Related papers: Task--Specificity Score: Measuring How Much Instru…

To combat the misuse of Large Language Models (LLMs), many recent studies have presented LLM-generated-text detectors with promising performance. When users instruct LLMs to generate texts, the instruction can include different constraints…

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…

Large language models (LLMs) have demonstrated impressive capabilities in various natural language processing tasks. Despite this, their application to information retrieval (IR) tasks is still challenging due to the infrequent occurrence…

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…

Instruction-tuning plays a vital role in enhancing the task-solving abilities of large language models (LLMs), improving their usability in generating helpful responses on various tasks. However, previous work has demonstrated that they are…

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse domains, but developing high-performing models for specialized applications often requires substantial human annotation -- a process that is…

Instruction following aims to align Large Language Models (LLMs) with human intent by specifying explicit constraints on how tasks should be performed. However, we reveal a counterintuitive phenomenon: instruction following can…

Supervised fine-tuning (SFT) is a critical step in aligning large language models (LLMs) with human instructions and values, yet many aspects of SFT remain poorly understood. We trained a wide range of base models on a variety of datasets…

Recently, Instruction fine-tuning has risen to prominence as a potential method for enhancing the zero-shot capabilities of Large Language Models (LLMs) on novel tasks. This technique has shown an exceptional ability to boost the…

Production-grade LLM systems require robust adherence to dozens or even hundreds of instructions simultaneously. However, the instruction-following capabilities of LLMs at high instruction densities have not yet been characterized, as…

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…

Despite the fact that large language models (LLMs) show exceptional skill in instruction following tasks, this strength can turn into a vulnerability when the models are required to disregard certain instructions. Instruction-following…

Large language models (LLMs) could be valuable personal AI agents across various domains, provided they can precisely follow user instructions. However, recent studies have shown significant limitations in LLMs' instruction-following…

While metrics available during pre-training, such as perplexity, correlate well with model performance at scaling-laws studies, their predictive capacities at a fixed model size remain unclear, hindering effective model selection and…

Instruction tuning has become the de facto method to equip large language models (LLMs) with the ability of following user instructions. Usually, hundreds of thousands or millions of instruction-following pairs are employed to fine-tune the…

Researchers are increasingly using language models (LMs) for text annotation. These approaches rely only on a prompt telling the model to return a given output according to a set of instructions. The reproducibility of LM outputs may…

How well can NLP models generalize to a variety of unseen tasks when provided with task instructions? To address this question, we first introduce Super-NaturalInstructions, a benchmark of 1,616 diverse NLP tasks and their expert-written…

Instructions trigger a production-centered mechanism in language models. Through a cognitively inspired lens that separates language processing and production, we reveal this mechanism as an asymmetry between the two stages by probing…

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…

Finetuning language models on a collection of datasets phrased as instructions has been shown to improve model performance and generalization to unseen tasks. In this paper we explore instruction finetuning with a particular focus on (1)…