Research map / Vision-language and multimodal / Visual question answering
DomainCQA: Crafting Knowledge-Intensive QA from Domain-Specific Charts
Yujing Lu, Ling Zhong, Jing Yang, Weiming Li, Peng Wei, Yongheng Wang, Manni Duan, Qing Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| fine-tune on DomainCQA-generated QA data | MiniCPM-V2.6-8B · AstroChart (all) | accuracy (%): 56.44 -> 61.46 | Improved |
| fine-tune on DomainCQA-generated QA data | MiniCPM-V2.6-8B · AstroChart Data Calculation | accuracy (%): 18.21 -> 24.64 | Improved |
| fine-tune on DomainCQA-generated QA data | MiniCPM-V2.6-8B · CharXiv overall | accuracy: 49.08 -> 49.52 | No clear effect |
| fine-tune on DomainCQA-generated QA data | MiniCPM-V2.6-8B · ChartQA overall | accuracy: 70.48 -> 69.52 | Hurt |
| fine-tune on DomainCQA-generated QA data | MiniCPM-V2.6-8B · MMC-Benchmark overall | accuracy: 74.40 -> 73.28 | Hurt |
| fine-tune on DomainCQA-generated QA data | MiniCPM-V2.6-8B · ChartQA Augmented | accuracy: 83.84 -> 80.80 | Hurt |
| select chart abstracts via CoT and voting instead of random FQA charts for AQA (ablation) | DomainCQA AQA generation · Expert relevance, Astronomy | domain relevance (1-5): 3.27 -> 3.84 | Improved |
| select chart abstracts via CoT and voting instead of random FQA charts for AQA (ablation) | DomainCQA AQA generation · Expert relevance, Biochemistry | domain relevance (1-5): 3.48 -> 3.80 | Improved |
| select chart abstracts via CoT and voting instead of random FQA charts for AQA (ablation) | DomainCQA AQA generation · Expert relevance, Economics | domain relevance (1-5): 3.48 -> 3.78 | Improved |
| select chart abstracts via CoT and voting instead of random FQA charts for AQA (ablation) | DomainCQA AQA generation · Expert relevance, Medicine | domain relevance (1-5): 3.21 -> 3.77 | Improved |
| select chart abstracts via CoT and voting instead of random FQA charts for AQA (ablation) | DomainCQA AQA generation · Expert relevance, Social Science | domain relevance (1-5): 3.23 -> 3.46 | Improved |
| select chart abstracts instead of random FQA charts (ablation) | DomainCQA AQA generation · Expert validity, Social Science | QA validity: 0.95 -> 0.93 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CogVLM2-19B — CogVLM: Visual Expert for Pretrained Language Models (NeurIPS 2024) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models (NeurIPS 2025 · similarity 0.89)
- Synthesize Step-by-Step: Tools Templates and LLMs as Data Generators for Reasoning-Based Chart VQA (CVPR 2024 · similarity 0.88)
- Union Is Strength! Unite the Power of LLMs and MLLMs for Chart Question Answering (AAAI 2025 · similarity 0.87)
- ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding (CVPR 2026 · similarity 0.87)
- EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding (AAAI 2025 · similarity 0.87)
- InfoChartQA: A Benchmark for Multimodal Question Answering on Infographic Charts (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
