Year: 2026
Type: conference-paper
Abstract: Large language models (LLMs) are increasingly expected to support pluralistic alignment, representing diverse human perspectives.However, current methods often induce motivated reasoning: LLMs tend to hallucinate "convenient" facts to forcefully justify a requested stance.To address this, we propose Value-Graph-Consistent Chain-of-Thought (VGC-CoT), a neuro-symbolic framework that enables steerable pluralism without distorting objective reality.We enforce a strict distinction: facts should be shared, while value trade-offs may diverge.Our approach models reasoning as a directed traversal over a multi-perspective graph comprising a fixed factual layer and perspective-specific value layers.By projecting generated CoT paths onto this structure, we align the model with target values while constraining it to a shared factual backbone.Experiments show that our method reduces factual hallucinations by 3× and improves crossperspective consistency by 25% compared to standard steerable baselines, paving the way for trustworthy pluralistic AI.
Authors: Gejian Zhao, Hanzhou Wu, Xinpeng Zhang
Institution: Shanghai University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166820378