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

arXiv: https://arxiv.org/abs/2605.19285 · HTML: https://mlsanity.com/paper/2605.19285/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 50 references that are in the map.
- First posted on arXiv 19 May 2026.

## Builds on (most cited first, 30 of 30)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [LIMO: Less is More for Reasoning](https://mlsanity.com/paper/2502.03387/) (2025)
- [Large Language Models Are Reasoning Teachers](https://mlsanity.com/paper/2212.10071/) (2022)
- [Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networks](https://mlsanity.com/paper/2001.06362/) (2020)
- [The science of fake news](https://mlsanity.com/paper/2307.07903/) (2023)
- [Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection](https://mlsanity.com/paper/2309.12247/) (2023)
- [The Best Instruction-Tuning Data are Those That Fit](https://mlsanity.com/paper/2502.04194/) (2025)
- [Explainable Fake News Detection With Large Language Model via Defense Among Competing Wisdom](https://mlsanity.com/paper/2405.03371/) (2024)
- [Disentangling Memory and Reasoning Ability in Large Language Models](https://mlsanity.com/paper/2411.13504/) (2024)
- [Deconstructing Long Chain-of-Thought: A Structured Reasoning Optimization Framework for Long CoT Distillation](https://mlsanity.com/paper/2503.16385/) (2025)
- [FakeSV: A Multimodal Benchmark with Rich Social Context for Fake News Detection on Short Video Platforms](https://mlsanity.com/paper/2211.10973/) (2022)
- [DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection](https://mlsanity.com/paper/2402.10426/) (2024)
- [Evidence-Driven Retrieval Augmented Response Generation for Online Misinformation](https://mlsanity.com/paper/2403.14952/) (2024)
- [The Truth Becomes Clearer Through Debate! Multi-Agent Systems with Large Language Models Unmask Fake News](https://mlsanity.com/paper/2505.08532/) (2025)
- [Instance-adaptive Zero-shot Chain-of-Thought Prompting](https://mlsanity.com/paper/2409.20441/) (2024)
- [Let Silence Speak: Enhancing Fake News Detection with Generated Comments from Large Language Models](https://mlsanity.com/paper/2405.16631/) (2024)
- [Skip-Thinking: Chunk-wise Chain-of-Thought Distillation Enable Smaller Language Models to Reason Better and Faster](https://mlsanity.com/paper/2505.18642/) (2025)
- [RAEmoLLM: Retrieval Augmented LLMs for Cross-Domain Misinformation Detection Using In-Context Learning Based on Emotional Information](https://mlsanity.com/paper/2406.11093/) (2024)
- [A Coarse-to-fine Cascaded Evidence-Distillation Neural Network for Explainable Fake News Detection](https://mlsanity.com/paper/2209.14642/) (2022)
- [Learning from Diverse Reasoning Paths with Routing and Collaboration](https://mlsanity.com/paper/2508.16861/) (2025)
- [Why Misinformation is Created? Detecting them by Integrating Intent Features](https://mlsanity.com/paper/2407.19196/) (2024)
- [PCoT: Persuasion-Augmented Chain of Thought for Detecting Fake News and Social Media Disinformation](https://mlsanity.com/paper/2506.06842/) (2025)
- [Where Did This Sentence Come From? Tracing Provenance in LLM Reasoning Distillation](https://mlsanity.com/paper/2512.20908/) (2025)
- [Collaboration and Controversy Among Experts: Rumor Early Detection by Tuning a Comment Generator](https://mlsanity.com/paper/2504.04076/) (2025)
- [Robust Misinformation Detection by Visiting Potential Commonsense Conflict](https://mlsanity.com/paper/2504.21604/) (2025)
- [A Dynamic Knowledge Update-Driven Model with Large Language Models for Fake News Detection](https://mlsanity.com/paper/2509.11687/) (2025)
- [Rethinking Toxicity Evaluation in Large Language Models: A Multi-Label Perspective](https://mlsanity.com/paper/2510.15007/) (2025)

## Built on by (most cited first, 1 of 1)

- [Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability](https://mlsanity.com/paper/2607.10402/) (2026)

## Abstract (arXiv)

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.