AI-assisted teams outperform AI-led teams but not human-only teams in assessing research reproducibility in quantitative social science
- Occurred
- May 29, 2026
- Published
- May 29, 2026
- Source
- CSER Cambridge
Summary
Abstract Large Language Models (LLMs) such as ChatGPT are transforming how scientists conduct and validate research, offering promise as tools to improve scientific reproducibility. However, computational reproducibility and error detection remain expensive and labor-intensive. We experimentally test how collaboration between researchers and LLM assistants influences the reproduction of quantitative social science findings across different levels […] The post AI-assisted teams outperform AI-led teams but not human-only teams in assessing research reproducibility in quantitative social science first appeared on CSER.
Tags
- Publication
Classification
Rationale: Research paper analyzing LLM performance in scientific reproducibility without concrete incident or harm.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8