Research map / Label-efficient and robust learning / Recognition and long-tail
Automated Cross-prompt Scoring of Essay Traits
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 CTS's multi-task shared/private-layer architecture instead of training a separate PAES model for each trait | Cross-prompt essay trait scoring · ASAP/ASAP++ all prompts | average QWK: 0.527 -> 0.545 | Helped |
| Add trait attention to CTS (ablation) | CTS · ASAP/ASAP++ all prompts | average QWK: 0.535 -> 0.545 | Helped |
| Add trait attention to CTS (ablation) | CTS · ASAP/ASAP++ Prompt 5 | average QWK across traits: 0.616 -> 0.613 | Hurt |
| Add trait attention to CTS (ablation) | CTS · ASAP/ASAP++ Prompt 2, overall score | QWK: 0.578 -> 0.617 | Helped |
| Add trait attention to CTS (ablation) | CTS · ASAP/ASAP++ Prompt 2, Content | QWK: 0.558 -> 0.518 | Hurt |
| Use multi-task CTS rather than single-task PAES for traits with sparse training coverage | Cross-prompt essay trait scoring · ASAP/ASAP++ Prompt 2, Word Choice | QWK: 0.480 -> 0.544 | Helped |
| Use multi-task CTS rather than single-task PAES for traits with sparse training coverage | Cross-prompt essay trait scoring · ASAP/ASAP++ Prompt 2, Sentence Fluency | QWK: 0.534 -> 0.567 | Helped |
| Use CTS instead of PAES | Cross-prompt essay trait scoring · ASAP/ASAP++ Prompt 5 | average QWK across traits: 0.634 -> 0.613 | Hurt |
| Use CTS instead of PAES | Cross-prompt essay trait scoring · ASAP/ASAP++ all prompts, Prompt Adherence | QWK: 0.570 -> 0.565 | Hurt |
Closest papers by meaning
- Unveiling the Tapestry of Automated Essay Scoring: A Comprehensive Investigation of Accuracy, Fairness, and Generalizability (AAAI 2024 · similarity 0.94)
- KAES: Multi-aspect Shared Knowledge Finding and Aligning for Cross-prompt Automated Scoring of Essay Traits (AAAI 2025 · similarity 0.90)
- Towards Automatic Boundary Detection for Human-AI Collaborative Hybrid Essay in Education (AAAI 2024 · similarity 0.82)
- IDGen: Item Discrimination Induced Prompt Generation for LLM Evaluation (NeurIPS 2024 · similarity 0.80)
- AAAR-1.0: Assessing AI’s Potential to Assist Research (ICML 2025 · similarity 0.80)
- Automated Evaluation of Retrieval-Augmented Language Models with Task-Specific Exam Generation (ICML 2024 · similarity 0.80)
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.