Identifying and Resolving Pitfalls of Knowledge-Based VQA Benchmarks: Auditing, Repairing, and Augmenting

• URL: http://arxiv.org/abs/2607.00159v1
• Date: Tue, 30 Jun 2026 20:35:30 GMT
• Title: Identifying and Resolving Pitfalls of Knowledge-Based VQA Benchmarks: Auditing, Repairing, and Augmenting
• Abstract summary: Knowledge-Based Visual Question Answering (KB-VQA) aims to evaluate whether Visual Language Models (VLMs) can retrieve, ground, and reason over external structured knowledge.<n>We show that these assumptions are systematically violated in existing KB-VQA benchmarks.<n>We introduce (1) a principled audit-and-repair protocol that restores answer derivability and question clarity, and (2) a controlled multi-entity augmentation protocol that introduces visual ambiguity to challenge initial retrieval and grounded reasoning.
• Score: 11.990076788699456
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Knowledge-Based Visual Question Answering (KB-VQA) aims to evaluate whether Visual Language Models (VLMs) can retrieve, ground, and reason over external structured knowledge beyond visual evidence. In practice, answer accuracy is widely adopted as the primary evaluation metric, implicitly treating correctness as a proxy for knowledge-grounded reasoning. However, for existing KB-VQA benchmarks, this proxy relies on critical assumptions that are often overlooked and rendered unreliable by benchmark issues: annotated answer must be derivable from the associated knowledge base, question must be well-posed with sufficient constraints, and visual setting must meaningfully require grounded disambiguation. In this work, we show that these assumptions are systematically violated in existing KB-VQA benchmarks. Our audit reveals substantial instances with missing or contradicted answers and underspecified questions that render accuracy a misleading metric. Furthermore, we find that existing datasets rely on visually trivial, single-entity scenes that bypass the need for sophisticated visual-to-knowledge mapping. We demonstrate that even with controlled architectures, these flaws lead to distorted model rankings and overestimations of reasoning capabilities. To address this, we introduce (1) a principled audit-and-repair protocol that restores answer derivability and question clarity, and (2) a controlled multi-entity augmentation protocol that introduces visual ambiguity to challenge initial retrieval and grounded reasoning. Re-evaluation under corrected and augmented settings yields markedly different performance trends. Our findings call for rethinking evaluation protocols and designing more interaction-aware KB-VQA benchmarks that prioritize verifiable reasoning over simple matching.

Related papers

• Knowledge Dependency Estimation for Reliable Question Answering [11.800158247203312]
  We study emphknowledge dependency estimation<n>We propose textbfKnot, a structured rank-aware knowledge dependency estimator.
  arXiv  Detail & Related papers  (2026-05-27T06:48:57Z)
• VISTAQA: Benchmarking Joint Visual Question Answering and Pixel-Level Evidence [26.0945130521806]
  Existing benchmarks assess either textual answer correctness or pixel-level localization in isolation.<n>We introduce VISTAQA, a benchmark for joint evaluation of free-form answer correctness and pixel-level evidence grounding in visual question answering.<n>We introduce GROVE, a metric that enforces joint correctness by combining textual accuracy and grounding quality via a per-sample geometric mean.
  arXiv  Detail & Related papers  (2026-05-20T03:44:06Z)
• ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning [59.558706734431276]
  Current evaluations of spatial intelligence can be systematically invalid under modern vision-language model (VLM) settings.<n>We introduce ReVSI, a benchmark and protocol that ensures each QA pair is answerable and correct under the model's actual inputs.
  arXiv  Detail & Related papers  (2026-04-27T10:45:51Z)
• Diagnosing Causal Reasoning in Vision-Language Models via Structured Relevance Graphs [18.83755844366017]
  We introduce Vision-Language Causal Graphs (VLCGs), a structured, query-conditioned representation that explicitly encodes causally relevant objects, attributes, relations, and scene-grounded assumptions.<n>We present ViLCaR, a diagnostic benchmark comprising tasks for Causal Attribution, Causal Inference, and Question Answering, along with graph-aligned evaluation metrics.<n> Experiments in state-of-the-art LVLMs show that injecting structured relevance information significantly improves attribution and inference compared to zero-shot and standard in-context learning.
  arXiv  Detail & Related papers  (2026-02-24T13:20:07Z)
• Benchmarking Uncertainty Calibration in Large Language Model Long-Form Question Answering [7.1559850008795385]
  Large Language Models (LLMs) are commonly used in Question Answering (QA) settings.<n>Existing UQ approaches remain weakly validated in scientific QA.<n>We introduce the first large-scale benchmark for evaluating UQ metrics in reasoning-demanding QA.
  arXiv  Detail & Related papers  (2026-01-30T20:02:34Z)
• ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering [54.72902502486611]
  ReAG is a Reasoning-Augmented Multimodal RAG approach that combines coarse- and fine-grained retrieval with a critic model that filters irrelevant passages.<n>ReAG significantly outperforms prior methods, improving answer accuracy and providing interpretable reasoning grounded in retrieved evidence.
  arXiv  Detail & Related papers  (2025-11-27T19:01:02Z)
• Diagnosing and Addressing Pitfalls in KG-RAG Datasets: Toward More Reliable Benchmarking [63.84117489519164]
  Knowledge Graph Question Answering systems rely on high-quality benchmarks to evaluate complex multi-hop reasoning.<n>Despite their widespread use, popular datasets such as WebQSP and CWQ suffer from critical quality issues.<n>We introduce KGQAGen, an LLM-in-the-loop framework that systematically resolves these pitfalls.<n>Our findings advocate for more rigorous benchmark construction and position KGQAGen as a scalable framework for advancing KGQA evaluation.
  arXiv  Detail & Related papers  (2025-05-29T14:44:52Z)
• Detecting Multimodal Situations with Insufficient Context and Abstaining from Baseless Predictions [75.45274978665684]
  Vision-Language Understanding (VLU) benchmarks contain samples where answers rely on assumptions unsupported by the provided context.<n>We collect contextual data for each sample whenever available and train a context selection module to facilitate evidence-based model predictions.<n>We develop a general-purpose Context-AwaRe Abstention detector to identify samples lacking sufficient context and enhance model accuracy.
  arXiv  Detail & Related papers  (2024-05-18T02:21:32Z)
• Open-Set Knowledge-Based Visual Question Answering with Inference Paths [79.55742631375063]
  The purpose of Knowledge-Based Visual Question Answering (KB-VQA) is to provide a correct answer to the question with the aid of external knowledge bases. We propose a new retriever-ranker paradigm of KB-VQA, Graph pATH rankER (GATHER for brevity) Specifically, it contains graph constructing, pruning, and path-level ranking, which not only retrieves accurate answers but also provides inference paths that explain the reasoning process.
  arXiv  Detail & Related papers  (2023-10-12T09:12:50Z)
• Towards Clear Expectations for Uncertainty Estimation [64.20262246029286]
  Uncertainty Quantification (UQ) is crucial to achieve trustworthy Machine Learning (ML) Most UQ methods suffer from disparate and inconsistent evaluation protocols. This opinion paper offers a new perspective by specifying those requirements through five downstream tasks.
  arXiv  Detail & Related papers  (2022-07-27T07:50:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.