Update README.md

README.md

@@ -10,10 +10,10 @@ This repository contains the code to evaluate models on CharXiv from the paper [
 https://github.com/princeton-nlp/CharXiv/assets/59942464/ab9b293b-8fd6-4735-b8b3-0079ee978b61
 
 ## 📰 News
-🆕 [07/26/2024] Upcoming this week: we'll be releasing scores for [GPT-4o-mini](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) as well as the largest and most capable open-weight VLM in our benchmark: [InternVL2 LLaMA-3 76B](https://huggingface.co/OpenGVLab/InternVL2-Llama3-76B). Alongside scores, we find some interesting patterns in the trend of model improvement with respect to differnet chart understanding benchmarks on X. Stay tuned!  
-🆕 [07/24/2024] We released the [full evaluation pipeline](https://github.com/princeton-nlp/CharXiv) (i.e., v1.0).  
-🆕 [07/23/2024] We released our [evaluation results](https://huggingface.co/datasets/princeton-nlp/CharXiv/tree/main/existing_evaluations) on **all 34 MLLMs** that we have tested so far -- this includes all models' responses to CharXiv's challenging questions, scores graded by GPT-4o, as well as aggregated stats.   
-🆕 [07/14/2024] We further evaluated the latest [InternVL Chat V2.0 26B](https://huggingface.co/OpenGVLab/InternVL2-26B) and [Cambrian 34B models](https://huggingface.co/nyu-visionx/cambrian-34b) on CharXiv with some State-of-the-Art results. More analysis are [here](https://x.com/zwcolin/status/1812650435808792731).
+**[07/26/2024]** 🚀 Upcoming this week: we'll be releasing scores for [GPT-4o-mini](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) as well as the largest and most capable open-weight VLM in our benchmark: [InternVL2 LLaMA-3 76B](https://huggingface.co/OpenGVLab/InternVL2-Llama3-76B). Alongside scores, we find some interesting patterns in the **trend of model improvement with respect to differnet chart understanding benchmarks** on X. Stay tuned!  
+**[07/24/2024]** 🚀 We released the [full evaluation pipeline](https://github.com/princeton-nlp/CharXiv) (i.e., v1.0).  
+**[07/23/2024]** 🚀 We released our [evaluation results](https://huggingface.co/datasets/princeton-nlp/CharXiv/tree/main/existing_evaluations) on **all 34 MLLMs** that we have tested so far -- this includes all models' responses to CharXiv's challenging questions, scores graded by GPT-4o, as well as aggregated stats.   
+**[07/14/2024]** 🚀 We further evaluated the latest [InternVL Chat V2.0 26B](https://huggingface.co/OpenGVLab/InternVL2-26B) and [Cambrian 34B models](https://huggingface.co/nyu-visionx/cambrian-34b) on CharXiv with some **State-of-the-Art results**. More analysis are [here](https://x.com/zwcolin/status/1812650435808792731).
 
 ## 👋 Introduction
 Chart understanding plays a pivotal role when applying Multimodal Large Language Models (MLLMs) to real-world tasks such as analyzing scientific papers or financial reports. However, existing datasets often focus on oversimplified and homogeneous charts with template-based questions, leading to an over-optimistic measure of progress. In this work, we propose CharXiv, a comprehensive evaluation suite involving 2,323 natural, challenging, and diverse charts from scientific papers. CharXiv includes two types of questions: (1) descriptive questions about examining basic chart elements and (2) reasoning questions that require synthesizing information across complex visual elements in the chart. To ensure quality, all charts and questions are handpicked, curated, and verified by human experts. Our results reveal a substantial, previously underestimated gap between the reasoning skills of the strongest proprietary model (i.e., GPT-4o), which achieves 47.1% accuracy, and the strongest open-source model (i.e., InternVL Chat V1.5), which achieves 29.2%. All models lag far behind human performance of 80.5%, underscoring weaknesses in the chart understanding capabilities of existing MLLMs. We hope CharXiv facilitates future research on MLLM chart understanding by providing a more realistic and faithful measure of progress.