Enhancing Financial VQA in Vision Language Models using Intermediate Structured Representations

Chart interpretation is crucial for visual data analysis, but accurately extracting information from charts poses significant challenges for automated models. This study investigates the fine-tuning of DEPLOT, a modality conversion module that translates the image of a plot or chart to a linearized table, on a custom dataset of 50,000 bar charts. The dataset comprises simple, stacked, and grouped bar charts, targeting the unique structural features of these visualizations. The finetuned DEPLOT model is evaluated against its base version using a test set of 1,000 images and two metrics: Relative Mapping Similarity (RMS), which measures categorical mapping accuracy, and Relative Number Set Similarity (RNSS), which evaluates numerical interpretation accuracy. To further explore the reasoning capabilities of large language models (LLMs), we curate an additional set of 100 bar chart images paired with question answer sets. Our findings demonstrate that providing a structured intermediate table alongside the image significantly enhances LLM reasoning performance compared to direct image queries.

Contextual Emotion Estimation from Image Captions

Emotion estimation in images is a challenging task, typically using computer vision methods to directly estimate people's emotions using face, body pose and contextual cues. In this paper, we explore whether Large Language Models (LLMs) can support the contextual emotion estimation task, by first captioning images, then using an LLM for inference. First, we must understand: how well do LLMs perceive human emotions? And which parts of the information enable them to determine emotions? One initial challenge is to construct a caption that describes a person within a scene with information relevant for emotion perception. Towards this goal, we propose a set of natural language descriptors for faces, bodies, interactions, and environments. We use them to manually generate captions and emotion annotations for a subset of 331 images from the EMOTIC dataset. These captions offer an interpretable representation for emotion estimation, towards understanding how elements of a scene affect emotion perception in LLMs and beyond. Secondly, we test the capability of a large language model to infer an emotion from the resulting image captions. We find that GPT-3.5, specifically the text-davinci-003 model, provides surprisingly reasonable emotion predictions consistent with human annotations, but accuracy can depend on the emotion concept. Overall, the results suggest promise in the image captioning and LLM approach.