Related papers: Unnatural Instructions: Tuning Language Models wit…

Enhancing the zero-shot performance of instruction-following models requires heavy computation, either by scaling the total number of training datasets or the model size. In this work, we explore how retrieval of soft prompts obtained…

Large language models can perform well on general natural language tasks, but their effectiveness is still suboptimal for information extraction (IE). Recent works indicate that the main reason lies in the lack of extensive data on IE…

Large pre-trained language models (LMs) such as GPT-3 have acquired a surprising ability to perform zero-shot learning. For example, to classify sentiment without any training examples, we can "prompt" the LM with the review and the label…

How can an end-user provide feedback if a deployed structured prediction model generates inconsistent output, ignoring the structural complexity of human language? This is an emerging topic with recent progress in synthetic or constrained…

Instruction tuning improves the ability of large language models (LLMs) to follow diverse human instructions, but achieving strong performance on specific target tasks remains challenging. A critical bottleneck is selecting the most…

Large language models have recently been shown to attain reasonable zero-shot generalization on a diverse set of tasks (Brown et al., 2020). It has been hypothesized that this is a consequence of implicit multitask learning in language…

In recent years, instruction tuning has gained increasing attention and emerged as a crucial technique to enhance the capabilities of Large Language Models (LLMs). To construct high-quality instruction datasets, many instruction processing…

Recent advances in text-to-music editing, which employ text queries to modify music (e.g.\ by changing its style or adjusting instrumental components), present unique challenges and opportunities for AI-assisted music creation. Previous…

Instruction tuning significantly enhances the performance of large language models (LLMs) across various tasks. However, the procedure to optimizing the mixing of instruction datasets for LLM fine-tuning is still poorly understood. This…

Large language models (LLMs) that are tuned with instructions have demonstrated remarkable capabilities in various tasks and languages. However, their ability to generalize to underrepresented languages is limited due to the scarcity of…

Machine translation (MT) models used in industries with constantly changing topics, such as translation or news agencies, need to adapt to new data to maintain their performance over time. Our aim is to teach a pre-trained MT model to…

Large language models have unlocked strong multi-task capabilities from reading instructive prompts. However, recent studies have shown that existing large models still have difficulty with information extraction tasks. For example,…

While recent research on natural language inference has considerably benefited from large annotated datasets, the amount of inference-related knowledge (including commonsense) provided in the annotated data is still rather limited. There…

This paper surveys research works in the quickly advancing field of instruction tuning (IT), which can also be referred to as supervised fine-tuning (SFT)\footnote{In this paper, unless specified otherwise, supervised fine-tuning (SFT) and…

We consider a setting where a population of artificial learners is given, and the objective is to optimize aggregate measures of performance, under constraints on training resources. The problem is motivated by the study of peer learning in…

Datasets are foundational to many breakthroughs in modern artificial intelligence. Many recent achievements in the space of natural language processing (NLP) can be attributed to the finetuning of pre-trained models on a diverse set of…

Instruction tuning is a vital step of training large language models (LLMs), so how to enhance the effect of instruction tuning has received increased attention. Existing works indicate that the quality of the dataset is more crucial than…

Natural Language Inference (NLI) models are known to learn from biases and artefacts within their training data, impacting how well they generalise to other unseen datasets. Existing de-biasing approaches focus on preventing the models from…

During the pre-training step of natural language models, the main objective is to learn a general representation of the pre-training dataset, usually requiring large amounts of textual data to capture the complexity and diversity of natural…

Complex, long-horizon planning and its combinatorial nature pose steep challenges for learning-based agents. Difficulties in such settings are exacerbated in low data regimes where over-fitting stifles generalization and compounding errors…