SyncAI.news, a Varaisys broadcasting
RelCheck: Dual-Evidence Spatial Grounding for VLM Hallucination Correction
SP

Siddhi Patil, Navrati Saxena, William B. Andreopoulos

· 1 min read

ResearcharXiv cs.CV

RelCheck: Dual-Evidence Spatial Grounding for VLM Hallucination Correction

arXiv:2609.27890v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) fre- quently generate text that is inconsistent with the input image. While object- and attribute-level hallucinations have received considerable attention, relational hallucinations (incorrect de- scriptions of spatial or interactive relationships between objects) remain largely unaddressed by existing post-hoc correction methods. We present RelCheck, a training-free post-hoc correction pipeline that augments object-level visual grounding with dual relational evidence: learned scene-graph triples from RelTR and deterministic spatial predicates from bounding-box geometry. These combine with a Woodpecker-style object claim layer to form a three-layer visual knowledge base, which a language model corrector uses to rewrite hallucinated text. Evaluated on LLaVA v1 13B, RelCheck achieves a total MME hallucination score of 630.0 versus 585.0 for a Woodpecker-style baseline, with the largest gain on the position subtask (+31.7 points, accuracy+ improving from 0.367 to 0.600). A four-configuration ablation confirms that both relational layers contribute independently (McNemar p = 0.025). These results show that structured relational evidence meaningfully improves post-hoc hallucination correction on the spatial reasoning subtasks where current MLLMs are most deficient.

Original source

This story was published by arXiv cs.CV and written by Siddhi Patil, Navrati Saxena, William B. Andreopoulos. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News