相关论文: Article Reranking by Memory-Enhanced Key Sentence …

While machine-generated texts (MGTs) offer great convenience, they also pose risks such as disinformation and phishing, highlighting the need for reliable detection. Metric-based methods, which extract statistically distinguishable features…

Fake news on social media is a widespread and serious problem in today's society. Existing fake news detection methods focus on finding clues from Long text content, such as original news articles and user comments. This paper solves the…

Grounded claim factuality checking is important for large language model (LLM) applications such as retrieval-augmented generation, as it helps users assess the correctness of generated outputs. Existing metrics using entailment classifiers…

Misinformation detection models often rely on superficial cues (i.e., \emph{shortcuts}) that correlate with misinformation in training data but fail to generalize to the diverse and evolving nature of real-world misinformation. This issue…

Political misinformation poses significant challenges to democratic processes, shaping public opinion and trust in media. Manual fact-checking methods face issues of scalability and annotator bias, while machine learning models require…

Inference tasks such as answer sentence selection (AS2) or fact verification are typically solved by fine-tuning transformer-based models as individual sentence-pair classifiers. Recent studies show that these tasks benefit from modeling…

Automated Fact-Checking (AFC) relies on claim extraction as a first step, yet existing methods largely overlook the multimodal nature of today's misinformation. Social media posts often combine short, informal text with images such as…

Pairing a lexical retriever with a neural re-ranking model has set state-of-the-art performance on large-scale information retrieval datasets. This pipeline covers scenarios like question answering or navigational queries, however, for…

Despite recent concerns about undesirable behaviors generated by large language models (LLMs), including non-factual, biased, and hateful language, we find LLMs are inherent multi-task language checkers based on their latent representations…

Machine-translated text plays an important role in modern life by smoothing communication from various communities using different languages. However, unnatural translation may lead to misunderstanding, a detector is thus needed to avoid…

Automatically generated fake restaurant reviews are a threat to online review systems. Recent research has shown that users have difficulties in detecting machine-generated fake reviews hiding among real restaurant reviews. The method used…

In clinical research and clinical decision-making, it is important to know if a study changes or only supports the current standards of care for specific disease management. We define such a change as transformative and a support as…

SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval is approached as a Learning-to-Rank task using a bi-encoder model fine-tuned from a pre-trained transformer optimized for sentence similarity. Training used…

We present ClaimRank, an online system for detecting check-worthy claims. While originally trained on political debates, the system can work for any kind of text, e.g., interviews or regular news articles. Its aim is to facilitate manual…

Text reranking models are a crucial component in modern systems like Retrieval-Augmented Generation, tasked with selecting the most relevant documents prior to generation. However, current Large Language Models (LLMs) powered rerankers…

Recent Long-Context Language Models (LCLMs) can process hundreds of thousands of tokens in a single prompt, enabling new opportunities for knowledge-intensive multi-hop reasoning by integrating large sets of retrieved documents or, in some…

Factual inconsistency with source documents in automatically generated summaries can lead to misinformation or pose risks. Existing factual consistency (FC) metrics are constrained by their performance, efficiency, and explainability.…

The goal of text ranking is to generate an ordered list of texts retrieved from a corpus in response to a query. Although the most common formulation of text ranking is search, instances of the task can also be found in many natural…

Large language models (LLMs) have raised hopes for automated end-to-end fact-checking, but prior studies report mixed results. As mainstream chatbots increasingly ship with reasoning capabilities and web search tools -- and millions of…

Deep neural networks have achieved significant improvements in information retrieval (IR). However, most existing models are computational costly and can not efficiently scale to long documents. This paper proposes a novel End-to-End neural…