Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.07912 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909832614772736 |
|---|---|
| author | Zhua, Fanwei He, Jiaxuan Chen, Xiaoxiao Chen, Zulong Lu, Quan Mei, Chenrui |
| author_facet | Zhua, Fanwei He, Jiaxuan Chen, Xiaoxiao Chen, Zulong Lu, Quan Mei, Chenrui |
| contents | Automatic grading of subjective questions remains a significant challenge in examination assessment due to the diversity in question formats and the open-ended nature of student responses. Existing works primarily focus on a specific type of subjective question and lack the generality to support comprehensive exams that contain diverse question types. In this paper, we propose a unified Large Language Model (LLM)-enhanced auto-grading framework that provides human-like evaluation for all types of subjective questions across various domains. Our framework integrates four complementary modules to holistically evaluate student answers. In addition to a basic text matching module that provides a foundational assessment of content similarity, we leverage the powerful reasoning and generative capabilities of LLMs to: (1) compare key knowledge points extracted from both student and reference answers, (2) generate a pseudo-question from the student answer to assess its relevance to the original question, and (3) simulate human evaluation by identifying content-related and non-content strengths and weaknesses. Extensive experiments on both general-purpose and domain-specific datasets show that our framework consistently outperforms traditional and LLM-based baselines across multiple grading metrics. Moreover, the proposed system has been successfully deployed in real-world training and certification exams at a major e-commerce enterprise. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_07912 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Human-Like Grading: A Unified LLM-Enhanced Framework for Subjective Question Evaluation Zhua, Fanwei He, Jiaxuan Chen, Xiaoxiao Chen, Zulong Lu, Quan Mei, Chenrui Computation and Language Artificial Intelligence Automatic grading of subjective questions remains a significant challenge in examination assessment due to the diversity in question formats and the open-ended nature of student responses. Existing works primarily focus on a specific type of subjective question and lack the generality to support comprehensive exams that contain diverse question types. In this paper, we propose a unified Large Language Model (LLM)-enhanced auto-grading framework that provides human-like evaluation for all types of subjective questions across various domains. Our framework integrates four complementary modules to holistically evaluate student answers. In addition to a basic text matching module that provides a foundational assessment of content similarity, we leverage the powerful reasoning and generative capabilities of LLMs to: (1) compare key knowledge points extracted from both student and reference answers, (2) generate a pseudo-question from the student answer to assess its relevance to the original question, and (3) simulate human evaluation by identifying content-related and non-content strengths and weaknesses. Extensive experiments on both general-purpose and domain-specific datasets show that our framework consistently outperforms traditional and LLM-based baselines across multiple grading metrics. Moreover, the proposed system has been successfully deployed in real-world training and certification exams at a major e-commerce enterprise. |
| title | Towards Human-Like Grading: A Unified LLM-Enhanced Framework for Subjective Question Evaluation |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2510.07912 |