arXiv:2609.22588v1 Announce Type: new Abstract: Vision-language models (VLMs) perform strongly on visual question answering benchmarks, yet often make decisions that contradict visual evidence they h...
The paper shows that chain‑of‑thought (CoT) instructions can distort evaluation of vision‑language models (VLMs) when a scorer reads answer‑label logits before the model generates a rationale. On ScienceQA, Qwen2.5‑VL‑7B’s accuracy falls from 80.76% to 45.48% under this CoT‑prefix scoring, and most predictions incorrectly pick the first option. Linear probes and free generation recover most of the lost accuracy, indicating that the answer information remains in the hidden states but is missed by the early readout. The authors explain the mismatch with vocabulary and layer diagnostics, noting that probability mass shifts toward continuation tokens while answer information stays linearly accessible in later layers. The effect varies across datasets and models, but the study demonstrates that CoT‑prefix scoring can misrepresent model knowledge unless the requested and scored outputs are aligned.
The paper introduces “SpaceConflict”, a benchmark of 23,196 multimodal inputs designed to test whether large language models can not only report spatial facts but also use them in reasoning. Experiments show a gap between a model’s ability to recover an initial spatial state from visual evidence and its ability to apply that state to perform transformations, with the gap narrowing but not closing as model size increases. To address this, the authors propose Operational State Supervision (OSS), which supervises task‑relevant spatial states and their transformation trajectories, improving accuracy on judgments that require state organization and use.
PRISM-BENCH is a new benchmark comprising 1,000 expert‑curated vision‑language questions across five under‑represented reasoning categories, each paired with an idealized reasoning trace validated by a second annotator. It introduces diagnostics beyond final‑answer accuracy: a perception probe that attributes about 85% of frontier‑model failures to misperception, and trace alignment that predicts answer correctness with a macro AUROC of 0.66. The benchmark also presents CORE, an efficiency‑aware metric that reorders 24.2% of model pairs relative to accuracy while remaining uncorrelated with response length, revealing that recent gains are driven by recognition rather than spatial grounding.
The paper shows that chain‑of‑thought (CoT) instructions can distort multiple‑choice vision‑language model evaluation when a scorer appends a reasoning cue but reads answer‑label logits before the model generates any rationale. This CoT‑prefix scoring causes significant drops in accuracy (e.g., Qwen2.5‑VL‑7B falls from 80.76% to 45.48% on ScienceQA) and leads most predictions to choose the first option. Analysis reveals that while answer information remains linearly accessible in late layers, the immediate readout is misled by probability mass shifting toward continuation tokens, and the issue varies across datasets and models.
The paper investigates how visual interventions—training‑free edits applied to multimodal large language models—affect hallucinations and prediction quality. By applying a visual‑residual edit across successive decoder layers and matching its RMS strength, the authors identify an Evidence Anchoring Boundary (EAB) where the intervention’s influence drops sharply; effects before the EAB are 13.78–26.10× larger than after it. They further compare counterfactual subtraction across different question types and introduce calibrated selective routing, which only alters predictions when calibration supports an intervention, improving attribute accuracy by 1.56–1.81 percentage points while avoiding the harms of universal subtraction.
arXiv:2609.39142v1 Announce Type: new Abstract: Can structured text replace vision for diagram reasoning? A wrong answer after textualization can arise because the representation omits information th...
arXiv:2610.19611v1 Announce Type: new Abstract: Modern vision-language models can accept multi-image contexts, but aggregate accuracy rarely reveals where a multi-image reasoning pipeline fails. We s...
arXiv:2607. 07507v1 Announce Type: cross Abstract: Hallucinations in vision language models (VLMs) are commonly treated as semantic errors, yet they often arise from partial or ambiguous visual evidence.
arXiv:2606. 00148v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) often know the rule but pick the wrong answer: on abstract visual reasoning (AVR) tasks, a model can describe what it sees and name the underlying pattern, yet still fail to choose the matching candidate.
arXiv:2608. 10954v1 Announce Type: cross Abstract: While Multimodal Large Language Models (MLLMs) demonstrate impressive performance in benign scenarios, their cognitive reliability deteriorates significantly in complex scenes under adverse conditions.
arXiv:2506.09557v2 Announce Type: replace-cross Abstract: While Multimodal Large Language Models (MLLMs) demonstrate impressive performance in benign scenarios, their cognitive reliability deteriorat...