Related papers: $C^2$: Scalable Auto-Feedback for LLM-based Chart …

Retrieval-augmented generation (RAG) is critical for reducing hallucinations and incorporating external knowledge into Large Language Models (LLMs). However, advanced RAG systems face a trade-off between performance and efficiency.…

Large Language Models (LLMs) leverage external tools primarily through generating the API request to enhance task completion efficiency. The accuracy of API request generation significantly determines the capability of LLMs to accomplish…

Large language models (LLMs) have demonstrated strong capabilities across various language tasks, notably through instruction-tuning methods. However, LLMs face challenges in visualizing complex, real-world data through charts and plots.…

Large language models (LLMs) struggle to consistently generate UI code that compiles and produces visually relevant designs. Existing approaches to improve generation rely on expensive human feedback or distilling a proprietary model. In…

Learning from human feedback has become a pivot technique in aligning large language models (LLMs) with human preferences. However, acquiring vast and premium human feedback is bottlenecked by time, labor, and human capability, resulting in…

High-quality instruction-tuning data is crucial for developing Large Language Models (LLMs) that can effectively navigate real-world tasks and follow human instructions. While synthetic data generation offers a scalable approach for…

We propose a novel framework that leverages Visual Question Answering (VQA) models to automate the evaluation of LLM-generated data visualizations. Traditional evaluation methods often rely on human judgment, which is costly and unscalable,…

In this time when biased information, deep fakes, and propaganda proliferate, the accessibility of reliable data sources is more important than ever. National statistical institutes provide curated data that contain quantitative information…

Retrieval-augmented generation (RAG) systems are increasingly deployed in user-facing applications, yet systematic, human-centered evaluation of their outputs remains underexplored. Building on Gienapp's utility-dimension framework, we…

Automated chart design has seen significant advancements with the emergence of Large-Language Models (LLMs), which offer a practical solution for generating charts. However, LLMs frequently introduce possibly critical design failures, such…

Large Language Models (LLMs) are increasingly used to automate software development, yet most prior evaluations focus on functional correctness or high-level languages such as Python. As one of the first systematic explorations of…

Chart-to-code generation demands strict visual precision and syntactic correctness from Vision-Language Models (VLMs). However, existing approaches are fundamentally constrained by data-centric limitations: despite the availability of…

The emergence of Multi-modal Large Language Models (MLLMs) presents new opportunities for chart understanding. However, due to the fine-grained nature of these tasks, applying MLLMs typically requires large, high-quality datasets for…

The integration of experimental technologies with large language models (LLMs) is transforming scientific research. It positions AI as a versatile research assistant rather than a mere problem-solving tool. In the field of power systems,…

Vision Language Models (VLMs) often struggle with chart understanding tasks, particularly in accurate chart description and complex reasoning. Synthetic data generation is a promising solution, while usually facing the challenge of noise…

Charts are ubiquitous, as people often use them to analyze data, answer questions, and discover critical insights. However, performing complex analytical tasks with charts requires significant perceptual and cognitive effort. Chart Question…

Data visualizations are central to scientific communication, journalism, and everyday decision-making, yet they are frequently prone to errors that can distort interpretation or mislead audiences. Rule-based visualization linters can flag…

Continuous emotional image generation (C-EICG) is emerging rapidly due to its ability to produce images aligned with both user descriptions and continuous emotional values. However, existing approaches lack emotional feedback from generated…

In aligning large language models (LLMs), utilizing feedback from existing advanced AI rather than humans is an important method to scale supervisory signals. However, it is highly challenging for AI to understand human intentions and…

Generating diverse, readable statistical charts from tabular data remains challenging for LLMs, as many failures become apparent after rendering and are not detectable from data or code alone. Existing chart datasets also rarely provide…