Skip to content
← Back to explorer

From Prompting to Preference Optimization: A Comparative Study of LLM-based Automated Essay Scoring

Minh Hoang Nguyen, Vu Hoang Pham, Xuan Thanh Huynh, Phuc Hong Mai, Vinh The Nguyen, Quang Nhut Huynh, Huy Tien Nguyen, Tung Le · Mar 6, 2026 · Citations: 0

Automatic Metrics Coding Pairwise Preference
Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Mar 6, 2026, 3:59 PM

Recent

Extraction refreshed

Mar 13, 2026, 5:37 AM

Fresh

Extraction source

Persisted extraction

Confidence 0.70

Abstract

Large language models (LLMs) have recently reshaped Automated Essay Scoring (AES), yet prior studies typically examine individual techniques in isolation, limiting understanding of their relative merits for English as a Second Language (L2) writing. To bridge this gap, we presents a comprehensive comparison of major LLM-based AES paradigms on IELTS Writing Task~2. On this unified benchmark, we evaluate four approaches: (i) encoder-based classification fine-tuning, (ii) zero- and few-shot prompting, (iii) instruction tuning and Retrieval-Augmented Generation (RAG), and (iv) Supervised Fine-Tuning combined with Direct Preference Optimization (DPO) and RAG. Our results reveal clear accuracy-cost-robustness trade-offs across methods, the best configuration, integrating k-SFT and RAG, achieves the strongest overall results with F1-Score 93%. This study offers the first unified empirical comparison of modern LLM-based AES strategies for English L2, promising potential in auto-grading writing tasks. Code is public at https://github.com/MinhNguyenDS/LLM_AES-EnL2

HFEPX Relevance Assessment

This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.

Best use

Secondary protocol comparison source

Use if you need

A secondary eval reference to pair with stronger protocol papers.

Main weakness

No major weakness surfaced.

Trust level

Moderate

Eval-Fit Score

65/100 • Medium

Useful as a secondary reference; validate protocol details against neighboring papers.

Human Feedback Signal

Detected

Evaluation Signal

Detected

HFEPX Fit

Moderate-confidence candidate

Extraction confidence: Moderate

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

strong

Pairwise Preference

Confidence: Moderate Source: Persisted extraction evidenced

Directly usable for protocol triage.

Evidence snippet: Large language models (LLMs) have recently reshaped Automated Essay Scoring (AES), yet prior studies typically examine individual techniques in isolation, limiting understanding of their relative merits for English as a Second Language (L2) writing.

Evaluation Modes

strong

Automatic Metrics

Confidence: Moderate Source: Persisted extraction evidenced

Includes extracted eval setup.

Evidence snippet: Large language models (LLMs) have recently reshaped Automated Essay Scoring (AES), yet prior studies typically examine individual techniques in isolation, limiting understanding of their relative merits for English as a Second Language (L2) writing.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: Large language models (LLMs) have recently reshaped Automated Essay Scoring (AES), yet prior studies typically examine individual techniques in isolation, limiting understanding of their relative merits for English as a Second Language (L2) writing.

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Persisted extraction missing

No benchmark anchors detected.

Evidence snippet: Large language models (LLMs) have recently reshaped Automated Essay Scoring (AES), yet prior studies typically examine individual techniques in isolation, limiting understanding of their relative merits for English as a Second Language (L2) writing.

Reported Metrics

strong

Accuracy, F1, Cost

Confidence: Moderate Source: Persisted extraction evidenced

Useful for evaluation criteria comparison.

Evidence snippet: Our results reveal clear accuracy-cost-robustness trade-offs across methods, the best configuration, integrating k-SFT and RAG, achieves the strongest overall results with F1-Score 93%.

Rater Population

missing

Unknown

Confidence: Low Source: Persisted extraction missing

Rater source not explicitly reported.

Evidence snippet: Large language models (LLMs) have recently reshaped Automated Essay Scoring (AES), yet prior studies typically examine individual techniques in isolation, limiting understanding of their relative merits for English as a Second Language (L2) writing.

Human Data Lens

  • Uses human feedback: Yes
  • Feedback types: Pairwise Preference
  • Rater population: Unknown
  • Unit of annotation: Unknown
  • Expertise required: Coding
  • Extraction source: Persisted extraction

Evaluation Lens

  • Evaluation modes: Automatic Metrics
  • Agentic eval: None
  • Quality controls: Not reported
  • Confidence: 0.70
  • Flags: None

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

accuracyf1cost

Research Brief

Deterministic synthesis

On this unified benchmark, we evaluate four approaches: (i) encoder-based classification fine-tuning, (ii) zero- and few-shot prompting, (iii) instruction tuning and Retrieval-Augmented Generation (RAG), and (iv) Supervised Fine-Tuning… HFEPX signals include Pairwise Preference, Automatic Metrics with confidence 0.70. Updated from current HFEPX corpus.

Generated Mar 13, 2026, 5:37 AM · Grounded in abstract + metadata only

Key Takeaways

  • On this unified benchmark, we evaluate four approaches: (i) encoder-based classification fine-tuning, (ii) zero- and few-shot prompting, (iii) instruction tuning and…
  • Our results reveal clear accuracy-cost-robustness trade-offs across methods, the best configuration, integrating k-SFT and RAG, achieves the strongest overall results with…

Researcher Actions

  • Compare its human-feedback setup against pairwise and rubric hubs.
  • Identify benchmark choices from full text before operationalizing conclusions.
  • Validate metric comparability (accuracy, f1, cost).

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Extraction confidence is probabilistic and should be validated for critical decisions.

Research Summary

Contribution Summary

  • On this unified benchmark, we evaluate four approaches: (i) encoder-based classification fine-tuning, (ii) zero- and few-shot prompting, (iii) instruction tuning and Retrieval-Augmented Generation (RAG), and (iv) Supervised Fine-Tuning…
  • Our results reveal clear accuracy-cost-robustness trade-offs across methods, the best configuration, integrating k-SFT and RAG, achieves the strongest overall results with F1-Score 93%.

Why It Matters For Eval

  • On this unified benchmark, we evaluate four approaches: (i) encoder-based classification fine-tuning, (ii) zero- and few-shot prompting, (iii) instruction tuning and Retrieval-Augmented Generation (RAG), and (iv) Supervised Fine-Tuning…

Researcher Checklist

  • Pass: Human feedback protocol is explicit

    Detected: Pairwise Preference

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Pass: Metric reporting is present

    Detected: accuracy, f1, cost

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote