Zobrazeno 1 - 10
of 7 148
pro vyhledávání: '"Gales A"'
Large Language Models (LLMs) are increasingly used to assess NLP tasks due to their ability to generate human-like judgments. Single LLMs were used initially, however, recent work suggests using multiple LLMs as judges yields improved performance. An
Externí odkaz:
http://arxiv.org/abs/2410.10215
Automated assessment in natural language generation is a challenging task. Instruction-tuned large language models (LLMs) have shown promise in reference-free evaluation, particularly through comparative assessment. However, the quadratic computation
Externí odkaz:
http://arxiv.org/abs/2409.15979
Error correction (EC) models play a crucial role in refining Automatic Speech Recognition (ASR) transcriptions, enhancing the readability and quality of transcriptions. Without requiring access to the underlying code or model weights, EC can improve
Externí odkaz:
http://arxiv.org/abs/2409.09554
Grammatical feedback is crucial for consolidating second language (L2) learning. Most research in computer-assisted language learning has focused on feedback through grammatical error correction (GEC) systems, rather than examining more holistic feed
Externí odkaz:
http://arxiv.org/abs/2408.09565
Foundation ASR models often support many languages, e.g. 100 languages in Whisper. However, there has been limited work on integrating an additional, typically low-resource, language, while maintaining performance on the original language set. Fine-t
Externí odkaz:
http://arxiv.org/abs/2407.06800
Autor:
Raina, Vyas, Gales, Mark
Speech enabled foundation models, either in the form of flexible speech recognition based systems or audio-prompted large language models (LLMs), are becoming increasingly popular. One of the interesting aspects of these models is their ability to pe
Externí odkaz:
http://arxiv.org/abs/2407.04482
There has been increasing interest in building multilingual foundation models for NLP and speech research. This paper examines how to expand the speech translation capability of these models with restricted data. Whisper, a speech foundation model wi
Externí odkaz:
http://arxiv.org/abs/2407.01130
Autor:
Cripps, Sally, Lopatnikova, Anna, Afshar, Hadi Mohasel, Gales, Ben, Marchant, Roman, Francis, Gilad, Moreira, Catarina, Fischer, Alex
This paper proposes Bayesian Adaptive Trials (BAT) as both an efficient method to conduct trials and a unifying framework for evaluation social policy interventions, addressing limitations inherent in traditional methods such as Randomized Controlled
Externí odkaz:
http://arxiv.org/abs/2406.02868
Autor:
Sun, Guangzhi, Manakul, Potsawee, Liusie, Adian, Pipatanakul, Kunat, Zhang, Chao, Woodland, Phil, Gales, Mark
Multimodal foundation models are prone to hallucination, generating outputs that either contradict the input or are not grounded by factual information. Given the diversity in architectures, training data and instruction tuning techniques, there can
Externí odkaz:
http://arxiv.org/abs/2405.13684
Autor:
Raina, Vatsal, Gales, Mark
Enterprise retrieval augmented generation (RAG) offers a highly flexible framework for combining powerful large language models (LLMs) with internal, possibly temporally changing, documents. In RAG, documents are first chunked. Relevant chunks are th
Externí odkaz:
http://arxiv.org/abs/2405.12363