Related papers: DaCy: A Unified Framework for Danish NLP

Self-play with large language models has emerged as a promising paradigm for achieving self-improving artificial intelligence. However, existing self-play frameworks often suffer from optimization instability, due to (i) non-stationary…

Language technologies should be judged on their usefulness in real-world use cases. An often overlooked aspect in natural language processing (NLP) research and evaluation is language variation in the form of non-standard dialects or…

Large Language Models (LLMs) excel in handling general knowledge tasks, yet they struggle with user-specific personalization, such as understanding individual emotions, writing styles, and preferences. Personalized Large Language Models…

Large language models (LLMs) offer strong capabilities but raise cost and privacy concerns, whereas small language models (SLMs) facilitate efficient and private local inference yet suffer from limited capacity. To synergize the…

With the advancement of large language models (LLMs), significant progress has been achieved in various Natural Language Processing (NLP) tasks. However, existing LLMs still face two major challenges that hinder their broader adoption: (1)…

Disentangled representation learning in speech processing has lagged behind other domains, largely due to the lack of datasets with annotated generative factors for robust evaluation. To address this, we propose SynSpeech, a novel…

Current large language models (LLMs) generally show a significant performance gap in alignment between English and other languages. To bridge this gap, existing research typically leverages the model's responses in English as a reference to…

Sentiment analysis has become increasingly important for assessing public opinion and informing decision-making. Large language models (LLMs) have revolutionized this field by capturing nuanced language patterns. However, adapting LLMs to…

Recent advances in large language models (LLMs) have demonstrated remarkable capabilities on widely benchmarked high-resource languages. However, linguistic nuances of under-resourced languages remain unexplored. We introduce Batayan, a…

Recent advancements in large language models have demonstrated that extended inference through techniques can markedly improve performance, yet these gains come with increased computational costs and the propagation of inherent biases found…

The traditional process of creating labeled datasets is labor-intensive and expensive. Recent breakthroughs in open-source large language models (LLMs) have opened up a new avenue in generating labeled datasets automatically for various…

Semi-supervised learning through deep generative models and multi-lingual pretraining techniques have orchestrated tremendous success across different areas of NLP. Nonetheless, their development has happened in isolation, while the…

We present SnakModel, a Danish large language model (LLM) based on Llama2-7B, which we continuously pre-train on 13.6B Danish words, and further tune on 3.7M Danish instructions. As best practices for creating LLMs for smaller language…

For text-level discourse analysis, there are various discourse schemes but relatively few labeled data, because discourse research is still immature and it is labor-intensive to annotate the inner logic of a text. In this paper, we attempt…

Large Language Models (LLMs) are increasingly deployed in high-stakes contexts where their outputs influence real-world decisions. However, evaluating bias in LLM outputs remains methodologically challenging due to sensitivity to prompt…

Natural language processing covers a wide variety of tasks predicting syntax, semantics, and information content, and usually each type of output is generated with specially designed architectures. In this paper, we provide the simple…

Objective: Most existing fine-tuned biomedical large language models (LLMs) focus on enhancing performance in monolingual biomedical question answering and conversation tasks. To investigate the effectiveness of the fine-tuned LLMs on…

For high-resource languages like English, text classification is a well-studied task. The performance of modern NLP models easily achieves an accuracy of more than 90% in many standard datasets for text classification in English (Xie et…

Large language models (LLMs) excel in general tasks but struggle with domain-specific ones, requiring fine-tuning with specific data. With many open-source LLMs available, selecting the best model for fine-tuning downstream tasks is…

We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including: part-of-speech tagging, chunking, named entity recognition, and semantic role labeling. This…