LLM-based automated assessment of student code self-explanations outperforms semantic similarity methods on a balanced classification task¶
Claim · All claims
Evidence · 1 study · designr2·q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: 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? In 5-fold cross-validation on a balanced dataset, LLM-based scoring achieved F1 = 0.98 and accuracy = 0.96 while the best semantic similarity method reached F1 = 0.72 and accuracy = 0.65. → Arun-Balajiee Lekshmi-Narayanan 2026
Evidence¶
Arun-Balajiee Lekshmi-Narayanan 2026¶
Arun-Balajiee Lekshmi-Narayanan, Mohammad Hassany, Peter Brusilovsky. (2026). Exploring the Effectiveness of Using LLMs for Automated Assessment of Student Self–Explanations in Programming Education. https://arxiv.org/abs/2605.21614 doi:10.48550/arxiv.2605.21614
q2 · i? · design · r2
Comparison experiment on the balanced SelfCode2.0 subset using 5-fold cross-validation, with LLMs run zero-shot and semantic similarity thresholds tuned on training folds. Table 1 reports LLM Behavior at "F1 = 0.98, Accuracy = 0.96" versus Deep Tutor, RoBERTa and GPT-SE (best F1 = 0.72, accuracy = 0.65).
"the LLM Behavior (F1 = 0.98, Accuracy = 0.96) outperforms Deep Tutor (F1 = 0.69, Accuracy = 0.6) and RoBERTa (F1 = 0.7, Accuracy = 0.61)"
Discussion¶
Related Claims¶
- LLM-based assessment can replace similarity-based methods because it needs no ground-truth response and no correctness threshold — related
- A construction-focused correctness rubric underperformed behavior-focused and undefined prompts for LLM scoring of code explanations — related
- Frontier LLMs achieve the best balance between detecting misconceptions in correct-answer cases and not over-flagging correct students, while fine-tuned local models achieve under 58% TM recall — related
- LLM-based scoring produced fewer false negatives than Deep Tutor on a balanced test set, which the authors expect would spare students the frustration of correct explanations judged incorrect — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
llm-assessment-outperforms-semantic-similarity-code-explanations |
title |
LLM-based automated assessment of student code self-explanations outperforms semantic similarity methods on a balanced classification task |
description |
LLM-based automated assessment of student code self-explanations outperforms semantic similarity methods on a balanced classification task |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2026 |
recheck_by |
2029 |
generated |
by process:wiki-ingest on 2026-10-11 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — arun-balajiee-lekshmi-narayanan-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.