Related papers: Instruction Following without Instruction Tuning

Domain models are central to software engineering, as they enable a shared understanding, guide implementation, and support automated analyses and model-driven development. Yet, despite these benefits, practitioners often skip modeling…

As large language models (LLMs) continue to advance, instruction tuning has become critical for improving their ability to generate accurate and contextually appropriate responses. Although numerous instruction-tuning datasets have been…

Self-supervised pre-training of large-scale transformer models on text corpora followed by finetuning has achieved state-of-the-art on a number of natural language processing tasks. Recently, Lu et al. (2021, arXiv:2103.05247) claimed that…

Language modeling on large-scale datasets leads to impressive performance gains on various downstream language tasks. The validation pre-training loss (or perplexity in autoregressive language modeling) is often used as the evaluation…

Diffusion models continuously push the boundary of state-of-the-art image generation, but the process is hard to control with any nuance: practice proves that textual prompts are inadequate for accurately describing image style or fine…

Derivative-free prompt learning has emerged as a lightweight alternative to prompt tuning, which only requires model inference to optimize the prompts. However, existing work did not take full advantage of the over-parameterized…

Yes-no questions expect a yes or no for an answer, but people often skip polar keywords. Instead, they answer with long explanations that must be interpreted. In this paper, we focus on this challenging problem and release new benchmarks in…

Instruction tuning has been shown to be able to improve cross-task generalization of language models. However, it is still challenging for language models to complete the target tasks following the instructions, as the instructions are…

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…

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)…

Large Language Models (LLMs), trained on extensive web-scale corpora, have demonstrated remarkable abilities across diverse tasks, especially as they are scaled up. Nevertheless, even state-of-the-art models struggle in certain cases,…

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…

Prompt tuning is a parameter-efficient tuning (PETuning) method for utilizing pre-trained models (PTMs) that simply prepends a soft prompt to the input and only optimizes the prompt to adapt PTMs to downstream tasks. Although it is…

Large language models' behavior is often shaped by instructions such as system prompts, refusal boundaries, privacy constraints, and tool-use rules that must hold at inference time. Yet in practice these constraints can be violated under…

Providing user-understandable explanations to justify recommendations could help users better understand the recommended items, increase the system's ease of use, and gain users' trust. A typical approach to realize it is natural language…

Continual pre-training has been urgent for adapting a pre-trained model to a multitude of domains and tasks in the fast-evolving world. In practice, a continually pre-trained model is expected to demonstrate not only greater capacity when…

Tabular instruction tuning has emerged as a promising research direction for improving LLMs understanding of tabular data. However, the majority of existing works only consider question-answering and reasoning tasks over tabular data,…

It has been shown for English that discrete and soft prompting perform strongly in few-shot learning with pretrained language models (PLMs). In this paper, we show that discrete and soft prompting perform better than finetuning in…

Behavioral skills or policies for autonomous agents are conventionally learned from reward functions, via reinforcement learning, or from demonstrations, via imitation learning. However, both modes of task specification have their…

We show that explicit pragmatic inference aids in correctly generating and following natural language instructions for complex, sequential tasks. Our pragmatics-enabled models reason about why speakers produce certain instructions, and…