Related papers: Exploring Cross-lingual Textual Style Transfer wit…
Large language models have the potential to generate explanations for their own predictions in a variety of styles based on user instructions. Recent research has examined whether these self-explanations faithfully reflect the models'…
Large language models pretrained on extensive web corpora demonstrate remarkable performance across a wide range of downstream tasks. However, a growing concern is data contamination, where evaluation datasets may be contained in the…
Neural language models often fail to generate diverse and informative texts, limiting their applicability in real-world problems. While previous approaches have proposed to address these issues by identifying and penalizing undesirable…
Watermarking of language model outputs enables statistical detection of model-generated text, which can mitigate harms and misuses of language models. Existing watermarking strategies operate by altering the decoder of an existing language…
We introduce a new pretraining approach geared for multi-document language modeling, incorporating two key ideas into the masked language modeling self-supervised objective. First, instead of considering documents in isolation, we pretrain…
Text style transfer is a hot issue in recent natural language processing,which mainly studies the text to adapt to different specific situations, audiences and purposes by making some changes. The style of the text usually includes many…
Large language models have shown unprecedented abilities in generating linguistically coherent and syntactically correct natural language output. However, they often return incorrect and inconsistent answers to input questions. Due to the…
Large language models are ubiquitous in natural language processing because they can adapt to new tasks without retraining. However, their sheer scale and complexity present unique challenges and opportunities, prompting researchers and…
This paper investigates using knowledge editing techniques to detoxify Large Language Models (LLMs). We construct a benchmark, SafeEdit, which covers nine unsafe categories with various powerful attack prompts and equips comprehensive…
Most Transformer language models are primarily pretrained on English text, limiting their use for other languages. As the model sizes grow, the performance gap between English and other languages with fewer compute and data resources…
Text style transfer refers to the task of rephrasing a given text in a different style. While various methods have been proposed to advance the state of the art, they often assume the transfer output follows a delta distribution, and thus…
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…
Text Style Transfer (TST) seeks to alter the style of text while retaining its core content. Given the constraints of limited parallel datasets for TST, we propose CoTeX, a framework that leverages large language models (LLMs) alongside…
Modeling long texts has been an essential technique in the field of natural language processing (NLP). With the ever-growing number of long documents, it is important to develop effective modeling methods that can process and analyze such…
Translate-test is a popular technique to improve the performance of multilingual language models. This approach works by translating the input into English using an external machine translation system, and running inference over the…
Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…
The widespread use of Large Language Models (LLMs), celebrated for their ability to generate human-like text, has raised concerns about misinformation and ethical implications. Addressing these concerns necessitates the development of…
Zero-shot cross-lingual transfer by fine-tuning multilingual pretrained models shows promise for low-resource languages, but often suffers from misalignment of internal representations between languages. We hypothesize that even when the…
Understanding how styles differ across languages is advantageous for training both humans and computers to generate culturally appropriate text. We introduce an explanation framework to extract stylistic differences from multilingual LMs…
This paper investigates the propagation of harmful information in multilingual large language models (LLMs) and evaluates the efficacy of various unlearning methods. We demonstrate that fake information, regardless of the language it is in,…