AI RESEARCH

Causal methods for LLM development and evaluation

arXiv CS.LG

ArXi:2605.25998v1 Announce Type: new Large language model (LLM) development is currently driven by large-scale empirical iteration over data mixtures, reward models, routing strategies, and evaluation pipelines. Here, we argue that many central questions in LLM development and evaluation are inherently causal: What is the effect of adding a data domain during pre