation studies offer deeper insights into the underlying mechanism of the method, improving its interpretability.

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