How Do VLMs Behave When Blind or Misled? Behavioral Evaluation of VLMs on Scientific Figures

• URL: http://arxiv.org/abs/2608.13267v1
• Date: Thu, 13 Aug 2026 14:06:35 GMT
• Title: How Do VLMs Behave When Blind or Misled? Behavioral Evaluation of VLMs on Scientific Figures
• Abstract summary: We introduce SciFigBench, a diagnostic VLM benchmark for scientific figure understanding.<n>It jointly evaluates perception, reasoning, and behavioral reliability under uncertainty.<n>Our results reveal substantial behavioral differences among models.
• Score: 17.423679874903062
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing vision-language model (VLM) benchmarks emphasize perception and reasoning accuracy (how well VLMs describe and reason about what they see in an image), with limited attention to behavioral reliability under uncertainty (how they behave when visual evidence is missing or misleading). We introduce SciFigBench, a diagnostic VLM benchmark for scientific figure understanding that jointly evaluates perception, reasoning, and behavioral reliability under uncertainty. It contains 250 figures with high-quality human annotations across three evaluation aspects, totaling 600+ hours of annotation effort. We further extend these figures via image transformations, reasoning questions, resistance probes, caption-bias probes, and confirmed selective-blur targets, producing over 34,000 evaluation setups for stress testing. We further propose the Admittance-Resistance-Inductance (A-R-I) framework to evaluate whether models acknowledge insufficient evidence, resist misleading context, and infer cautiously from partial information. Our results reveal substantial behavioral differences among models. GPT-5.2 achieves the highest description quality (MQM 91.6) with strong reasoning accuracy (78.4%), yet hallucinates unreadable content in 96% of cases, whereas Gemini 3.1 Pro, a comparably capable model (MQM 90.2, reasoning 81.0%), admits uncertainty in 71% of such cases and achieves the strongest resistance score (0.91). These findings show that high perception and reasoning accuracy alone do not guarantee behavioral reliability, a dimension critical for deployment in scientific workflows.

Related papers

• NovGauge: A Fine-Grained Benchmark for Diagnosing LLMs' Capability in Paper Novelty Assessment [54.4265627247104]
  Large language models (LLMs) are increasingly used in peer review at major AI conferences.<n>Existing benchmarks assess novelty as a single holistic score.<n>We present NovGauge, a human-anchored benchmark for fine-grained novelty assessment diagnosis.
  arXiv  Detail & Related papers  (2026-09-10T08:34:56Z)
• Evaluating the Diagnostic Robustness of Vision-Language Models Under Visual and Textual Perturbations [3.765860543344957]
  We assess the diagnostic robustness of four VLM families under evidence-preserving perturbations.<n>Our results reveal significant vulnerabilities in presentation-order stability, with models exhibiting prediction flips in up to 48.9% of cases.
  arXiv  Detail & Related papers  (2026-08-05T14:09:55Z)
• Evaluation Awareness Is Not One Capability: Evidence from Open Language Models [1.758143872501506]
  Safety benchmarks assume that test-condition behavior predicts deployment behavior, an assumption that fails if models detect evaluation cues and adapt.<n>This opens a gap between benchmark performance and deployment behavior.<n>We characterize this evaluation awareness through eight experiments across 37 open-weight models and seven families.
  arXiv  Detail & Related papers  (2026-06-22T16:48:43Z)
• Verbal Confidence Saturation in 3-9B Open-Weight Instruction-Tuned LLMs: A Pre-Registered Psychometric Validity Screen [0.0]
  We tested whether seven instruction-tuned open-weight models produce verbalised confidence that meets minimal validity criteria.<n>We found Categorical elicitation did not rescue validity.<n> Token-level logprobability did not usefully predict verbalised confidence under the observed variance regime.
  arXiv  Detail & Related papers  (2026-04-24T04:45:21Z)
• Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models? [0.0]
  Chain-of-thought (CoT) reasoning has been proposed as a transparency mechanism for large language models in safety-critical deployments.<n>This study tests 12 open-weight reasoning models spanning 9 architectural families on 498 multiple-choice questions.<n>Across 41,832 inference runs, overall faithfulness rates range from 39.7% (Seed-1.6-Flash) to 89.9% (DeepSeek-V3.2-Speciale) across model families.
  arXiv  Detail & Related papers  (2026-03-23T21:21:37Z)
• Same Answer, Different Representations: Hidden instability in VLMs [65.36933543377346]
  We introduce a representation-aware and frequency-aware evaluation framework that measures internal embedding drift, spectral sensitivity, and structural smoothness.<n>We apply this framework to modern Vision Language Models (VLMs) across the SEEDBench, MMMU, and POPE datasets.
  arXiv  Detail & Related papers  (2026-02-06T12:24:26Z)
• AdversaRiskQA: An Adversarial Factuality Benchmark for High-Risk Domains [3.721111684544962]
  Hallucination in large language models (LLMs) contributes to spread of misinformation and diminished public trust.<n>We introduce AdversaRiskQA, the first verified and reliable benchmark systematically evaluating adversarial factuality.<n>We evaluate six open- and closed-source LLMs from the Qwen, GPT-OSS, and GPT families, measuring misinformation detection rates.
  arXiv  Detail & Related papers  (2026-01-21T22:47:59Z)
• EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models [82.43729208063468]
  Recent benchmarks for medical Large Vision-Language Models (LVLMs) emphasize leaderboard accuracy, overlooking reliability and safety.<n>We study sycophancy -- models' tendency to uncritically echo user-provided information.<n>We introduce EchoBench, a benchmark to systematically evaluate sycophancy in medical LVLMs.
  arXiv  Detail & Related papers  (2025-09-24T14:09:55Z)
• MedOmni-45°: A Safety-Performance Benchmark for Reasoning-Oriented LLMs in Medicine [69.08855631283829]
  We introduce Med Omni-45 Degrees, a benchmark designed to quantify safety-performance trade-offs under manipulative hint conditions.<n>It contains 1,804 reasoning-focused medical questions across six specialties and three task types, including 500 from MedMCQA.<n>Results show a consistent safety-performance trade-off, with no model surpassing the diagonal.
  arXiv  Detail & Related papers  (2025-08-22T08:38:16Z)
• Reasoning Models Are More Easily Gaslighted Than You Think [85.84943447589511]
  We evaluate three state-of-the-art reasoning models, including OpenAI's o4-mini, Claude-3.7-Sonnet and Gemini-2.5-Flash.<n>Our evaluation reveals significant accuracy drops following gaslighting negation prompts.<n>We introduce GaslightingBench-R, a new diagnostic benchmark designed to evaluate reasoning models' susceptibility to defend their belief.
  arXiv  Detail & Related papers  (2025-06-11T12:52:25Z)
• Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations [63.330182403615886]
  A major barrier towards the practical deployment of large language models (LLMs) is their lack of reliability. Three situations where this is particularly apparent are correctness, hallucinations when given unanswerable questions, and safety. In all three cases, models should ideally abstain from responding, much like humans, whose ability to understand uncertainty makes us refrain from answering questions we don't know.
  arXiv  Detail & Related papers  (2024-04-16T23:56:38Z)
• Navigating the Grey Area: How Expressions of Uncertainty and Overconfidence Affect Language Models [74.07684768317705]
  LMs are highly sensitive to markers of certainty in prompts, with accuies varying more than 80%. We find that expressions of high certainty result in a decrease in accuracy as compared to low expressions; similarly, factive verbs hurt performance, while evidentials benefit performance. These associations may suggest that LMs is based on observed language use, rather than truly reflecting uncertainty.
  arXiv  Detail & Related papers  (2023-02-26T23:46:29Z)

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.