Enhancing Dialectal Commonsense Reasoning in Large Language Models through Data Augmentation
Data augmentation techniques can improve the performance of large language models on dialectal commonsense reasoning tasks.
Adapting Language Models to Linguistic Variation: Insights from Controlled Experiments
Linguistic variation poses significant challenges for language models, requiring careful consideration of data characteristics and model capabilities to facilitate effective adaptation.
Continuous Language Model Interpolation for Dynamic and Predictable Text Generation
Linear weight interpolation between fine-tuned language models can be used to dynamically generate text with predictable and fine-grained control over multiple stylistic attributes simultaneously.
Adapting Large Language Models to Diverse Languages: A Comprehensive Study
This paper presents a comprehensive methodology for adapting large language models to new languages, demonstrating state-of-the-art results across 9 diverse languages and 2 model scales.
Adapting Llama 2 to Estonian Through Cross-Lingual Instruction-Tuning and Monolingual Pretraining
This paper explores cost-efficient methods to adapt the Llama 2 language model to the Estonian language, leveraging cross-lingual instruction-tuning and additional monolingual pretraining.
Efficient Customization of Large Language Models through Proxy-Tuning
Proxy-tuning is a lightweight decoding-time algorithm that can efficiently customize large pretrained language models without accessing their internal weights, by leveraging small tuned models as "experts" to guide the predictions of the larger base model.
© 2024 by Linnk AI