Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| 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 |