ACL Findings2026
K-GIP: Diagnosing Logical Fractures in Large Vision-Language Models via Verification Scene Graphs and Sequential Pruning
Yujun Hu, Xiaoyu Zhou, Changbo Wang, Gaoqi He
Abstract
Diagnosing fine-grained hallucinations inLarge Vision-Language Models (LVLMs) can greatly advance their reliable deployment in real-world applications.Nevertheless, current benchmarks predominantly employ flat metrics that treat errors in isolation, leaving a gap in evaluating the complex causal dependencies between visual perception and textual reasoning.Motivated by this, we introduce the Knowledge-Guided In-Context Probing (K-GIP) framework to fill this gap.Specifically, K-GIP constructs a high-fidelity dualperception ground truth to transform abstract priors into multi-granularity queries.Furthermore, we propose a Verification Scene Graph metric equipped with a Sequential Logic Pruning protocol, which explicitly models existenceattribute dependencies to strictly penalize logical fractures.We conduct comprehensive evaluations of mainstream LVLMs across three datasets using K-GIP.The experimental results highlight that our methodology successfully isolates deep reasoning failures from simple perceptual misses.We hope K-GIP can serve as a valuable and rigorous standard to assess logical robustness in multimodal systems.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
- Evaluating Object Hallucination in Large Vision-Language Models cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
- Analyzing and Mitigating Object Hallucination in Large Vision-Language Models cites InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning
- Analyzing and Mitigating Object Hallucination in Large Vision-Language Models cites Evaluating Object Hallucination in Large Vision-Language Models
- Analyzing and Mitigating Object Hallucination in Large Vision-Language Models cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
Builds on11
- InstructBLIP: Towards General-purpose Vision-Language Models with Instruction TuningWenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong et al.NeurIPS 2023 · 4,013 citations
- MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language ModelsDeyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li et al.ICLR 2024 · 3,079 citations
- Evaluating Object Hallucination in Large Vision-Language ModelsYifan Li, Yifan Du, Kun Zhou, Jinpeng Wang et al.EMNLP 2023 · 344 citations
- Analyzing and Mitigating Object Hallucination in Large Vision-Language ModelsYiyang Zhou, Chenhang Cui, Jaehong Yoon, Linjun Zhang et al.ICLR 2024 · 316 citations
- SGTR: End-to-end Scene Graph Generation with TransformerRongjie Li, Songyang Zhang, Xuming HeCVPR 2022 · 108 citations
Related papers
- Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMsSreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar, Utkarsh Tyagi et al.ICLR 2025
- CF-VLM: CounterFactual Vision-Language Fine-tuningJusheng Zhang, Kaitong Cai, Yijia Fan, Jian Wang et al.NeurIPS 2025 · 71 citations
- Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language ModelsJunfei Wu, Qiang Liu, Ding Wang, Jinghao Zhang et al.ACL Findings 2024 · 24 citations
- HSGG: Training-Free Hierarchical Scene Graph Generation with Geometry-Guided Relation Reasoningyunzhe Liu, Wenbiao Liu, Lihui Cen, Zhe Qu et al.ICML 2026
- OKGraph: Online Knowledge Graph Probing for Open-vocabulary RecognitionJunhui Yin, Zhizhen Cai, Puze Wang, Guanzhou Ke, Jianhua Yang, Man Zhang, Qiang Zhang, Shengfeng HeCVPR Findings 2026
