Challenge: Existing automated essay scoring relies on essay text without explanatory rationales for the scores.
Approach: They propose a rationale-based multiple trait scoring approach that integrates large language models with a smaller large language model to generate trait-specific rationales.
Outcome: The proposed approach outperforms state-of-the-art models and vanilla S-LLMs on benchmark datasets.

Similar Papers

Can Large Language Models Automatically Score Proficiency of Written Essays? (2024.lrec-main)

Copied to clipboard

Challenge: Automated essay scoring (AES) is one of the earliest research problems in natural language processing.
Approach: They propose to use large language models to analyze and score written essays using four different prompts.
Outcome: The proposed models show comparable performance on four different prompts and a slight advantage over the state-of-the-art models.
Unleashing Large Language Models’ Proficiency in Zero-shot Essay Scoring (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in automated essay scoring (AES) have relied on labeled essays, requiring tremendous cost and expertise for their acquisition.
Approach: They propose a zero-shot prompting framework that automatically decomposes writing proficiency into distinct traits and generates scoring criteria for each trait.
Outcome: The proposed framework outperforms straightforward prompting (Vanilla) on TOEFL11 and ASAP, while the small-sized Llama2-13b-chat significantly outperformed ChatGPT.
TRATES: Trait-Specific Rubric-Assisted Cross-Prompt Essay Scoring (2025.findings-acl)

Copied to clipboard

Challenge: Automated Essay Scoring (AES) has seen significant progress in assessing writing ability and trait scoring.
Approach: They propose a trait-specific and rubric-based cross-prompt AES framework that is generic yet specific to the underlying trait.
Outcome: The proposed framework achieves state-of-the-art across all traits on a widely-used dataset, with the generated LLM-based features being the most significant.
Automated Chinese Essay Scoring from Multiple Traits (2022.coling-1)

Copied to clipboard

Challenge: Current research on AES focuses on scoring the overall quality or single trait of prompt-specific essays.
Approach: They propose a hierarchical multi-task trait scorer to evaluate quality of writing . they propose an inter-sequence attention mechanism to enhance information interaction .
Outcome: The proposed model outperforms several strong models on ACEA and outperformed other models.
EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Automated Essay Scoring (AES) systems face three major challenges: reliance on handcrafted features that limit generalizability, difficulty in capturing fine-grained traits like coherence and argumentation, and inability to handle multimodal contexts.
Approach: They propose a multimodal benchmark to evaluate AES capabilities across lexical-, sentence-, and discourse-level traits without manual feature engineering.
Outcome: The proposed system can evaluate AES capabilities across lexical-, sentence-, and discourse-level traits without manual feature engineering.
LLM Agents at the Roundtable: A Multi-Perspective and Dialectical Reasoning Framework for Essay Scoring (2025.findings-emnlp)

Copied to clipboard

Challenge: a new framework for automated essay scoring is needed to achieve multi-perspective understanding and judgment.
Approach: They propose a roundtable essay scoring framework that performs precise and human-aligned scoring under a zero-shot setting.
Outcome: The proposed framework outperforms previous zero-shot AES approaches by enabling collaboration among agents with diverse evaluation perspectives.
Beyond Agreement: Diagnosing the Rationale Alignment of Automated Essay Scoring Methods based on Linguistically-informed Counterfactuals (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing Automated Essay Scoring (AES) methods focus on sentence-level features, whereas Large Language Models (LLMs) are sensitive to conventions & accuracy, language complexity, and organization.
Approach: They propose to use large language models to aid in decision-making . they propose to analyze the reasoning of neural models by analyzing sentence-level features.
Outcome: The proposed method improves understanding of neural approaches to Automated Essay Scoring (AES) and can also apply to other domains seeking transparency in model-driven decisions.
T-MES: Trait-Aware Mix-of-Experts Representation Learning for Multi-trait Essay Scoring (2025.coling-main)

Copied to clipboard

Challenge: Existing methods for automatic essay scoring fail to learn trait representations and ignore correlations between trait scores.
Approach: They propose a multi-trait essay scoring method based on Trait-Aware Mix-of-Experts Representation Learning.
Outcome: The proposed method improves on existing methods and improves in computational efficiency.
Prompt- and Trait Relation-aware Cross-prompt Essay Trait Scoring (2023.findings-acl)

Copied to clipboard

Challenge: Existing systems assume to grade essays on same prompt as used in training and assign only a holistic score.
Approach: They propose a prompt- and trait relation-aware cross-prompt essay trait scorer that encodes prompt-awful essay representation by essay-promotion attention and utilizing the topic-coherence feature extracted by the topic model.
Outcome: The proposed model shows state-of-the-art results for all prompts and traits.
Autoregressive Multi-trait Essay Scoring via Reinforcement Learning with Scoring-aware Multiple Rewards (2024.emnlp-main)

Copied to clipboard

Challenge: Existing reinforcement learning (RL) applications in AES are limited to classification models despite associated performance degradation.
Approach: They propose to integrate actual evaluation schemes into the training process by designing QWK-based rewards with a mean-squared error penalty for multi-trait AES.
Outcome: The proposed scoring-aware multi-reward reinforcement learning integrates actual evaluation schemes into the training process.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations