AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

HSKBenchmark: Modeling and Benchmarking Chinese Second Language Acquisition in Large Language Models Through Curriculum Tuning

Qihao Yang, Xuelin Wang, Jiale Chen, Xuelian Dong, Yuxin Hao, Tianyong Hao

AAAI 2026 · Large language models › Instruction and fine-tuning · approach: Calibration and knowledge in LLM tuning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add curriculum tuning from HSK3 to HSK6 (staged pretraining plus instruction tuning)LLaMA2-7B-Chat · HSKBenchmark writing testholistic score: 70.0000 -> 81.8333Improved
add curriculum tuning from HSK3 to HSK6Mistral-7B-Instruct-v0.3 · HSKBenchmark writing testholistic score: 76.8333 -> 85.3333Improved
add curriculum tuning from HSK3 to HSK6Chinese-Alpaca-2-7B · HSKBenchmark writing testholistic score: 77.5000 -> 85.6667Improved
tune only through HSK3 (first stage)Chinese-Alpaca-2-7B · HSKBenchmark writing testholistic score: 77.5000 -> 75.8333Hurt
add curriculum tuning to reduce writing errorsLLaMA2-7B-Chat · HSKBenchmark writing testwriting errors (Err): 0.9000 -> 0.5333Improved
add curriculum tuning to raise lexical complexityMistral-7B-Instruct-v0.3 · HSKBenchmark writing testMATTR-50: 0.5260 -> 0.7886Improved
curriculum tuning versus syntactic complexity on Chinese-Alpaca and Llama2Llama2 and Chinese-Alpaca · HSKBenchmark writing testMDD: 2.4253 -> 2.5558 (Llama2HSK6)No clear effect
order data by HSK level (curriculum) instead of shuffling all data into four stages (ablation)Llama2, Chinese-Alpaca, Mistral · HSKBenchmark writing test, average scoreholistic scoreMixed
add curriculum tuning and check general ability after tuningLlama2 · MMLUaccuracyNo clear effect
add curriculum tuning and check Chinese general abilityLlama2 · C-EvalaccuracyImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy