Related papers: From Instance Training to Instruction Learning: Ta…

Large language models (LLMs) are capable of performing conditional sequence generation tasks, such as translation or summarization, through instruction fine-tuning. The fine-tuning data is generally sequentially concatenated from a specific…

Recent works on instruction tuning (IT) have achieved great performance with zero-shot generalizability to unseen tasks. With additional context (e.g., task definition, examples) provided to models for fine-tuning, they achieved much higher…

Fine-tuning pre-trained language models (LMs) is essential for enhancing their capabilities. Existing techniques commonly fine-tune on input-output pairs (e.g., instruction tuning) or with numerical rewards that gauge the output quality…

Pretrained Large Language Models (LLM) such as ChatGPT, Claude, etc. have demonstrated strong capabilities in various fields of natural language generation. However, there are still many problems when using LLM in specialized…

In-context learning (ICL) refers to a remarkable capability of pretrained large language models, which can learn a new task given a few examples during inference. However, theoretical understanding of ICL is largely under-explored,…

Test-time training (TTT) methods explicitly update the weights of a model to adapt to the specific test instance, and they have found success in a variety of settings, including most recently language modeling and reasoning. To demystify…

Instruction Tuning (IT), the process of training large language models (LLMs) using instruction-response pairs, has emerged as the predominant method for transforming base pre-trained LLMs into open-domain conversational agents. While IT…

The improved competence of generative models can help building multi-modal virtual assistants that leverage modalities beyond language. By observing humans performing multi-step tasks, one can build assistants that have situational…

Designing effective task-level prompts is crucial for improving the performance of Large Language Models (LLMs). While prior work on instruction induction demonstrates that LLMs can infer better instructions with limited examples, existing…

Despite the artificial intelligence (AI) revolution, deep learning has yet to achieve much success with tabular data due to heterogeneous feature space and limited sample sizes without viable transfer learning. The new era of generative AI,…

Diverse instruction data is vital for effective instruction tuning of large language models, as it enables the model to generalize across different types of inputs . Building such diversified instruction dataset is an essential step in this…

Instruction tuning aims to align large language models (LLMs) with open-domain instructions and human-preferred responses. While several studies have explored autonomous approaches to distilling and annotating instructions from powerful…

Large Language Models (LLMs), primarily trained on text-based datasets, exhibit exceptional proficiencies in understanding and executing complex linguistic instructions via text outputs. However, they falter when requests to generate…

Learning from demonstrations has made great progress over the past few years. However, it is generally data hungry and task specific. In other words, it requires a large amount of data to train a decent model on a particular task, and the…

The main challenge in domain generalization (DG) is to handle the distribution shift problem that lies between the training and test data. Recent studies suggest that test-time training (TTT), which adapts the learned model with test data,…

Due to limited supervised training data, large language models (LLMs) are typically pre-trained via a self-supervised "predict the next word" objective on a vast amount of unstructured text data. To make the resulting model useful to users,…

Large language models (LLM) have recently shown the extraordinary ability to perform unseen tasks based on few-shot examples provided as text, also known as in-context learning (ICL). While recent works have attempted to understand the…

Recent state-of-the-art artificial agents lack the ability to adapt rapidly to new tasks, as they are trained exclusively for specific objectives and require massive amounts of interaction to learn new skills. Meta-reinforcement learning…

While large language models (LLMs) have advanced the development of general-purpose agents, achieving robust generalization to unseen tasks remains a significant challenge. Current approaches typically rely on either fine-tuning or…

In-context learning (ICL) is a remarkable capability of pretrained transformers that allows models to generalize to unseen tasks after seeing only a few examples. We investigate empirically the conditions necessary on the pretraining…