The rise in malicious usage of large language models, such as fake content creation and
academic plagiarism, has motivated the development of approaches that identify AI …

This paper presents a question answering (QA) system that will enable workers from the
manufacturing industry to'hands-free'request information. This kind of systems, that are …

Current approaches in paraphrase generation and detection heavily rely on a single general
similarity score, ignoring the intricate linguistic properties of language. This paper introduces …

While large pretrained language models (PLMs) demonstrate incredible fluency and
performance on many natural language tasks, recent work has shown that well-performing …

Semantic consistency of a language model is broadly defined as the model's ability to
produce semantically-equivalent outputs, given semantically-equivalent inputs. We address …

Paraphrase generation is a fundamental natural language processing (NLP) task that refers
to the process of generating a well‐formed and coherent output sentence that exhibits both …

We present MCPG: a simple and effectiveapproach for controllable unsupervised
paraphrase generation, which is also flexible toadapt to specific domains without extra …

Most existing text generation models follow the sequence-to-sequence paradigm.
Generative Grammar suggests that humans generate natural language texts by learning …

This paper describes our system developed for SemEval-2024 Task 8," Multigenerator,
Multidomain, and Multilingual Black-Box Machine-Generated Text Detection." Machine …

While fine-tuned language models perform well on many tasks, they were also shown to rely
on superficial surface features such as lexical overlap. Excessive utilization of such …