The rapid spread of online misinformation poses a serious threat to public trust and social stability, making automatic fake news detection increasingly critical. In this work, we propose a novel retrieval-augmented fake news detection framework, Triple-R (Rewriting, Retrieval, and iterative Refinement), which emphasizes optimizing the retrieval query. Unlike prior retrieval-augmented methods that adapt either the retriever or the verification module, often overlooking the gap between news text and the evidence needed for verification, our approach focuses on adapting the search query to retrieve the most relevant evidence. Specifically, we employ a small language model as a trainable query rewriter, optimized via reinforcement learning with feedback from a frozen LLM-based fake news detector, to transform the original news text into effective retrieval queries. To further enhance evidence relevance, we introduce an iterative query refinement mechanism, which progressively updates rewritten queries based on previously retrieved results. Finally, the original news text and the evidence retrieved through refined queries are integrated for verification. Experiments on two real-world datasets demonstrate consistent improvements, validating the effectiveness of our approach.

Aspect-based sentiment analysis is a popular task in Natural Language Processing (NLP). Many methods utilize attention mechanisms and graph neural networks on dependency trees to identify the most relevant opinion words for aspects. However, improvements are limited due to the presence of rare words in small datasets and the inability to guarantee that each token will have a high probability of interacting with aspects. To address these challenges, we propose a Prior Knowledge Augmentation Network (PKAN) model that incorporates rich semantic information from knowledge graphs, syntactic structures, and prior probabilistic position embeddings. Specifically, to better comprehend semantic information, we design a knowledge augmentation module that constructs an adjacency matrix based on knowledge graphs, dependency trees and dataset co-occurrences. Additionally, to capture opinion words more comprehensively, we propose a probabilistic relative position embedding strategy. This strategy assumes that the semantic distribution of tokens at varying distances from the central word obeys a gaussian distribution and constrains the distance between words and aspects within one standard deviation. Experimental results on five public datasets validate the effectiveness of our model.