Measuring Epistemic Humility in Multimodal Large Language Models
Abstract
HumbleBench evaluates multimodal large language models' ability to reject incorrect answers, addressing the issue of hallucinations in visual question answering and decision-making.
Hallucinations in multimodal large language models (MLLMs) -- where the model generates content inconsistent with the input image -- pose significant risks in real-world applications, from misinformation in visual question answering to unsafe errors in decision-making. Existing benchmarks primarily test recognition accuracy, i.e., evaluating whether models can select the correct answer among distractors. This overlooks an equally critical capability for trustworthy AI: recognizing when none of the provided options are correct, a behavior reflecting epistemic humility. We present HumbleBench, a new hallucination benchmark designed to evaluate MLLMs' ability to reject plausible but incorrect answers across three hallucination types: object, relation, and attribute. Built from a panoptic scene graph dataset, we leverage fine-grained scene graph annotations to extract ground-truth entities and relations, and prompt GPT-4-Turbo to generate multiple-choice questions, followed by a rigorous manual filtering process. Each question includes a "None of the above" option, requiring models not only to recognize correct visual information but also to identify when no provided answer is valid. We evaluate a variety of state-of-the-art MLLMs -- including both general-purpose and specialized reasoning models -- on HumbleBench and share valuable findings and insights with the community. By incorporating explicit false-option rejection, HumbleBench fills a key gap in current evaluation suites, providing a more realistic measure of MLLM reliability in safety-critical settings. Our code and dataset are released publicly and can be accessed at https://github.com/maifoundations/HumbleBench.
Community
Evaluating whether models can say "none of the above" to reject incorrect answers
top!
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- SHALE: A Scalable Benchmark for Fine-grained Hallucination Evaluation in LVLMs (2025)
- See Different, Think Better: Visual Variations Mitigating Hallucinations in LVLMs (2025)
- A Survey of Multimodal Hallucination Evaluation and Detection (2025)
- KnowDR-REC: A Benchmark for Referring Expression Comprehension with Real-World Knowledge (2025)
- Self-Rewarding Vision-Language Model via Reasoning Decomposition (2025)
- Evaluating Variance in Visual Question Answering Benchmarks (2025)
- ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper