TruthSplit: Operationalizing Conditional Validity in Arguments Through Multi-Perspective Reasoning
2026-06-08 • Computation and Language
Computation and Language
AI summaryⓘ
The authors created TruthSplit, a tool that helps analyze arguments by showing how the same statement can lead to different conclusions based on different worldviews. Unlike other tools that just look at the argument itself, this system considers the background values and beliefs that influence interpretation. It uses language processing techniques to check if arguments make sense logically and within specific worldviews, then shows where perspectives differ or clash. The system also provides interactive visuals to help users explore these differences.
argument analysisnatural language inferenceworldviewconditional validitylarge language modellogical consistencynormative consistencyinteractive visualizationstructured worldview profilesperspective-specific interpretation
Authors
Benjamin Stieger, Maximilian Terberger, Thomas Huber, Christina Niklaus
Abstract
We present TruthSplit, an interactive system for multi-perspective argument analysis. Existing argumentation tools typically analyze properties of the argument itself, such as structure, quality, stance, or persuasiveness, while leaving perspective-specific background knowledge implicit. TruthSplit addresses this gap by supporting an exploratory analysis of how the same claim can lead to different conclusions when interpreted through worldview-specific values, assumptions, and conceptual definitions. We refer to this perspective-dependent analysis as conditional validity. Given an input argumentative text, TruthSplit extracts claims and premises, applies a three-layer natural language inference (NLI) approach to assess both logical and worldview-specific normative consistency, and conditions large language model (LLM) reasoning on structured worldview profiles that encode core values and decision principles. The system then generates perspective-specific interpretations, identifies value conflicts and assumption gaps, and visualizes divergence through interactive analytical interfaces.