Fact-checking explanations adapt to readers personal preferences
Same Verdict, Different Readers: Personalizing Fact-Checking Explanations from Relative Preferences
Computation and Language
Summary
Fact-checking websites explain why a claim is true or false, but one explanation may not suit every reader. To fix this, the authors created a method that rewrites explanations to fit people’s individual tastes while keeping the facts accurate. They use computer simulations to learn what kinds of explanations different readers prefer without needing people to write example explanations. Their approach outperforms larger general-purpose AI systems in matching personal preferences while staying truthful.
What this means in practice
- •For news platform developers: Customize fact-check explanations on news sites to match diverse reader preferences while preserving factual accuracy.
- •For chatbot builders: Design chatbots that tailor fact-checking explanations to user preferences inferred from interaction patterns.
Authors
Haokun Wen, Xuemeng Song, Mong-Li Lee, Wynne Hsu
Abstract
Fact-checking explanations help Web users understand why a claim receives its verdict, yet the same explanation may not satisfy readers with different backgrounds and preferences. We formulate Faithful Personalized Fact-Checking Explanation Rewriting, which adapts an existing explanation to individual readers while preserving factual fidelity. Rather than relying on reader-written reference explanations, we learn personalized rewriting from the relative preferences of LLM-simulated readers. However, this presents two challenges: distinguishing persona-specific preferences from general explanation quality and learning beyond a limited set of predefined explanation styles. To address these challenges, we propose Personalized Explanation Rewriting via Preference Learning (PERPL), a framework consisting of two components. Simulated Preference Construction derives persona-specific supervision from simulated reader preferences through cross-persona reciprocal pairing. Progressive Preference Learning first trains a lightweight rewriter on the constructed supervision and then refines it through exploration-guided preference optimization, enabling it to discover preferred explanations beyond the predefined styles. Extensive experiments demonstrate that PERPL outperforms much larger general-purpose LLMs in personalized preference alignment while maintaining high factual fidelity.