TACTCorpus and TACTBench

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

Dongjie Yang et al.'s released corpus, diagnostic benchmark, annotations, and model weights support reproducible research on pedagogically adaptive next-turn generation for one-to-one ESL tutoring.

Components

Claims

• Taxonomy-guided post-training raises TACTutor's TACT_Overall on TACTBench from 0.629 (backbone) to 0.832, the highest among evaluated models [+M]
• Post-training improves TACTutor's auxiliary guardrail flags on TACTBench: accept rate rises from 0.603 to 0.872 and leak-or-overhelp falls from 0.346 to 0.026 [+M]

Related Products and Programmes

• FEEDTYPE: a benchmark of teacher and LLM feedback annotated for feedback focus across three writing domains

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	tactcorpus-and-tactbench
title	TACTCorpus and TACTBench
description	Dongjie Yang et al.'s released corpus, diagnostic benchmark, annotations, and model weights support reproducible research on pedagogically adaptive next-turn generation for one-to-one ESL tutoring.
status	review
product_kind	dataset
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.