Are Rationales Necessary and Sufficient? Tuning LLMs for Explainable Misinformation Detection

2026-05-18

AI Summary

Existing explainable misinformation detection methods often produce rationales that lack necessity or sufficiency. To address this limitation, this work proposes the LONSREX framework, which leverages multiple large language models to collaboratively generate predictions and corresponding reasoning chains. High-quality training data are constructed through a dual filtering mechanism that evaluates both factual correctness and the contribution of each reasoning step to the final prediction. The framework further introduces quantitative metrics to assess the necessity and sufficiency of individual reasoning steps, enabling precise extraction of faithful explanations. A dedicated large language model fine-tuned on this curated dataset achieves substantially improved detection performance and explanation quality, outperforming baseline approaches that rely solely on label correctness.

Abstract

The rapid spread of misinformation on social media platforms has become a formidable challenge. To mitigate its proliferation, Misinformation Detection (MD) has emerged as a critical research topic. Traditional MD approaches based on small models typically perform binary classification through a black-box process. Recently, the rise of Large Language Models (LLMs) has enabled explainable MD, where models generate rationales that explain their decisions, thereby enhancing transparency. Existing explainable MD methods primarily focus on crafting sophisticated prompts to elicit rationales from off-the-shelf LLMs. In this work, we propose a pipeline to fine-tune a dedicated LLM specifically for explainable MD. Our pipeline begins by collecting large-scale fact-checked articles, and then uses multiple strong LLMs to produce veracity predictions and rationales. To ensure high-quality training data, we leverage a filtering strategy that selects only the correct instances for fine-tuning. While this pipeline is intuitive and prevalent, our experiments reveal that naive filtering based solely on label correctness is insufficient in practice and suffers from two critical limitations: (1) Coarse-grained labels cause insufficient rationales: Rationales filtered solely based on binary labels are insufficient to adequately support their decisions; (2) Over-verification behavior causes unnecessary rationales: Stronger LLMs tend to exhibit over-verification behavior, producing excessively verbose and unnecessary rationales. To address these issues, we introduce LONSREX, a novel data synthesis pipeline to Locate Necessary and Sufficient Rationales for Explainable MD. Specifically, we propose a metric that quantifies the contribution of each verification step to the final prediction, thereby evaluating its necessity and sufficiency. Experimental results demonstrate the effectiveness of LONSREX.

Problem

• Explainable Misinformation Detection
• Rationales
• Large Language Models
• Necessity and Sufficiency
• Data Filtering

Innovation

• Explainable Misinformation Detection
• Large Language Models
• Rationale Filtering
• Necessity and Sufficiency
• Data Synthesis