Research map / Large language models / Language, safety and interpretability
H-AES: Towards Automated Essay Scoring for Hindi
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use a fine-tuned multilingual transformer rather than feature-based or neural approaches | Hindi AES · ASAP-Hindi average | QWK: 0.688 -> 0.741 | Helped |
| Use XLM-RoBERTa rather than other evaluated models | Hindi AES · ASAP-Hindi P4 | QWK: 0.809 | Helped |
| Use XLM-RoBERTa rather than other evaluated models | Hindi AES · ASAP-Hindi P5 | QWK: 0.834 | Helped |
| Use XLM-RoBERTa rather than other evaluated models | Hindi AES · ASAP-Hindi P6 | QWK: 0.822 | Helped |
| Use XLM-RoBERTa rather than other evaluated models | Hindi AES · ASAP-Hindi P7 | QWK: 0.794 | Helped |
| Use mBERT rather than other evaluated models | Hindi AES · ASAP-Hindi P3 | QWK: 0.711 | Helped |
| Use XGBoost rather than other evaluated models | Hindi AES · ASAP-Hindi P2 | QWK: 0.667 | Helped |
| Use XGBoost rather than other evaluated models | Hindi AES · ASAP-Hindi P8 | QWK: 0.641 | Helped |
| Use mBERT rather than other evaluated models | Hindi AES · Organic prompt (Travel) | QWK: 0.852 | Helped |
| Use an Indic-specific transformer rather than mBERT or XLM-RoBERTa | Hindi AES · ASAP-Hindi average | QWK: 0.720 vs 0.656; 0.720 vs 0.589 | Hurt |
| Use source-dependent prompts with consistent syntax, coherence, and source material | AES models · ASAP-Hindi P4, P5, and P6 | QWK | Helped |
| Use larger multilingual pretrained models rather than feature-based or smaller approaches | Hindi AES · ASAP-Hindi | QWK | Helped |
Closest papers by meaning
- Unveiling the Tapestry of Automated Essay Scoring: A Comprehensive Investigation of Accuracy, Fairness, and Generalizability (AAAI 2024 · similarity 0.89)
- KAES: Multi-aspect Shared Knowledge Finding and Aligning for Cross-prompt Automated Scoring of Essay Traits (AAAI 2025 · similarity 0.87)
- Towards Automatic Boundary Detection for Human-AI Collaborative Hybrid Essay in Education (AAAI 2024 · similarity 0.83)
- IPAD: Inverse Prompt for AI Detection - A Robust and Interpretable LLM-Generated Text Detector (NeurIPS 2025 · similarity 0.82)
- AAAR-1.0: Assessing AI’s Potential to Assist Research (ICML 2025 · similarity 0.82)
- Reliable and Efficient Amortized Model-based Evaluation (ICML 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.