AI RESEARCH
Conditional Hypothesis Generation for LLM-Based Text Analysis with Researcher-Specified Covariates
arXiv CS.CL
•
ArXi:2606.03029v1 Announce Type: new A core goal of computational social science is to discover interpretable differences in how language varies across outcomes of interest, such as political affiliation or instructional quality. Recent LLM-based hypothesis generation methods describe such differences in natural language, but select for globally discriminative patterns without accounting for covariates that shape the data based on researchers' domain knowledge. When covariates are ignored, selected patterns can reflect confounds rather than differences of substantive interest. We.