Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.14165 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909585596481536 |
|---|---|
| author | Zhang, Ziyan Hou, Yang Gong, Chen Li, Zhenghua |
| author_facet | Zhang, Ziyan Hou, Yang Gong, Chen Li, Zhenghua |
| contents | Large language models (LLMs) have achieved remarkable success across various natural language processing (NLP) tasks. However, recent studies suggest that they still face challenges in performing fundamental NLP tasks essential for deep language understanding, particularly syntactic parsing. In this paper, we conduct an in-depth analysis of LLM parsing capabilities, delving into the specific shortcomings of their parsing results. We find that LLMs may stem from limitations to fully leverage grammar rules in existing treebanks, which restricts their capability to generate valid syntactic structures. To help LLMs acquire knowledge without additional training, we propose a self-correction method that leverages grammar rules from existing treebanks to guide LLMs in correcting previous errors. Specifically, we automatically detect potential errors and dynamically search for relevant rules, offering hints and examples to guide LLMs in making corrections themselves. Experimental results on three datasets with various LLMs, demonstrate that our method significantly improves performance in both in-domain and cross-domain settings on the English and Chinese datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_14165 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Self-Correction Makes LLMs Better Parsers Zhang, Ziyan Hou, Yang Gong, Chen Li, Zhenghua Computation and Language Large language models (LLMs) have achieved remarkable success across various natural language processing (NLP) tasks. However, recent studies suggest that they still face challenges in performing fundamental NLP tasks essential for deep language understanding, particularly syntactic parsing. In this paper, we conduct an in-depth analysis of LLM parsing capabilities, delving into the specific shortcomings of their parsing results. We find that LLMs may stem from limitations to fully leverage grammar rules in existing treebanks, which restricts their capability to generate valid syntactic structures. To help LLMs acquire knowledge without additional training, we propose a self-correction method that leverages grammar rules from existing treebanks to guide LLMs in correcting previous errors. Specifically, we automatically detect potential errors and dynamically search for relevant rules, offering hints and examples to guide LLMs in making corrections themselves. Experimental results on three datasets with various LLMs, demonstrate that our method significantly improves performance in both in-domain and cross-domain settings on the English and Chinese datasets. |
| title | Self-Correction Makes LLMs Better Parsers |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2504.14165 |