# When Does Consensus Mean Correctness? Measuring the Agreement-Accuracy Coupling with Semantics-Preserving Re-Rendering

arXiv: https://arxiv.org/abs/2608.05670 · HTML: https://mlsanity.com/paper/2608.05670/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 36 references that are in the map.
- First posted on arXiv 6 Aug 2026.

## Builds on (most cited first, 29 of 29)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [PlotQA: Reasoning over Scientific Plots](https://mlsanity.com/paper/1909.00997/) (2019)
- [FigureQA: An Annotated Figure Dataset for Visual Reasoning](https://mlsanity.com/paper/1710.07300/) (2017)
- [VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation](https://mlsanity.com/paper/2411.11919/) (2024)
- [On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning?](https://mlsanity.com/paper/2405.02266/) (2024)
- [Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Reward](https://mlsanity.com/paper/2506.07218/) (2025)
- [Selective "Selective Prediction": Reducing Unnecessary Abstention in Vision-Language Reasoning](https://mlsanity.com/paper/2402.15610/) (2024)
- [Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answering](https://mlsanity.com/paper/2404.10193/) (2024)
- [Unraveling the Truth: Do VLMs really Understand Charts? A Deep Dive into Consistency and Robustness](https://mlsanity.com/paper/2407.11229/) (2024)
- [Efficient Test-Time Scaling for Small Vision-Language Models](https://mlsanity.com/paper/2510.03574/) (2025)
- [On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs](https://mlsanity.com/paper/2602.12506/) (2026)
- [ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch](https://mlsanity.com/paper/2601.13606/) (2026)
- [ChartGen: Scaling Chart Understanding Via Code-Guided Synthetic Chart Generation](https://mlsanity.com/paper/2507.19492/) (2025)
- [VL-Calibration: Decoupled Confidence Calibration for Large Vision-Language Models Reasoning](https://mlsanity.com/paper/2604.09529/) (2026)
- [Do Vision-Language Models See or Guess? Measuring and Reducing Textual-Prior Reliance with a Phrasing-Controlled Benchmark](https://mlsanity.com/paper/2606.10400/) (2026)
- [Decompose and Compare Consistency: Measuring VLMs' Answer Reliability via Task-Decomposition Consistency Comparison](https://mlsanity.com/paper/2407.07840/) (2024)
- [Chart-RVR: Reinforcement Learning with Verifiable Rewards for Explainable Chart Reasoning](https://mlsanity.com/paper/2510.10973/) (2025)
- [V-FAT: Benchmarking Visual Fidelity Against Text-bias](https://mlsanity.com/paper/2601.04897/) (2026)
- [VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-Evaluation](https://mlsanity.com/paper/2602.21054/) (2026)
- [Losing the Plot: How VLM responses degrade on imperfect charts](https://mlsanity.com/paper/2509.18425/) (2025)
- [Questioning the Stability of Visual Question Answering](https://mlsanity.com/paper/2511.11206/) (2025)
- [CDH-Bench: A Commonsense-Driven Hallucination Benchmark for Evaluating Visual Fidelity in Vision-Language Models](https://mlsanity.com/paper/2603.27982/) (2026)
- [Zoom Consistency: A Free Confidence Signal in Multi-Step Visual Grounding Pipelines](https://mlsanity.com/paper/2604.15376/) (2026)
- [Chart-RL: Generalized Chart Comprehension via Reinforcement Learning with Verifiable Rewards](https://mlsanity.com/paper/2603.06958/) (2026)

## Abstract (arXiv)

A model's agreement across perturbed inputs is used both as a label-free reliability signal and as a self-training target, on the premise that agreement tracks correctness. That coupling is rarely measured directly: natural-image perturbations preserve meaning only by assumption, and no exact answer key localizes errors. Scientific figures remove both obstacles, a figure is drawn from data by a program, so redrawing it yields images that are semantically equivalent by construction and share a programmatically exact answer. We build RENDEQ, a generator of such render-equivalence sets, and measure the coupling on three open-weight VLMs, checking every finding across three independent instantiations. Re-rendering beats resampling on both accuracy and reliability. Agreement beats an evidence-carrying baseline, mean token log-probability, on two of three models and ties on the third, reversing an intermediate, buggy replication traced to a rendering-pipeline failure. The dispersion behind this is concentrated in one style factor, the plotting library, more than double the next-largest factor and an order of magnitude above the noise floor. Fine-tuning on the model's own cross-render consensus inverts: accuracy falls in every one of five replication runs, the opposite sign to published results on natural images. Agreement certifies correctness only above a threshold set by how diffuse a model's errors are, and an objective that rewards agreement destroys exactly that diffuseness.