Related papers: Instructive Decoding: Instruction-Tuned Large Lang…

Despite rapid advances in the capabilities of Large Language Models (LLMs), they continue to struggle with following relatively simple and unambiguous instructions, particularly when compositional structure is involved. Recent work suggests…

Instruction tuning plays a crucial role in shaping the outputs of language models (LMs) to desired styles. In this work, we propose a simple yet effective method, Instruction Modelling (IM), which trains LMs by applying a loss function to…

Despite their remarkable performance, large language models lack elementary safety features, making them susceptible to numerous malicious attacks. In particular, previous work has identified the absence of an intrinsic separation between…

Instruction tuning enhances the instruction following ability of large language models by finetuning with supervised instruction data. Previous work proposes in-context instruction tuning (ICIT) where specific positive or negative examples…

The purpose of instruction tuning is enabling zero-shot performance, but instruction tuning has also been shown to improve chain-of-thought reasoning and value alignment (Si et al., 2023). Here we consider the impact on…

Despite their impressive capabilities, large language models (LLMs) have been observed to generate responses that include inaccurate or fabricated information, a phenomenon commonly known as ``hallucination''. In this work, we propose a…

Recent research on fine-tuning vision-language models has demonstrated impressive performance in various downstream tasks. However, the challenge of obtaining accurately labeled data in real-world applications poses a significant obstacle…

Instruction tuning is an emergent paradigm in NLP wherein natural language instructions are leveraged with language models to induce zero-shot performance on unseen tasks. Instructions have been shown to enable good performance on unseen…

Lack of training data presents a grand challenge to scaling out spoken language understanding (SLU) to low-resource languages. Although various data augmentation approaches have been proposed to synthesize training data in low-resource…

Instruction tuning is an effective technique to align large language models (LLMs) with human intents. In this work, we investigate how an adversary can exploit instruction tuning by injecting specific instruction-following examples into…

Discriminative pre-trained language models (PrLMs) can be generalized as denoising auto-encoders that work with two procedures, ennoising and denoising. First, an ennoising process corrupts texts with arbitrary noising functions to…

Large language models exhibit exciting capabilities, yet can show surprisingly narrow generalization from finetuning. E.g. they can fail to generalize to simple reversals of relations they are trained on, or fail to make simple logical…

Instruction tuning is crucial for enabling Large Language Models (LLMs) to solve real-world tasks. Prior work has shown the effectiveness of instruction-tuning data synthesized solely from LLMs, raising a fundamental question: Do we still…

Instruction-tuned large language models (LLMs) have demonstrated promising zero-shot generalization capabilities across various downstream tasks. Recent research has introduced multimodal capabilities to LLMs by integrating independently…

In-Context Learning (ICL) is suffering from unsatisfactory performance and under-calibration due to high prior bias and unfaithful confidence. Some previous works fine-tuned language models for better ICL performance with enormous datasets…

Fine-tuning large language models (LLMs) with a collection of large and diverse instructions has improved the model's generalization to different tasks, even for unseen tasks. However, most existing instruction datasets include only single…

Learning with guidance has proven effective across a wide range of machine learning systems. Guidance may, for example, come from annotated datasets in supervised learning, pseudo-labels in semi-supervised learning, and expert demonstration…

Instruction tuning has emerged as a critical paradigm for improving the capabilities and alignment of large language models (LLMs). However, existing iterative model-aware data selection methods incur significant computational overhead, as…

It is widely known in the machine learning community that class noise can be (and often is) detrimental to inducing a model of the data. Many current approaches use a single, often biased, measurement to determine if an instance is noisy. A…

Large language models respond well in high-resource languages like English but struggle in low-resource languages. It may arise from the lack of high-quality instruction following data in these languages. Directly translating English…