| title | Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering |
|---|---|
| authors | Yanjie Zhang, Yafei Li, Rui Sheng, Zixin Chen, Yanna Lin, Huamin Qu, Lei Chen, Yushi Sun |
| date | 2026-07-14 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2603.28583 |
| affiliation | HKUST |
| upvotes | 8 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Despite the success of Vision-Language Models (VLMs), misleading charts remain a significant challenge due to their deceptive visual structures and distorted data representations. We present ChartCynics, an agentic dual-path framework designed to unmask visual deception via a "skeptical" reasoning paradigm. Unlike holistic models, ChartCynics decouples perception from verification: a Diagnostic Vision Path captures structural anomalies (e.g., inverted axes) through strategic ROI cropping, while an OCR-Driven Data Path ensures numerical grounding. To resolve cross-modal conflicts, we introduce an Agentic Summarizer optimized via a two-stage protocol: Oracle-Informed SFT for reasoning distillation and Deception-Aware GRPO for adversarial alignment. This pipeline effectively penalizes visual traps and enforces logical consistency. Evaluations on two benchmarks show that ChartCynics achieves 74.43% and 64.55% accuracy, providing an absolute performance boost of ~29% over the Qwen3-VL-8B backbone, outperforming state-of-the-art proprietary models. Our results demonstrate that specialized agentic workflows can grant smaller open-source models superior robustness, establishing a new foundation for trustworthy chart interpretation. |
cite
@misc{zhang2026navigating,
title={Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering},
author={Yanjie Zhang and Yafei Li and Rui Sheng and Zixin Chen and Yanna Lin and Huamin Qu and Lei Chen and Yushi Sun},
year={2026},
eprint={2603.28583},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2603.28583}
}