Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Pan, Yikang, Zhu, Yi, Xie, Rand, Liu, Yizhi
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2412.09884
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915062835314688
author Pan, Yikang
Zhu, Yi
Xie, Rand
Liu, Yizhi
author_facet Pan, Yikang
Zhu, Yi
Xie, Rand
Liu, Yizhi
contents Large Language Models (LLMs), while being increasingly dominant on a myriad of knowledge-intensive activities, have only had limited success understanding lengthy table-text mixtures, such as academic papers and financial reports. Recent advances of long-context LLMs have opened up new possibilities for this field. Nonetheless, we identify two roadblocks: (1) Prior benchmarks of table question answering (TableQA) have focused on isolated tables without context, making it hard to evaluate models in real-world scenarios. (2) Prior benchmarks have focused on some narrow skill sets of table comprehension such as table recognition, data manipulation/calculation, table summarization etc., while a skilled human employs those skills collectively. In this work, we introduce TableQuest, a new benchmark designed to evaluate the holistic table comprehension capabilities of LLMs in the natural table-rich context of financial reports. We employ a rigorous data processing and filtering procedure to ensure that the question-answer pairs are logical, reasonable, and diverse. We experiment with 7 state-of-the-art models, and find that despite reasonable accuracy in locating facts, they often falter when required to execute more sophisticated reasoning or multi-step calculations. We conclude with a qualitative study of the failure modes and discuss the challenges of constructing a challenging benchmark. We make the evaluation data, judging procedure and results of this study publicly available to facilitate research in this field.
format Preprint
id arxiv_https___arxiv_org_abs_2412_09884
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Benchmarking Table Comprehension In The Wild
Pan, Yikang
Zhu, Yi
Xie, Rand
Liu, Yizhi
Computation and Language
Large Language Models (LLMs), while being increasingly dominant on a myriad of knowledge-intensive activities, have only had limited success understanding lengthy table-text mixtures, such as academic papers and financial reports. Recent advances of long-context LLMs have opened up new possibilities for this field. Nonetheless, we identify two roadblocks: (1) Prior benchmarks of table question answering (TableQA) have focused on isolated tables without context, making it hard to evaluate models in real-world scenarios. (2) Prior benchmarks have focused on some narrow skill sets of table comprehension such as table recognition, data manipulation/calculation, table summarization etc., while a skilled human employs those skills collectively. In this work, we introduce TableQuest, a new benchmark designed to evaluate the holistic table comprehension capabilities of LLMs in the natural table-rich context of financial reports. We employ a rigorous data processing and filtering procedure to ensure that the question-answer pairs are logical, reasonable, and diverse. We experiment with 7 state-of-the-art models, and find that despite reasonable accuracy in locating facts, they often falter when required to execute more sophisticated reasoning or multi-step calculations. We conclude with a qualitative study of the failure modes and discuss the challenges of constructing a challenging benchmark. We make the evaluation data, judging procedure and results of this study publicly available to facilitate research in this field.
title Benchmarking Table Comprehension In The Wild
topic Computation and Language
url https://arxiv.org/abs/2412.09884