The proposed framework outperforms fine-tuned BERT, Instructor-LM, GPT-4, and RAPT on TeacherEval-2023 across consistency, credibility, calibration, and fairness metrics¶
Claim · All claims
Evidence · 1 study · designr2·q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person · recheck by 2028: tool and model accuracy changes quickly
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? On TeacherEval-2023 the framework achieves ICS of 82.4%, 12.6 points higher than BERT-base and 9.2 points higher than Instructor-LM, with ExpScore 0.78, ECE 0.032, and FG 1.8% versus 6–9% for baselines. → Li 2025
Evidence¶
Li 2025¶
Li, Y.; Yang, H.; Fang, Q. (2025). Towards Trustworthy and Explainable-by-Design Large Language Models for Automated Teacher Assessment. Information 2025, 16, 882. https://doi.org/10.3390/info16100882
q2 · i? · design · r2
Quantitative comparison on TeacherEval-2023 (Table 3) against BERT-base, Instructor-LM, GPT-4, and RAPT; the framework reports "an ICS of 82.4%", ExpScore 0.78, ECE 0.032, and FG 1.8% versus a 6–9% baseline range, with paired t-tests reported significant at α = 0.05.
"The proposed framework achieves an ICS of 82.4%, which is 12.6 absolute points higher than BERT-base and 9.2 points higher than Instructor-LM. The ExpScore reaches 0.78, representing an increase of 0.31 over BERT-base."
Discussion¶
Related Claims¶
- Fine-tuned BERT outperforms a Naive Bayes baseline and zero-shot GPT-4 in classifying self-affirmation essays — related
- GPT-4 classifies self-affirmation essays reasonably in zero-shot mode but below fine-tuned BERT, and few-shot prompting does not appreciably improve it — related
- The framework is robust to 15% ASR transcription noise and retains 99.6% of its ICS under zero-shot cross-domain transfer to EdNet-Math — related
- Expert raters rate TeachingCoach higher than a GPT-4o baseline on clarity, tone, reflection, and acknowledgment of user input — related
- In one reviewed study, GPT-4 automated essay scoring showed score inflation, with AI–human rating discrepancies exceeding 1.5 standard deviations in 38% of graduate-level bibliographies — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
llm-teacher-assessment-outperforms-baselines-teachereval |
title |
The proposed framework outperforms fine-tuned BERT, Instructor-LM, GPT-4, and RAPT on TeacherEval-2023 across consistency, credibility, calibration, and fairness metrics |
description |
The proposed framework outperforms fine-tuned BERT, Instructor-LM, GPT-4, and RAPT on TeacherEval-2023 across consistency, credibility, calibration, and fairness metrics |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2025 |
recheck_by |
2028 |
generated |
by process:wiki-ingest on 2026-10-12 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — li-2025 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.