Related papers: On the probability-quality paradox in language gen…

We propose Composition Sampling, a simple but effective method to generate diverse outputs for conditional generation of higher quality compared to previous stochastic decoding strategies. It builds on recently proposed plan-based neural…

People tend to distribute information evenly in language production for better and clearer communication. In this study, we compared essays written by second language learners with various native language (L1) backgrounds to investigate how…

Large Language Models have been demonstrating broadly satisfactory generative abilities for users, which seems to be due to the intensive use of human feedback that refines responses. Nevertheless, suggestibility inherited via human…

Neural text generation models are often autoregressive language models or seq2seq models. These models generate text by sampling words sequentially, with each word conditioned on the previous word, and are state-of-the-art for several…

The spread of fake news has emerged as a critical challenge, undermining trust and posing threats to society. In the era of Large Language Models (LLMs), the capability to generate believable fake content has intensified these concerns. In…

We conduct a quantitative analysis contrasting human-written English news text with comparable large language model (LLM) output from six different LLMs that cover three different families and four sizes in total. Our analysis spans several…

Natural language generation (NLG) systems are computer software systems that produce texts in English and other human languages, often from non-linguistic input data. NLG systems, like most AI systems, need substantial amounts of knowledge.…

While generative methods have progressed rapidly in recent years, generating expressive prosody for an utterance remains a challenging task in text-to-speech synthesis. This is particularly true for systems that model prosody explicitly…

Recent language models generate false but plausible-sounding text with surprising frequency. Such "hallucinations" are an obstacle to the usability of language-based AI systems and can harm people who rely upon their outputs. This work…

Recent advances in large language models (LLMs) have brought public and scholarly attention to their potential in generating low-quality information. While widely acknowledged as a risk, low-quality information remains a vaguely defined…

Adversarial examples in NLP are receiving increasing research attention. One line of investigation is the generation of word-level adversarial examples against fine-tuned Transformer models that preserve naturalness and grammaticality.…

Large Language Models (LLMs) have demonstrated remarkable capabilities across various applications, fundamentally reshaping the landscape of natural language processing (NLP) research. However, recent evaluation frameworks often rely on the…

Emotional language generation is one of the keys to human-like artificial intelligence. Humans use different type of emotions depending on the situation of the conversation. Emotions also play an important role in mediating the engagement…

Human evaluation is often considered to be the gold standard method of evaluating a Natural Language Generation system. However, whilst its importance is accepted by the community at large, the quality of its execution is often brought into…

Synthetic data becomes crucial for large language model training, but its effectiveness is highly inconsistent. We provide an information-theoretic account of this inconsistency: synthetic data improves a model only when the…

Despite their ubiquity in language generation, it remains unknown why truncation sampling heuristics like nucleus sampling are so effective. We provide a theoretical explanation for the effectiveness of the truncation sampling by proving…

The increasing reliance on large language models (LLMs) in academic writing has led to a rise in plagiarism. Existing AI-generated text classifiers have limited accuracy and often produce false positives. We propose a novel approach using…

The natural language generation (NLG) component of a spoken dialogue system (SDS) usually needs a substantial amount of handcrafting or a well-labeled dataset to be trained on. These limitations add significantly to development costs and…

Effective generation of novel hypotheses is instrumental to scientific progress. So far, researchers have been the main powerhouse behind hypothesis generation by painstaking data analysis and thinking (also known as the Eureka moment). In…

Large Language Models (LLMs) are now capable of generating highly fluent, human-like text. They enable many applications, but also raise concerns such as large scale spam, phishing, or academic misuse. While much work has focused on…