2024/04/09 by Tianyu Cao, Natraj Raman, Cao, Tianyu +5 · 2 citations
Computer Science · #Advanced Text Analysis Techniques #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Data Mining Algorithms and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2404.06162
openalex publication_date 2024/04/09 · openalex created_date 2024/04/12 · openalex updated_date 2026/07/28
As large language models (LLMs) expand the power of natural language processing to handle long inputs, rigorous and systematic analyses are necessary to understand their abilities and behavior. A salient application is summarization, due to its ubiquity and controversy (e.g., researchers have declared the death of summarization). In this paper, we use financial report summarization as a case study because financial reports are not only long but also use numbers and tables extensively. We propose a computational framework for characterizing multimodal long-form summarization and investigate the behavior of Claude 2.0/2.1, GPT-4/3.5, and Cohere. We find that GPT-3.5 and Cohere fail to perform this summarization task meaningfully. For Claude 2 and GPT-4, we analyze the extractiveness of the summary and identify a position bias in LLMs. This position bias disappears after shuffling the input for Claude, which suggests that Claude seems to recognize important information. We also conduct a comprehensive investigation on the use of numeric data in LLM-generated summaries and offer a taxonomy of numeric hallucination. We employ prompt engineering to improve GPT-4's use of numbers with limited success. Overall, our analyses highlight the strong capability of Claude 2 in handling long multimodal inputs compared to GPT-4. The generated summaries and evaluation code are available at https://github.com/ChicagoHAI/characterizing-multimodal-long-form-summarization.