Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.04771 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916151828676608 |
|---|---|
| author | Ai, Lin Hui, Zheng Liu, Zizhou Hirschberg, Julia |
| author_facet | Ai, Lin Hui, Zheng Liu, Zizhou Hirschberg, Julia |
| contents | To address the challenges of out-of-control generation in generative models for machine reading comprehension (MRC), we introduce the Question-Attended Span Extraction (QASE) module. Integrated during the fine-tuning of pre-trained generative language models (PLMs), QASE enables these PLMs to match SOTA extractive methods and outperform leading LLMs like GPT-4 in MRC tasks, without significant increases in computational costs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_04771 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | QASE Enhanced PLMs: Improved Control in Text Generation for MRC Ai, Lin Hui, Zheng Liu, Zizhou Hirschberg, Julia Computation and Language To address the challenges of out-of-control generation in generative models for machine reading comprehension (MRC), we introduce the Question-Attended Span Extraction (QASE) module. Integrated during the fine-tuning of pre-trained generative language models (PLMs), QASE enables these PLMs to match SOTA extractive methods and outperform leading LLMs like GPT-4 in MRC tasks, without significant increases in computational costs. |
| title | QASE Enhanced PLMs: Improved Control in Text Generation for MRC |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2403.04771 |