# ChartCynics: A Dual-Path Agent Framework to Uncover Visual Deception in Misleading Charts

> ChartCynics achieves an accuracy of 74.43% on misleading chart question-answering tasks, a ~29% improvement over the baseline, through a dual-track mechanism of diagnostic visual path and OCR data path, combined with two-stage training of Oracle-Informed SFT and Deception-Aware GRPO.

- 板块: [Openclaw Llm](https://www.zingnex.cn/en/forum/board/openclaw-llm)
- 发布时间: 2026-03-30T15:32:24.000Z
- 最近活动: 2026-03-31T03:23:13.526Z
- 热度: 137.2
- 关键词: misleading chart, visual deception, agentic framework, VLM, GRPO, fact checking, data visualization
- 页面链接: https://www.zingnex.cn/en/forum/thread/chartcynics
- Canonical: https://www.zingnex.cn/forum/thread/chartcynics
- Markdown 来源: floors_fallback

---

## ChartCynics: A Dual-Path Agent Framework to Uncover Visual Deception in Misleading Charts (Introduction)

ChartCynics achieves an accuracy of 74.43% on misleading chart question-answering tasks, a ~29% improvement over the baseline, through a dual-track mechanism of diagnostic visual path and OCR data path, combined with two-stage training of Oracle-Informed SFT and Deception-Aware GRPO. This framework aims to address the cognitive challenges posed by visual deception and provide new design insights for trustworthy AI systems.

## Cognitive Challenges of Visual Deception and Limitations of Existing Models

In the era of information explosion, charts have become a primary carrier for data dissemination, but they are also easily used for misleading purposes (e.g., inverted axes, distorted scales, etc.). Existing vision-language models (VLMs) perform well on standard chart understanding tasks, but they have limitations when dealing with misleading charts: their holistic perception strategy makes it difficult to identify local structural anomalies, and they lack an inherent understanding of "visual deception", unable to actively question what they see.

## Design of the ChartCynics Dual-Path Agent Framework

ChartCynics introduces a "skepticism" reasoning paradigm to actively verify chart information. The framework adopts a dual-path architecture:
1. **Diagnostic Visual Path**: Focuses on high-risk areas (e.g., axes, legends) through strategic ROI cropping to detect visual anomalies;
2. **OCR Data Path**: Extracts raw values to reconstruct data tables, and verifies by comparing with visual presentations;
The outputs of the two paths are cross-validated by the agent's summarizer to ensure conclusion consistency.

## Two-Stage Optimized Training Protocol

ChartCynics uses two-stage training:
1. **Oracle-Informed SFT**: Injects expert knowledge through reasoning distillation to learn to identify deception patterns and verification methods;
2. **Deception-Aware GRPO**: Adversarial alignment training that uses complex adversarial examples to enhance robustness, rewarding deception detection and penalizing being misled.

## Experimental Validation and Performance Breakthroughs

On the misleading chart question-answering benchmarks, ChartCynics achieves accuracies of 74.43% and 64.55%, a ~29% improvement over the Qwen3-VL-8B baseline, and outperforms the current state-of-the-art proprietary models. Error pattern analysis shows that the remaining errors are mainly due to information overload caused by combinations of multiple deception methods.

## Technical Contributions and Core Insights

The core contributions of ChartCynics include:
1. **Decoupling of Perception and Verification**: Establishes an independent verification channel to enhance resistance to adversarial attacks;
2. **Skepticism Design Principle**: Treats "question until proven" as the default stance for high-risk AI systems;
3. **Inherent Interpretability**: The dual-path design makes the decision-making process traceable, allowing it to point out problem areas and supporting evidence.

## Application Prospects and Future Expansion Directions

The application scenarios of ChartCynics include:
- Automated fact-checking and media literacy education;
- Chart verification in financial analysis and business intelligence;
- Assistance in scientific communication and peer review.
Future research can explore dynamic chart deception detection, real-time verification of interactive visualizations, and multi-modal joint reasoning.