short-answer-object-existence-questions-open-multimodal-models-llava-v15-minigpt-4
mechanismsingle paperpending review

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.

Ingested from a paper but not yet reviewed by a human. It is deliberately inert: it does not move any technique’s standing, does not count toward the backtest, and is excluded anywhere a claim would carry weight. Read the source before relying on it.

Capability: Grounding answers in the image

Observed on

Binary yes/no existence questions with very short outputs (POPE, MME-Existence); the paper says long-form description settings are more affected by language priors..

Sources

  • Cosine-similarity comparison and Grad-CAM entropy over 500 hallucinated vs 500 correct samples on LLaVA v1.5, plus encoder-swap interventions on POPE (average accuracy 0.842 baseline, 0.739-0.822 degraded, 0.864 with SigLIP-SO400M). Entropy differences are small (5.1%, 6.2%) and the diagnostic analysis is on one model; the encoder interventions do isolate visual feature quality.
Status: pending-reviewLast checked: 2026-09-09Evidence activity: not checked yet
Contest this claim

Disagreeing is the most useful thing you can do here. Both sides of every contested claim in this catalog were assembled by the same person, which is its weakest point.

Related claims

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: Show that varying visual encoder quality leaves object-existence hallucination rates unchanged, or that the image-text similarity and attention-entropy differences between hallucinated and correct cases disappear under matched question difficulty. Proposed technique, not catalogued: Adversarial contrastive fine-tuning on hallucination-flipped image pairs.