Related papers: Improving Instruct Models for Free: A Study on Par…

Majority of the modern meta-learning methods for few-shot classification tasks operate in two phases: a meta-training phase where the meta-learner learns a generic representation by solving multiple few-shot tasks sampled from a large…

Large language models demonstrate a remarkable capability for learning to solve new tasks from a few examples. The prompt template, or the way the input examples are formatted to obtain the prompt, is an important yet often overlooked…

It has recently been demonstrated empirically that in-context learning emerges in transformers when certain distributional properties are present in the training data, but this ability can also diminish upon further training. We provide a…

Large language models are able to learn new tasks in context, where they are provided with instructions and a few annotated examples. However, the effectiveness of in-context learning is dependent on the provided context, and the…

Image Captioning is a traditional vision-and-language task that aims to generate the language description of an image. Recent studies focus on scaling up the model size and the number of training data, which significantly increase the cost…

When a teacher provides examples for a student to study, these examples must be informative, enabling a student to progress from their current state toward a target concept or skill. Good teachers must therefore simultaneously infer what…

Machine learning methods adapt the parameters of a model, constrained to lie in a given model class, by using a fixed learning procedure based on data or active observations. Adaptation is done on a per-task basis, and retraining is needed…

Adversarial training is a popular method to robustify models against adversarial attacks. However, it exhibits much more severe overfitting than training on clean inputs. In this work, we investigate this phenomenon from the perspective of…

Attention-based architectures trained on internet-scale language data have demonstrated state of the art reasoning ability for various language-based tasks, such as logic problems and textual reasoning. Additionally, these Large Language…

With a handful of demonstration examples, large-scale language models show strong capability to perform various tasks by in-context learning from these examples, without any fine-tuning. We demonstrate that in-context learning performance…

Large language models have exhibited intriguing in-context learning capability, achieving promising zero- and few-shot performance without updating the parameters. However, conventional in-context learning is usually restricted by length…

In-context learning (ICL) allows a language model to improve its problem-solving capability when provided with suitable information in context. Since the choice of in-context information can be determined based on the problem itself,…

Improvements in language models are often driven by improving the quality of the data we train them on, which can be limiting when strong supervision is scarce. In this work, we show that paired preference data consisting of individually…

Large Language Models (LLMs) for public use require continuous pre-training to remain up-to-date with the latest data. The models also need to be fine-tuned with specific instructions to maintain their ability to follow instructions…

We present symbol tuning - finetuning language models on in-context input-label pairs where natural language labels (e.g., "positive/negative sentiment") are replaced with arbitrary symbols (e.g., "foo/bar"). Symbol tuning leverages the…

Pre-trained vision language models do not have good intuitions about the physical world. Recent work has shown that supervised fine-tuning can improve model performance on simple physical tasks. However, fine-tuned models do not appear to…

Multilingual language models often perform unevenly across different languages due to limited generalization capabilities for some languages. This issue is significant because of the growing interest in making universal language models that…

Foundation language models learn from their finetuning input context in different ways. In this paper, we reformulate inputs during finetuning for challenging translation tasks, leveraging model strengths from pretraining in novel ways to…

This work connects language model adaptation with concepts of machine learning theory. We consider a training setup with a large out-of-domain set and a small in-domain set. We derive how the benefit of training a model on either set…

Large pretrained language models have shown surprising in-context learning (ICL) ability. With a few demonstration input-label pairs, they can predict the label for an unseen input without parameter updates. Despite the great success in…