Related papers: Better Call SAUL: Fluent and Consistent Language M…

Large-scale generative models have shown impressive image-generation capabilities, propelled by massive data. However, this often inadvertently leads to the generation of harmful or inappropriate content and raises copyright concerns.…

Large language models (LLMs) often have a fixed knowledge cutoff, limiting their accuracy on emerging information. We present ALAS (Autonomous Learning Agent System), a modular pipeline that continuously updates an LLM's knowledge with…

Large Language Models (LLMs) generate responses to questions; however, their effectiveness is often hindered by sub-optimal quality of answers and occasional failures to provide accurate responses to questions. To address these challenges,…

This article explores the zero-shot performance of state-of-the-art large language models (LLMs) on one of the most challenging tasks in authorship analysis: sentence-level style change detection. Benchmarking four LLMs on the official…

In modern deep learning models, long training times and large datasets present significant challenges to both efficiency and scalability. Effective data curation and sample selection are crucial for optimizing the training process of deep…

We propose a novel data synthesis method to generate diverse error-corrected sentence pairs for improving grammatical error correction, which is based on a pair of machine translation models of different qualities (i.e., poor and good). The…

Efficient knowledge editing of large language models is crucial for replacing obsolete information or incorporating specialized knowledge on a large scale. However, previous methods implicitly assume that knowledge is localized and isolated…

Large Language Models (LLMs) are powerful models for generation tasks, but they may not generate good quality outputs in their first attempt. Apart from model fine-tuning, existing approaches to improve prediction accuracy and quality…

Sampling is a common strategy for generating text from probabilistic models, yet standard ancestral sampling often results in text that is incoherent or ungrammatical. To alleviate this issue, various modifications to a model's sampling…

Data curation is a critical yet under-explored area in large language model (LLM) training. Existing methods, such as data selection and mixing, operate in an offline paradigm, detaching themselves from training. This separation introduces…

Text-editing models have recently become a prominent alternative to seq2seq models for monolingual text-generation tasks such as grammatical error correction, simplification, and style transfer. These tasks share a common trait - they…

Large Language Models (LLMs) have demonstrated strong reasoning capabilities across various tasks. However, even minor variations in query phrasing, despite preserving the underlying semantic meaning, can significantly affect their…

The training of spoken language understanding (SLU) models often faces the problem of data scarcity. In this paper, we put forward a data augmentation method using pretrained language models to boost the variability and accuracy of…

Adapting general-purpose language models to new skills is currently an expensive process that must be repeated as new instruction datasets targeting new skills are created, or can cause the models to forget older skills. In this work, we…

Model editing techniques are essential for efficiently updating knowledge in large language models (LLMs). However, the effectiveness of existing approaches degrades in massive editing scenarios, particularly when evaluated with practical…

Multilingual spoken language understanding (SLU) consists of two sub-tasks, namely intent detection and slot filling. To improve the performance of these two sub-tasks, we propose to use consistency regularization based on a hybrid data…

Knowledge editing enables targeted updates without retraining, but prior work focuses on textual or visual facts, leaving abstract auditory perceptual knowledge underexplored. We introduce SAKE, the first benchmark for editing perceptual…

This paper examines the problem of adapting neural machine translation systems to new, low-resourced languages (LRLs) as effectively and rapidly as possible. We propose methods based on starting with massively multilingual "seed models",…

Fine-tuning LLMs for classification typically maps inputs directly to labels. We ask whether attaching brief explanations to each label during fine-tuning yields better models. We evaluate conversational response quality along three axes:…

Improving the quality of Natural Language Understanding (NLU) models, and more specifically, task-oriented semantic parsing models, in production is a cumbersome task. In this work, we present a system called AutoNLU, which we designed to…