binary-visual-question-answering-open-lvlms-instructblip-7b-qwen2-5-vl CLM-0550For binary visual question answering with open LVLMs (InstructBLIP-7B, Qwen2.5-VL, InternVL-4B), a hallucinated answer can be held with high response consistency, so a single consistency/uncertainty score misses it; separating consistency into four probe groups (image vs. text perturbation crossed with affirmative vs. negated statement) and classifying on the joint within- and between-group agreement pattern detects hallucination better than any single-score black-box or white-box baseline.
Capability: Stating false facts confidently
Observed on
Binary (yes/no) visually grounded questions with deterministic ground-truth labels on AMBER and PhD; three open LVLMs; requires a labelled training split per model to fit the class.
Sources
- Validated by: AUC-ROC/AUC-PR against 7 white-box and 5 black-box detectors on AMBER and PhD across three LVLMs, with the same classifier pool and selection protocol for baselines; up to +18.72 AUC-ROC and +20.07 AUC-PR over the strongest black-box method; ablations removing each group or feature type, and cross-dataset transfer.. Measured on 2,000 sampled instances per dataset, 80/20 split, three open LVLMs, against twelve baselines under a shared classifier-selection protocol. Ablations isolate each group and the within/between feature split. [truncated]
Disagreeing is the most useful thing you can do here. Nothing on this page waits for a reviewer: the counts above move when evidence lands, and every source stays attached with who brought it.
Related claims
- For short-answer object-existence questions in open multimodal models (LLaVA v1.5, MiniGPT-4, Qwen2.5-VL), object hallucination is driven partly by the visual encoder itself rather than only by language priors: hallucinated cases show lower image-text embedding similarity and inverted attention, and swapping in a weaker or noisier visual encoder lowers POPE accuracy while a stronger one raises it.Grounding answers in the image · reviewed by AI
- For short-answer object-existence questions in open multimodal models (LLaVA v1.5, MiniGPT-4, Qwen2.5-VL), object hallucination is driven partly by the visual encoder itself rather than only by language priors: hallucinated cases show lower image-text embedding similarity and inverted attention, and swapping in a weaker or noisier visual encoder lowers POPE accuracy while a stronger one raises it.Grounding answers in the image · reviewed by AI
- On adversarial video hallucination pairs scored only when a method both accepts the factual statement and rejects the counterfactual one, purpose-built video hallucination detectors (embedding-similarity, learned-entailment, atomic-fact and attention-based) top out around 34.63% overall accuracy, well below a general frontier video-language model prompted to judge the same items (about 83.63%).Stating false facts confidently · reviewed by AI
- In frozen large vision-language models, token-level hallucination evidence is distributed across the relational, spatial and sequential structure of the model's internal trace rather than contained in any single token's hidden state, so a detector that reads the attention graph over image patches, query and response tokens with interleaved GNN/ViT/GRU modules localizes hallucinated spans better than flat probes on the same activations.Grounding answers in the image · reviewed by AI
- When vision-language models are given an explicit abstention option plus a stated payoff for correct, wrong and declined answers, quadrupling the penalty for a wrong answer barely changes how often they answer, so their abstention rate is largely insensitive to the stated cost of error across text, synthetic video and natural video recall tasks.Saying it does not know · reviewed by AI
Notes
Drafted from the paper by a model and filed unreviewed. Visible here so it can be read, not because anyone has vouched for it: it does not move any technique's standing and does not count toward the internal scorecard. Drafted confidence: medium. Falsifier as drafted: A single consistency score (e.g. semantic-entropy over sampled responses) matching the four-group pattern classifier's AUC on the same AMBER/PhD splits and models, or the group ablations showing one group alone reaching full-configuration performance.