Self-correction is an approach to improving responses from large language models (LLMs)
by refining the responses using LLMs during inference. Prior work has proposed various self …

Data visualization in the form of charts plays a pivotal role in data analysis, offering critical
insights and aiding in informed decision-making. Automatic chart understanding has …

Solely relying on test passing to evaluate Large Language Models (LLMs) for code
synthesis may result in unfair assessment or promoting models with data leakage. As an …

Large Language Models (LLMs) like GPT-4 which support multimodal input (ie, prompts
containing images in addition to text) have immense potential to advance visualization …

Recently, many versatile Multi-modal Large Language Models (MLLMs) have emerged
continuously. However, their capacity to query information depicted in visual charts and …

The ability to understand and answer questions over documents can be useful in many
business and practical applications. However, documents often contain lengthy and diverse …

Fact-checking research has extensively explored verification but less so the generation of
natural-language explanations, crucial for user trust. While Large Language Models (LLMs) …

Trained on vast corpora, Large Language Models (LLMs) have the potential to encode
visualization design knowledge and best practices. However, if they fail to do so, they might …

While Vision-Language Models (VLMs) have shown remarkable abilities in visual and
language reasoning tasks, they invariably generate flawed responses. Self-correction that …

Large Vision-Language Models (LVLMs) suffer from hallucination issues, wherein the
models generate plausible-sounding but factually incorrect outputs, undermining their …