相关论文: ValiText -- a unified validation framework for com…

In natural language processing (NLP), state-of-the-art (SOTA) semi-supervised learning (SSL) frameworks have shown great performance on deep pre-trained language models such as BERT, and are expected to significantly reduce the demand for…

The ease of spreading false information online enables individuals with malicious intent to manipulate public opinion and destabilize social stability. Recently, fake news detection based on evidence retrieval has gained popularity in an…

Entity resolution is a widely studied problem with several proposals to match records across relations. Matching textual content is a widespread task in many applications, such as question answering and search. While recent methods achieve…

As intelligent systems become more autonomous, the scientific community focuses on creating decision-making mechanisms that include ethical and moral considerations, unlike traditional utility-maximisation models. To achieve this, a key…

Text and formulas constitute the core informational components of many documents. Accurately and efficiently recognizing both is crucial for developing robust and generalizable document parsing systems. Recently, vision-language models…

Many applications of computational social science aim to infer causal conclusions from non-experimental data. Such observational data often contains confounders, variables that influence both potential causes and potential effects.…

A fundamental limitation of Text-to-Code is that no guarantee can be obtained about the correctness of the generated code. Therefore, to ensure its correctness, the generated code still has to be reviewed, tested, and maintained by…

The combination of argumentation and probability paves the way to new accounts of qualitative and quantitative uncertainty, thereby offering new theoretical and applicative opportunities. Due to a variety of interests, probabilistic…

We address a fundamental challenge in Natural Language Generation (NLG) model evaluation -- the design and evaluation of evaluation metrics. Recognizing the limitations of existing automatic metrics and noises from how current human…

Recent deep research systems have improved the ability of large language models to produce long, grounded reports through iterative retrieval and reasoning. However, most text-centered systems rely mainly on textual evidence, while…

Recent LLMs are able to generate high-quality multilingual texts, indistinguishable for humans from authentic human-written ones. Research in machine-generated text detection is however mostly focused on the English language and longer…

In various provers and deductive verification tools, logical transformations are used extensively in order to reduce a proof task into a number of simpler tasks. Logical transformations are often part of the trusted base of such tools. In…

Cross-validation is one of the most popular model selection methods in statistics and machine learning. Despite its wide applicability, traditional cross validation methods tend to select overfitting models, due to the ignorance of the…

Detecting text generated by large language models (LLMs) is crucial but challenging. Existing detectors depend on impractical assumptions, such as white-box settings, or solely rely on text-level features, leading to imprecise detection…

This paper presents a formal theory of verification and validation (V&V) within systems engineering, grounded in the axiom that V&V are fundamentally knowledge-building activities. Using dynamic epistemic modal logic, we develop precise…

Social scientists are increasingly turning to unstructured datasets to unlock new empirical insights, e.g., estimating descriptive statistics of or causal effects on quantitative measures derived from text, audio, or video data. In many…

The output of an automated theorem prover is usually presented by using a text format, they are often too heavy to be understood. In model checking setting, it would be helpful if one can observe the structure of models and the verification…

Medical text generation aims to assist with administrative work and highlight salient information to support decision-making. To reflect the specific requirements of medical text, in this paper, we propose a set of metrics to evaluate the…

Trust is fundamental to effective visual data communication between the visualization designer and the reader. Although personal experience and preference influence readers' trust in visualizations, visualization designers can leverage…

We present a new scientific document similarity model based on matching fine-grained aspects of texts. To train our model, we exploit a naturally-occurring source of supervision: sentences in the full-text of papers that cite multiple…