Related papers: How much do language models copy from their traini…
When we speak, write or listen, we continuously make predictions based on our knowledge of a language's grammar. Remarkably, children acquire this grammatical knowledge within just a few years, enabling them to understand and generalise to…
Transformer-based pretrained models like BERT, GPT-2 and T5 have been finetuned for a large number of natural language processing (NLP) tasks, and have been shown to be very effective. However, while finetuning, what changes across layers…
Text generation from semantic graphs is traditionally performed with deterministic methods, which generate a unique description given an input graph. However, the generation problem admits a range of acceptable textual outputs, exhibiting…
Recent advances in large pre-trained language models have demonstrated strong results in generating natural languages and significantly improved performances for many natural language generation (NLG) applications such as machine…
Our ability to efficiently and accurately evaluate the quality of machine translation systems has been outrun by the effectiveness of current language models--which limits the potential for further improving these models on more challenging…
Recent studies have adopted pre-trained language models, such as CodeT5 and CodeGPT, for automated program generation tasks like code generation, repair, and translation. Numerous language model-based approaches have been proposed and…
The advent of instruction-tuned language models that convincingly mimic human writing poses a significant risk of abuse. However, such abuse may be counteracted with the ability to detect whether a piece of text was composed by a language…
Algorithms for text-generation in dialogue can be misguided. For example, in task-oriented settings, reinforcement learning that optimizes only task-success can lead to abysmal lexical diversity. We hypothesize this is due to poor…
Large language model (LLM)-based evaluation pipelines have demonstrated their capability to robustly evaluate machine-generated text. Extending this methodology to assess human-written text could significantly benefit educational settings…
Sensitivity of deep-neural models to input noise is known to be a challenging problem. In NLP, model performance often deteriorates with naturally occurring noise, such as spelling errors. To mitigate this issue, models may leverage…
Recently, generative AIs like ChatGPT have become available to the wide public. These tools can for instance be used by students to generate essays or whole theses. But how does a teacher know whether a text is written by a student or an…
Modern neural language models (LMs) are powerful tools for modeling human sentence production and comprehension, and their internal representations are remarkably well-aligned with representations of language in the human brain. But to…
Large language models generate judgments that resemble those of humans. Yet the extent to which these models align with human judgments in interpreting figurative and socially grounded language remains uncertain. To investigate this, human…
Text generative models (TGMs) excel in producing text that matches the style of human language reasonably well. Such TGMs can be misused by adversaries, e.g., by automatically generating fake news and fake product reviews that can look…
In this paper, we study recent neural generative models for text generation related to variational autoencoders. Previous works have employed various techniques to control the prior distribution of the latent codes in these models, which is…
Lack of repeatability and generalisability are two significant threats to continuing scientific development in Natural Language Processing. Language models and learning methods are so complex that scientific conference papers no longer…
The rapid proliferation of Large Language Models has significantly increased the difficulty of distinguishing between human-written and AI generated texts, raising critical issues across academic, editorial, and social domains. This paper…
Recent neural sequence-to-sequence models with a copy mechanism have achieved remarkable progress in various text generation tasks. These models addressed out-of-vocabulary problems and facilitated the generation of rare words. However, the…
Machine-translated data is widely used in multilingual NLP, particularly when native text is scarce. However, translated text differs systematically from native text. This phenomenon is known as translationese, and it reflects both traces…
Large language models exhibit impressive cross-lingual capabilities. However, prior work analyzes this phenomenon through isolated factors and at sparse points during training, limiting our understanding of how cross-lingual generalization…