Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2406.17274 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914967657119744 |
|---|---|
| author | He, Jianfeng Yang, Runing Yu, Linlin Li, Changbin Jia, Ruoxi Chen, Feng Jin, Ming Lu, Chang-Tien |
| author_facet | He, Jianfeng Yang, Runing Yu, Linlin Li, Changbin Jia, Ruoxi Chen, Feng Jin, Ming Lu, Chang-Tien |
| contents | Text summarization, a key natural language generation (NLG) task, is vital in various domains. However, the high cost of inaccurate summaries in risk-critical applications, particularly those involving human-in-the-loop decision-making, raises concerns about the reliability of uncertainty estimation on text summarization (UE-TS) evaluation methods. This concern stems from the dependency of uncertainty model metrics on diverse and potentially conflicting NLG metrics. To address this issue, we introduce a comprehensive UE-TS benchmark incorporating 31 NLG metrics across four dimensions. The benchmark evaluates the uncertainty estimation capabilities of two large language models and one pre-trained language model on three datasets, with human-annotation analysis incorporated where applicable. We also assess the performance of 14 common uncertainty estimation methods within this benchmark. Our findings emphasize the importance of considering multiple uncorrelated NLG metrics and diverse uncertainty estimation methods to ensure reliable and efficient evaluation of UE-TS techniques. Our code and data are available https://github.com/he159ok/Benchmark-of-Uncertainty-Estimation-Methods-in-Text-Summarization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_17274 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Can We Trust the Performance Evaluation of Uncertainty Estimation Methods in Text Summarization? He, Jianfeng Yang, Runing Yu, Linlin Li, Changbin Jia, Ruoxi Chen, Feng Jin, Ming Lu, Chang-Tien Computation and Language Machine Learning Text summarization, a key natural language generation (NLG) task, is vital in various domains. However, the high cost of inaccurate summaries in risk-critical applications, particularly those involving human-in-the-loop decision-making, raises concerns about the reliability of uncertainty estimation on text summarization (UE-TS) evaluation methods. This concern stems from the dependency of uncertainty model metrics on diverse and potentially conflicting NLG metrics. To address this issue, we introduce a comprehensive UE-TS benchmark incorporating 31 NLG metrics across four dimensions. The benchmark evaluates the uncertainty estimation capabilities of two large language models and one pre-trained language model on three datasets, with human-annotation analysis incorporated where applicable. We also assess the performance of 14 common uncertainty estimation methods within this benchmark. Our findings emphasize the importance of considering multiple uncorrelated NLG metrics and diverse uncertainty estimation methods to ensure reliable and efficient evaluation of UE-TS techniques. Our code and data are available https://github.com/he159ok/Benchmark-of-Uncertainty-Estimation-Methods-in-Text-Summarization. |
| title | Can We Trust the Performance Evaluation of Uncertainty Estimation Methods in Text Summarization? |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2406.17274 |