相关论文: Unsupervised Question Answering for Fact-Checking

Automatic detection of speaker confidence is critical for adaptive computing but remains constrained by limited labelled data and the subjectivity of paralinguistic annotations. This paper proposes a semi-supervised hybrid framework that…

Label error is a ubiquitous problem in annotated data. Large amounts of label error substantially degrades the quality of deep learning models. Existing methods to tackle the label error problem largely focus on the classification task, and…

Deep generative models trained with large amounts of unlabelled data have proven to be powerful within the domain of unsupervised learning. Many real life data sets contain a small amount of labelled data points, that are typically…

Large language models (LLMs) excel at natural language understanding and generation but remain vulnerable to factual errors, limiting their reliability in knowledge-intensive tasks. While decoding-time strategies provide a promising…

To improve performance in visual feature representation from photos or videos for practical applications, we generally require large-scale human-annotated labeled data while training deep neural networks. However, the cost of gathering and…

Capturing the interesting components of an image is a key aspect of image understanding. When a speaker annotates an image, selecting labels that are informative greatly depends on the prior knowledge of a prospective listener. Motivated by…

Unsupervised learning has always been appealing to machine learning researchers and practitioners, allowing them to avoid an expensive and complicated process of labeling the data. However, unsupervised learning of complex data is…

Masked language modeling (MLM) plays a key role in pretraining large language models. But the MLM objective is often dominated by high-frequency words that are sub-optimal for learning factual knowledge. In this work, we propose an approach…

In this paper, we explore the problem of Claim Extraction using one-to-many text generation methods, comparing LLMs, small summarization models finetuned for the task, and a previous NER-centric baseline QACG. As the current publications on…

This paper presents our system for SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval. In an era where misinformation spreads rapidly, effective fact-checking is increasingly critical. We introduce TriAligner, a…

Uncertainty calibration is essential for the safe deployment of large language models (LLMs), particularly when users rely on verbalized confidence estimates. While prior work has focused on classifiers or short-form generation, confidence…

Many important classification problems, such as object classification, speech recognition, and machine translation, have been tackled by the supervised learning paradigm in the past, where training corpora of parallel input-output pairs are…

The current Neuro-Symbolic (NeSy) Learning paradigm suffers from an over-reliance on labeled data, so if we completely disregard labels, it leads to less symbol information, a larger solution space, and more shortcuts-issues that current…

This paper introduces the task of factual error correction: performing edits to a claim so that the generated rewrite is better supported by evidence. This extends the well-studied task of fact verification by providing a mechanism to…

This paper introduces the task of factual error correction: performing edits to a claim so that the generated rewrite is better supported by evidence. This extends the well-studied task of fact verification by providing a mechanism to…

The Fact Extraction and VERification (FEVER) shared task was launched to support the development of systems able to verify claims by extracting supporting or refuting facts from raw text. The shared task organizers provide a large-scale…

Fact-checking systems have become important tools to verify fake and misguiding news. These systems become more trustworthy when human-readable explanations accompany the veracity labels. However, manual collection of such explanations is…

The remarkable success of today's deep neural networks highly depends on a massive number of correctly labeled data. However, it is rather costly to obtain high-quality human-labeled data, leading to the active research area of training…

In recent years, the amount of Cyber Security data generated in the form of unstructured texts, for example, social media resources, blogs, articles, and so on has exceptionally increased. Named Entity Recognition (NER) is an initial step…

Automatic fact verification systems increasingly rely on large language models (LLMs). We investigate how parametric knowledge biases in these models affect fact-checking outcomes of the HerO system (baseline for FEVER-25). We examine how…