Long Context Automated Essay Scoring with Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912585007235072 |
|---|---|
| author | Ormerod, Christopher Kehat, Gitit |
| author_facet | Ormerod, Christopher Kehat, Gitit |
| contents | Transformer-based language models are architecturally constrained to process text of a fixed maximum length. Essays written by higher-grade students frequently exceed the maximum allowed length for many popular open-source models. A common approach to addressing this issue when using these models for Automated Essay Scoring is to truncate the input text. This raises serious validity concerns as it undermines the model's ability to fully capture and evaluate organizational elements of the scoring rubric, which requires long contexts to assess. In this study, we evaluate several models that incorporate architectural modifications of the standard transformer architecture to overcome these length limitations using the Kaggle ASAP 2.0 dataset. The models considered in this study include fine-tuned versions of XLNet, Longformer, ModernBERT, Mamba, and Llama models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_10417 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Long Context Automated Essay Scoring with Language Models Ormerod, Christopher Kehat, Gitit Computation and Language Transformer-based language models are architecturally constrained to process text of a fixed maximum length. Essays written by higher-grade students frequently exceed the maximum allowed length for many popular open-source models. A common approach to addressing this issue when using these models for Automated Essay Scoring is to truncate the input text. This raises serious validity concerns as it undermines the model's ability to fully capture and evaluate organizational elements of the scoring rubric, which requires long contexts to assess. In this study, we evaluate several models that incorporate architectural modifications of the standard transformer architecture to overcome these length limitations using the Kaggle ASAP 2.0 dataset. The models considered in this study include fine-tuned versions of XLNet, Longformer, ModernBERT, Mamba, and Llama models. |
| title | Long Context Automated Essay Scoring with Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.10417 |