Search papers, labs, and topics across Lattice.
Fudan University 2 Shanghai Innovation Institute sjshi24@m.fudan.edu.cn zhengyushi96@gmail.com lingran414@gmail.com Equal Contributions.Corresponding author. Abstract Causal inference in social science relies on end-to-end, intervention-centered research-design reasoning grounded in real-world policy interventions, but current benchmarks fail to evaluate this capability of large language models (LLMs). We present InterveneBench, a benchmark designed to assess such reasoning in realistic social settings. Each instance in InterveneBench is derived from an empirical social science study and requires models to reason about policy interventions and identification assumptions without access to predefined causal graphs or structural equations. InterveneBench comprises 744 peer-reviewed studies across diverse policy domains. Experimental results show that state-of-the-art LLMs struggle under this setting. To address this limitation, we further propose a multi-agent framework, STRIDES. It achieves significant performance improvements over state-of-the-art reasoning models. Our code and data are available at https://github.com/Sii-yuning/STRIDES. InterveneBench: Benchmarking LLMs for Intervention Reasoning and Causal Study Design in Real Social Systems Shaojie Shi
1
0
3
10
LLMs can now predict other LLMs' performance with 14% higher accuracy, even when only seeing one or two data points, by blending statistical priors with reasoning.
