Aug 2026· arXiv.org· Vol abs/2609.27890· 0 citations· 22 references
Computer Science
TL;DR
RelCheck is presented, 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 to improve post-hoc hallucination correction on spatial reasoning subtasks where current MLLMs are most deficient.
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.
Large vision-language models often exhibit object hallucination, generating claims that are not supported by the input image. To mitigate this issue, we propose Evidence-Guided Visual Claim Admission (EGVCA), a training-free framework that admits a semantic claim only when it receives sufficient image-dependent support...
Multimodal large language models generate natural-language responses from visual inputs, yet may mention objects absent from an image. In medication assistance, accessible perception, and environmental decision-making, such hallucinations can create real-world safety risks. We propose Semantic-Spatial Agreement Verific...
Zi-Heng Ren, Qian Gao, Jun Fan et al.· arXiv.org· 0 citations
Multimodal large language models (MLLMs) remain prone to visual hallucinations when correct responses depend on subtle visual details. One line of post-training methods constructs visual contrasts through image retrieval, generation, or editing to improve fine-grained perception. However, these contrasts are not built...
Ben-Lei Cui, Chun-Yang Chai, Yi-Liang Zhang et al.· 0 citations
Object hallucination remains a major obstacle for large vision-language models (LVLMs) to generate reliable content. An intuitive mitigation strategy is to suppress hallucination-related components in hidden representations. However, these components may also contain useful information, and suppressing them can weaken...
Chen Zhao, Xing-Ping Dong, Jia-Chun Shi et al.· 0 citations
Multimodal large language models (MLLMs) process an interleaved image–text sequence with a single autoregressive backbone under causal attention. Since the causal mask prevents image tokens from attending to the question that follows them, their representations are computed without access to the query, which has been i...
Jeong-Woo Seo, Ho-Young Jung· Mathematics· 0 citations
Embodied agents driven by vision-language models (VLMs) can describe a scene fluently and invent objects, attributes, relations or executable targets. Such errors may cause serious injury if the language response is translated into navigation or manipulation operations. This paper introduces EViD-M as a conceptual comp...
Yi-Hui Wang· IEEE Computer Society Intern...· 0 citations
Known for his clear and elegant writing style, Bertsekas shaped fields from control and optimization to large-scale computation and artificial intelligence.