# Chimera: Diagnosing Shortcut Learning in Visual-Language Understanding

arXiv: https://arxiv.org/abs/2509.22437 · HTML: https://mlsanity.com/paper/2509.22437/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 49 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Builds on (most cited first, 28 of 28)

- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [A Diagram Is Worth A Dozen Images](https://mlsanity.com/paper/1603.07396/) (2016)
- [Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding](https://mlsanity.com/paper/2311.16922/) (2023)
- [Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs](https://mlsanity.com/paper/2503.01743/) (2025)
- [DVQA: Understanding Data Visualizations via Question Answering](https://mlsanity.com/paper/1801.08163/) (2018)
- [Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering](https://mlsanity.com/paper/1712.00377/) (2017)
- [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)
- [IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning](https://mlsanity.com/paper/2110.13214/) (2021)
- [SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models](https://mlsanity.com/paper/2307.10635/) (2023)
- [CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs](https://mlsanity.com/paper/2406.18521/) (2024)
- [RUBi: Reducing Unimodal Biases in Visual Question Answering](https://mlsanity.com/paper/1906.10169/) (2019)
- [VisualMRC: Machine Reading Comprehension on Document Images](https://mlsanity.com/paper/2101.11272/) (2021)
- [MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning](https://mlsanity.com/paper/2311.10774/) (2023)
- [ChartBench: A Benchmark for Complex Visual Reasoning in Charts](https://mlsanity.com/paper/2312.15915/) (2023)
- [Yin and Yang: Balancing and Answering Binary Visual Questions](https://mlsanity.com/paper/1511.05099/) (2015)
- [VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?](https://mlsanity.com/paper/2404.05955/) (2024)
- [ShapeWorld - A new test methodology for multimodal language understanding](https://mlsanity.com/paper/1704.04517/) (2017)
- [Do Vision-Language Models Really Understand Visual Language?](https://mlsanity.com/paper/2410.00193/) (2024)
- [Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond](https://mlsanity.com/paper/2402.10805/) (2024)
- [Pre-trained Vision-Language Models Learn Discoverable Visual Concepts](https://mlsanity.com/paper/2404.12652/) (2024)
- [Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning](https://mlsanity.com/paper/2402.17510/) (2024)
- [Semantic Parsing to Probabilistic Programs for Situated Question Answering](https://mlsanity.com/paper/1606.07046/) (2016)

## Built on by (most cited first, 7 of 7)

- [MASS: Motion-Aware Spatial-Temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Models](https://mlsanity.com/paper/2511.18373/) (2025)
- [HoloGeo: Mitigating Landmark Bias in Geo-localization via Evidence-Driven Reasoning](https://mlsanity.com/paper/2607.15255/) (2026)
- [Eye-Q: A Multilingual Benchmark for Visual Word Puzzle Solving and Image-to-Phrase Reasoning](https://mlsanity.com/paper/2601.03400/) (2026)
- [Chartographer: Counterfactual Chart Generation for Evaluating Vision-Language Models](https://mlsanity.com/paper/2605.27311/) (2026)
- [SHOVIR: A Benchmark for Evaluating Vision Shortcut Learning in Radiology Report Generation](https://mlsanity.com/paper/2606.30201/) (2026)
- [LightAIR: Lightweight Action Inversion and Riemannian Rectification for Text-based Person Anomaly Search](https://mlsanity.com/paper/2608.09152/) (2026)
- [PragMatch: Separating Pragmatic Incongruity from Cross-Modal Mismatch in Large Vision-Language Models](https://mlsanity.com/paper/2608.09772/) (2026)

## Abstract (arXiv)

Diagrams convey symbolic information in a visual format rather than a linear stream of words, making them especially challenging for AI models to process. While recent evaluations suggest that vision-language models (VLMs) perform well on diagram-related benchmarks, their reliance on knowledge, reasoning, or modality shortcuts raises concerns about whether they genuinely understand and reason over diagrams. To address this gap, we introduce Chimera, a comprehensive test suite comprising 7,500 high-quality diagrams sourced from Wikipedia; each diagram is annotated with its symbolic content represented by semantic triples along with multi-level questions designed to assess four fundamental aspects of diagram comprehension: entity recognition, relation understanding, knowledge grounding, and visual reasoning. We use Chimera to measure the presence of three types of shortcuts in visual question answering: (1) the visual-memorization shortcut, where VLMs rely on memorized visual patterns; (2) the knowledge-recall shortcut, where models leverage memorized factual knowledge instead of interpreting the diagram; and (3) the Clever-Hans shortcut, where models exploit superficial language patterns or priors without true comprehension. We evaluate 15 open-source VLMs from 7 model families on Chimera and find that their seemingly strong performance largely stems from shortcut behaviors: visual-memorization shortcuts have slight impact, knowledge-recall shortcuts play a moderate role, and Clever-Hans shortcuts contribute significantly. These findings expose critical limitations in current VLMs and underscore the need for more robust evaluation protocols that benchmark genuine comprehension of complex visual inputs (e.g., diagrams) rather than question-answering shortcuts.