2 papers
cs.CY2026
InterveneBench: Benchmarking LLMs for Intervention Reasoning and Causal Study Design in Real Social Systems
Shaojie Shi, Zhengyu Shi, Lingran Zheng +15
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…
cs.CL2026
On the Robustness of Knowledge Editing for Detoxification
Ming Dong, Shiyi Tang, Ziyan Peng +2
Knowledge-Editing-based (KE-based) detoxification has emerged as a promising approach for mitigating harmful behaviours in Large Language Models. Existing evaluations, however, lar…