TACTutor¶
Product or Programme · All products and programmes
Evidence · 2 claims (2 for) · 1 study (1 design),q2· 0 of 1 report an effect size · 2 claims rest on one study
Description¶
TACTutor is an open 4B language model for adaptive English-as-a-second-language tutoring, developed by Dongjie Yang and colleagues through supervised fine-tuning and taxonomy-grounded reinforcement learning.
Components¶
Claims¶
- In a blinded study with 50 learners, TACTutor receives the highest overall mean rating (5.54/7) and is rated above its backbone across all four teaching-behavior dimensions (+0.39 overall) [+M]
- TACTutor shows no degradation relative to its Qwen backbone on external educational benchmarks, with scores rising on MRBench, TutorBench, LongTutor, and DeepTutor [+M]
Related Products and Programmes¶
-
Key Sources¶
- Dongjie Yang, Siyan Lin, Leixian Shen, Rui Sheng, Huamin Qu, and Zixin Chen. (2026). TACT: Taxonomy-Aligned Post-Training for Pedagogically Adaptive English Tutoring. https://arxiv.org/abs/2608.03952
Page metadata
| Field | Value |
|---|---|
type |
product |
id |
tactutor |
title |
TACTutor |
description |
TACTutor is an open 4B language model for adaptive English-as-a-second-language tutoring, developed by Dongjie Yang and colleagues through supervised fine-tuning and taxonomy-grounded reinforcement learning. |
status |
review |
product_kind |
software |
generated |
by process:settle-candidates on 2026-10-11 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.