#social-science News & Analysis

6 articles tagged with #social-science. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

6 articles

AINeutralarXiv – CS AI · Mar 176/10

🧠

InterveneBench: Benchmarking LLMs for Intervention Reasoning and Causal Study Design in Real Social Systems

Researchers introduced InterveneBench, a new benchmark comprising 744 peer-reviewed studies to evaluate large language models' ability to reason about policy interventions and causal inference in social science contexts. Current state-of-the-art LLMs struggle with this type of reasoning, prompting the development of STRIDES, a multi-agent framework that significantly improves performance on these tasks.

AINeutralarXiv – CS AI · Mar 55/10

🧠

From We to Me: Theory Informed Narrative Shift with Abductive Reasoning

Researchers developed a neurosymbolic approach using social science theory and abductive reasoning to help Large Language Models transform text narratives while preserving core messages. The method achieved 55.88% improvement over baseline performance with GPT-4o when shifting between collectivistic and individualistic narrative frameworks.

🧠 GPT-4🧠 Llama🧠 Grok

AIBullisharXiv – CS AI · Mar 36/104

🧠

Augmenting Research Ideation with Data: An Empirical Investigation in Social Science

Researchers developed a framework that improves AI-generated research ideas by incorporating relevant data during the ideation process. The approach increased idea feasibility by 20% and overall quality by 7%, with human studies confirming that data-augmented AI assistance helps researchers generate higher-quality ideas.

AIBullishOpenAI News · Feb 136/107

🧠

Scaling social science research

OpenAI has released GABRIEL, an open-source toolkit that leverages GPT to convert qualitative text and images into quantitative data for social science research. This tool enables researchers to analyze large-scale qualitative data more efficiently and systematically.

AINeutralOpenAI News · Feb 196/105

🧠

AI safety needs social scientists

OpenAI researchers published a paper arguing that AI safety and alignment research requires social scientists to address human psychology, rationality, and biases. The company plans to hire social scientists full-time to collaborate with machine learning researchers on ensuring AI systems properly align with human values.

AIBullishMIT News – AI · Dec 14/104

🧠

Exploring how AI will shape the future of work

PhD student Benjamin Manning explores AI's transformative role in the future of work, particularly its potential to accelerate social scientific discovery. The article focuses on how AI will reshape work dynamics and research methodologies.