Explainable-by-design framework coupling dual-lens hierarchical attention, trust-gated inference, and on-the-spot explanation generation¶
Research Method · All research methods
Evidence · 2 claims (2 for) · 1 study (1 design),q2· 0 of 1 report an effect size · 2 claims rest on one study
Description¶
The framework is an LLM-based teacher assessment architecture in which trustworthiness and explainability are built into inference rather than appended afterward. It couples "a global lens aligned to curriculum standards and a local lens aligned to subject-specific rubrics" with a Trust-Gated Inference module combining Monte-Carlo-dropout calibration and adversarial debiasing, and an On-the-Spot Explanation generator that shares the same fused representation and predicted score used for decision making, so explanations are decision-consistent and curriculum-anchored. Trust gating exposes uncertainty and bias alerts and can output Reject with reason.
Accounts¶
- Explainable-by-design framework coupling dual-lens hierarchical attention, trust-gated inference, and on-the-spot explanation generation: The framework is an LLM-based teacher assessment architecture in which trustworthiness and explainability are built into inference rather than appended afterward. It couples "a global lens aligned to curriculum standards and a local lens aligned to subject-specific rubrics" with a Trust-Gated Inference module combining Monte-Carlo-dropout calibration and adversarial debiasing, and an On-the-Spot Explanation generator that shares the same fused representation and predicted score used for decision making, so explanations are decision-consistent and curriculum-anchored. Trust gating exposes uncertainty and bias alerts and can output Reject with reason. (Li et al. (2025))
Claims¶
- The proposed framework outperforms fine-tuned BERT, Instructor-LM, GPT-4, and RAPT on TeacherEval-2023 across consistency, credibility, calibration, and fairness metrics [+M]
- Ablations show the trustworthiness module contributes most to performance, and the explanation generator cuts human review time by 41% [+M]
Related Research Methods¶
-
Key Sources¶
- 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
Page metadata
| Field | Value |
|---|---|
type |
research-method |
id |
explainable-by-design-framework-coupling-dual-lens-hierarchical-attention-trust-gated-infe |
title |
Explainable-by-design framework coupling dual-lens hierarchical attention, trust-gated inference, and on-the-spot explanation generation |
description |
The framework is an LLM-based teacher assessment architecture in which trustworthiness and explainability are built into inference rather than appended afterward. |
status |
review |
generated |
by process:settle-candidates on 2026-10-12 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.