Reasoning Boosts Opinion Alignment in LLMs

ArXi:2603.01214v2 Announce Type: replace-cross Opinion modeling aims to capture individual or group political preferences, enabling applications such as digital cracies, where models could help shape fairer and popular policies. Given their versatility, strong generalization capabilities, and nstrated success across diverse text-to-text applications, large language models (LLMs) are natural candidates for this task. However, due to their statistical nature and limited causal understanding, they tend to produce biased opinions when prompted naively.