claim-level-hallucination-detection-pipelines-over-image-video-audio-inputs CLM-0369In claim-level hallucination detection pipelines over image, video and audio inputs (both comprehension and generation directions), decomposing an output into atomic claims contributes more to detection accuracy than ensembling several verifier models: removing decomposition costs about 6.6-7.9 macro-F1 across six cross-modal tasks while removing multi-expert majority voting costs about 4.5-5.3.
Capability: Stating false facts confidently
Observed on
Claim-level detection with a GPT-5.2 aggregator and modality-specific expert models, on a 10,000-sample benchmark spanning I2T, V2T, A2T, T2I, T2V, T2A; only one pipeline design te.
Sources
- Measured ablation on a 10,000-sample benchmark across six tasks; the gap between the two ablations is consistent in all six, but the comparison is within one pipeline with one decomposition model (GPT-4.1) and fixed expert sets, so it does not isolate decomposition quality from aggregator capacity.
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
- In synthetic hallucination benchmarks where faithful items are human-written and hallucinated items are LLM-rewrites, a detector's binary score partly measures human-vs-machine style rather than factuality: feeding faithful LLM rewrites of the same truthful articles makes some fine-tuned encoders flag nearly all of them as hallucinated.Whether the measurement made the finding · reviewed by AI
- For encoder-based hallucination/claim-faithfulness detectors moved from general-domain data to biomedical claim verification, which corpus the encoder was pre-trained on matters more than which data it is fine-tuned on: a PubMed-pretrained encoder fine-tuned on a few hundred SciFact pairs beat both a general encoder fine-tuned on the same pairs and a general encoder pre-fine-tuned on a large general hallucination set.Competence in a specialist domain · 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
- For 7-13B multimodal models, verifying each object claim with a frozen open-vocabulary detector lowers object hallucination only if evidence is pooled across semantically equivalent phrasings and checked for spatial agreement (the preferred boxes of different queries overlapping on one instance); a single-query maximum score is a weaker signal, and shuffling the spatial evidence across samples drives its discrimination to chance.Grounding answers in the image · reviewed by AI
- When claim-level uncertainty is estimated from a response-claim graph, anchoring the graph with trusted external priors (edges weighted by entailment from verified source sections) and scoring claims by weighted closeness centrality separates ungrounded claims from repeatedly-generated-but-false ones better than internal-consistency centrality alone, and yields retrieval whose answerability tracks its accuracy instead of the near-100% answer rate GraphRAG shows on the same long documents.Stating false facts confidently · 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: An ablation on the same or similar pipelines where removing ensemble verification degrades macro-F1 more than removing atomic claim decomposition. Drafted stance toward decomposing-long-answers-into-atomic-facts-checking-each: supports -- It extends atomic-claim checking to image, video and audio and shows decomposition is the largest single contributor to detection accuracy.