相关论文: Specialist or Generalist? Instruction Tuning for S…

While large language models (LLMs) have demonstrated superior multi-task capabilities, understanding the learning mechanisms behind this is still a challenging problem. In this paper, we attempt to understand such mechanisms from the…

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…

Social science NLP tasks, such as emotion or humor detection, are required to capture the semantics along with the implicit pragmatics from text, often with limited amounts of training data. Instruction tuning has been shown to improve the…

Instruction tuning is a pivotal technique for aligning large language models (LLMs) with human intentions, safety constraints, and domain-specific requirements. This survey provides a comprehensive overview of the full pipeline,…

Recently introduced instruction-paradigm empowers non-expert users to leverage NLP resources by defining a new task in natural language. Instruction-tuned models have significantly outperformed multitask learning models (without…

Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The recent progress in large-scale generative models has further expanded their use in real-world language applications. However, the…

Adhering to explicit length constraints, such as generating text with a precise word count, remains a significant challenge for Large Language Models (LLMs). This study aims at investigating the differences between foundation models and…

Instruction tuning plays a critical role in aligning large language models (LLMs) with human preference. Despite the vast amount of open instruction datasets, naively training a LLM on all existing instructions may not be optimal and…

Traditional supervised learning mostly works on individual tasks and requires training on a large set of task-specific examples. This paradigm seriously hinders the development of task generalization since preparing a task-specific example…

Instruction tuning is a widely used approach to improve the instruction-following ability of large language models (LLMs). Instruction-tuning datasets typically include a mixture of context-augmented and context-free examples, yet prior…

What makes large language models (LLMs) impressive is also what makes them hard to evaluate: their diversity of uses. To evaluate these models, we must understand the purposes they will be used for. We consider a setting where these…

Large language models (LLMs) are trained and tested extensively on symbolic representations such as code and graphs, yet real-world user tasks are often specified in natural language. To what extent can LLMs generalize across these…

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…

Task semantics can be expressed by a set of input-output examples or a piece of textual instruction. Conventional machine learning approaches for natural language processing (NLP) mainly rely on the availability of large-scale sets of…

With the capabilities of understanding and executing natural language instructions, Large language models (LLMs) can potentially act as a powerful tool for textual data augmentation. However, the quality of augmented data depends heavily on…

Large Language Models (LLMs) display strikingly different generalization behaviors: supervised fine-tuning (SFT) often narrows capability, whereas reinforcement-learning (RL) tuning tends to preserve it. The reasons behind this divergence…

Story understanding and generation have long been a challenging task in natural language processing (NLP), especially when dealing with various levels of instruction specificity. In this paper, we propose a novel approach called "Weak to…

Large Language Models (LLMs) and strong vision models have enabled rapid research and development in the field of Vision-Language-Action models that enable robotic control. The main objective of these methods is to develop a generalist…

Recent work has shown that fine-tuning large pre-trained language models on a collection of tasks described via instructions, a.k.a. instruction-tuning, improves their zero and few-shot generalization to unseen tasks. However, there is a…

Large Language Models (LLMs) trained on extensive textual corpora have emerged as leading solutions for a broad array of Natural Language Processing (NLP) tasks. Despite their notable performance, these models are prone to certain…