Model and Training Scripts for LLM-Fine-Tuned Psychological Questionnaires

A 2.3 MB ZIP file contains model and training configuration scripts from a study that reimagined psychology questionnaire development using LLM technology. The research fine-tuned the Qwen-2.5 and GLM-4 models on a corpus of 169 professional psychological questionnaires, integrating instruction fine-tuning with human feedback reinforcement. Author Zhitao Yuan uploaded this dataset to figshare under a CC-BY-4.0 license, with a last update timestamp of 2026-04-24.

Use Cases

• Fine-tuning LLMs for psychological assessment tasks based on the described specialized scheme.
• Evaluating text generation quality improvements (e.g., BLEU-4, ROUGE-L) for model outputs.
• Assessing scientific rigor and logical consistency in AI-generated psychological content.
• Studying cultural adaptability in AI models for cross-regional expression conversion.

Strengths

• The underlying study reports specific performance gains: BLEU-4 increased by 0.05 and ROUGE-L by 0.057.
• Logical consistency of the optimized models improved by 28.6%.
• Cultural adaptability achieved over 85% accuracy in cross-regional expression conversion.
• The fine-tuning corpus consisted of 169 professional psychological questionnaires.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The dataset is small at 2.3 MB, suggesting it contains scripts and configurations rather than large-scale data.

Provenance

Source

figshare, uploaded by author Zhitao Yuan.

Collection Method

Likely contains scripts and configurations from a research study fine-tuning LLMs on a corpus of psychological questionnaires.

Time Range

null

Freshness

Last updated 2026-04-24 17:29:21; freshness should be verified.

Geography

null