HalCECE: A Framework for Explainable Hallucination Detection through Conceptual Counterfactuals in Image Captioning
This work addresses the critical issue of hallucinations in vision-language models, which is important for improving trustworthiness in AI systems, though it appears incremental by building on existing counterfactual techniques.
The paper tackles the problem of hallucination detection in vision-language models for image captioning by proposing HalCECE, a framework that uses conceptual counterfactuals to identify and correct hallucinations, achieving interpretable results through semantically meaningful edits.
In the dynamic landscape of artificial intelligence, the exploration of hallucinations within vision-language (VL) models emerges as a critical frontier. This work delves into the intricacies of hallucinatory phenomena exhibited by widely used image captioners, unraveling interesting patterns. Specifically, we step upon previously introduced techniques of conceptual counterfactual explanations to address VL hallucinations. The deterministic and efficient nature of the employed conceptual counterfactuals backbone is able to suggest semantically minimal edits driven by hierarchical knowledge, so that the transition from a hallucinated caption to a non-hallucinated one is performed in a black-box manner. HalCECE, our proposed hallucination detection framework is highly interpretable, by providing semantically meaningful edits apart from standalone numbers, while the hierarchical decomposition of hallucinated concepts leads to a thorough hallucination analysis. Another novelty tied to the current work is the investigation of role hallucinations, being one of the first works to involve interconnections between visual concepts in hallucination detection. Overall, HalCECE recommends an explainable direction to the crucial field of VL hallucination detection, thus fostering trustworthy evaluation of current and future VL systems.