Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

RAAR: Retrieval Augmented Agentic Reasoning for Cross-Domain Misinformation Detection

Zhiwei Liu, Runteng Guo, Baojie Qu, Yuechen Jiang, Min Peng, Qianqian Xie, Sophia Ananiadou

TL;DR

RAAR introduces a retrieval-augmented agentic reasoning framework for cross-domain misinformation detection to address distribution shifts and the need for multi-perspective evidence. It retrieves source-domain data across semantics, sentiment, and writing style, constructs multi-agent reasoning paths with a verifier, and optimizes via supervised fine-tuning and reinforcement learning. Evaluated on AMTCele, PHEME, and COCO, RAAR-14B achieves state-of-the-art average F1 and outperforms other cross-domain methods and advanced LLM adaptations, demonstrating effective cross-domain knowledge transfer and multi-task capability. Ablation studies confirm the value of retrieval augmentation, multi-perspective reasoning, and RL in enhancing robustness. The work lays groundwork for scalable, multi-perspective misinformation detection and suggests future extensions to broader perspectives and modalities.

Abstract

Cross-domain misinformation detection is challenging, as misinformation arises across domains with substantial differences in knowledge and discourse. Existing methods often rely on single-perspective cues and struggle to generalize to challenging or underrepresented domains, while reasoning large language models (LLMs), though effective on complex tasks, are limited to same-distribution data. To address these gaps, we introduce RAAR, the first retrieval-augmented agentic reasoning framework for cross-domain misinformation detection. To enable cross-domain transfer beyond same-distribution assumptions, RAAR retrieves multi-perspective source-domain evidence aligned with each target sample's semantics, sentiment, and writing style. To overcome single-perspective modeling and missing systematic reasoning, RAAR constructs verifiable multi-step reasoning paths through specialized multi-agent collaboration, where perspective-specific agents produce complementary analyses and a summary agent integrates them under verifier guidance. RAAR further applies supervised fine-tuning and reinforcement learning to train a single multi-task verifier to enhance verification and reasoning capabilities. Based on RAAR, we trained the RAAR-8b and RAAR-14b models. Evaluation on three cross-domain misinformation detection tasks shows that RAAR substantially enhances the capabilities of the base models and outperforms other cross-domain methods, advanced LLMs, and LLM-based adaptation approaches. The project will be released at https://github.com/lzw108/RAAR.

RAAR: Retrieval Augmented Agentic Reasoning for Cross-Domain Misinformation Detection

TL;DR

RAAR introduces a retrieval-augmented agentic reasoning framework for cross-domain misinformation detection to address distribution shifts and the need for multi-perspective evidence. It retrieves source-domain data across semantics, sentiment, and writing style, constructs multi-agent reasoning paths with a verifier, and optimizes via supervised fine-tuning and reinforcement learning. Evaluated on AMTCele, PHEME, and COCO, RAAR-14B achieves state-of-the-art average F1 and outperforms other cross-domain methods and advanced LLM adaptations, demonstrating effective cross-domain knowledge transfer and multi-task capability. Ablation studies confirm the value of retrieval augmentation, multi-perspective reasoning, and RL in enhancing robustness. The work lays groundwork for scalable, multi-perspective misinformation detection and suggests future extensions to broader perspectives and modalities.

Abstract

Cross-domain misinformation detection is challenging, as misinformation arises across domains with substantial differences in knowledge and discourse. Existing methods often rely on single-perspective cues and struggle to generalize to challenging or underrepresented domains, while reasoning large language models (LLMs), though effective on complex tasks, are limited to same-distribution data. To address these gaps, we introduce RAAR, the first retrieval-augmented agentic reasoning framework for cross-domain misinformation detection. To enable cross-domain transfer beyond same-distribution assumptions, RAAR retrieves multi-perspective source-domain evidence aligned with each target sample's semantics, sentiment, and writing style. To overcome single-perspective modeling and missing systematic reasoning, RAAR constructs verifiable multi-step reasoning paths through specialized multi-agent collaboration, where perspective-specific agents produce complementary analyses and a summary agent integrates them under verifier guidance. RAAR further applies supervised fine-tuning and reinforcement learning to train a single multi-task verifier to enhance verification and reasoning capabilities. Based on RAAR, we trained the RAAR-8b and RAAR-14b models. Evaluation on three cross-domain misinformation detection tasks shows that RAAR substantially enhances the capabilities of the base models and outperforms other cross-domain methods, advanced LLMs, and LLM-based adaptation approaches. The project will be released at https://github.com/lzw108/RAAR.
Paper Structure (37 sections, 13 equations, 2 figures, 6 tables)

This paper contains 37 sections, 13 equations, 2 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Method
  3. Task Formulation
  4. Stage 1: Retrieval Augmented Data Building
  5. Stage 2: Multi-agent Collaborated Reasoning Path Building
  6. Stage 3: Model Optimization
  7. Retrieval Augmented SFT
  8. RL
  9. Experiments
  10. Datasets
  11. Baselines
  12. Settings and Evaluation
  13. Main results
  14. Ablation study
  15. Error Analysis
  16. ...and 22 more sections

Figures (2)

  • Figure 1: The architecture of RAAR. ① Retrieval Augmented Data Building: Retrieve source-domain samples similar to target-domain data in semantics, sentiment, and style for multi-perspective analysis. ② Multi-agent Collaborated Reasoning Path Building: Use multi-agent collaboration and a verifier to construct coherent, multi-perspective reasoning paths. ③ Model Optimization: Fine-tune the model with SFT and RL to enhance cross-domain verification and reasoning.
  • Figure :