Related papers: Unnatural Instructions: Tuning Language Models wit…

The ability to communicate with robots using natural language is a significant step forward in human-robot interaction. However, accurately translating verbal commands into physical actions is promising, but still presents challenges.…

In recent years, progress in NLU has been driven by benchmarks. These benchmarks are typically collected by crowdsourcing, where annotators write examples based on annotation instructions crafted by dataset creators. In this work, we…

Supervised machine learning provides the learner with a set of input-output examples of the target task. Humans, however, can also learn to perform new tasks from instructions in natural language. Can machines learn to understand…

Language models are commonly fine-tuned via reinforcement learning to alter their behavior or elicit new capabilities. Datasets used for these purposes, and particularly human preference datasets, are often noisy. The relatively small size…

Language model fine-tuning is essential for modern natural language processing, but is computationally expensive and time-consuming. Further, the effectiveness of fine-tuning is limited by the inclusion of training examples that negatively…

Instruction tuning has emerged to enhance the capabilities of large language models (LLMs) to comprehend instructions and generate appropriate responses. Existing methods either manually annotate or employ LLM (e.g., GPT-series) to generate…

Language model pre-training has proven to be useful in many language understanding tasks. In this paper, we investigate whether it is still helpful to add the self-training method in the pre-training step and the fine-tuning step. Towards…

Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts. However, prompting often leads models to make predictions with lower accuracy compared to finetuning a model…

Intelligent instruction-following robots capable of improving from autonomously collected experience have the potential to transform robot learning: instead of collecting costly teleoperated demonstration data, large-scale deployment of…

Despite being trained specifically to follow user instructions, today's instructiontuned language models perform poorly when instructed to produce random outputs. For example, when prompted to pick a number uniformly between one and ten…

In this paper, we study how the intrinsic nature of pre-training data contributes to the fine-tuned downstream performance. To this end, we pre-train different transformer-based masked language models on several corpora with certain…

We study whether automatically-induced prompts that effectively extract information from a language model can also be used, out-of-the-box, to probe other language models for the same information. After confirming that discrete prompts…

As instruction-tuned large language models (LLMs) gain global adoption, their ability to follow instructions in multiple languages becomes increasingly crucial. In this work, we investigate how multilinguality during instruction tuning of a…

Reinforcement learning is used to align language models with human preference signals after first pre-training the model to predict the next token of text within a large corpus using likelihood maximization. Before being deployed in a…

Many recent studies endeavor to improve open-source language models through imitation learning, and re-training on the synthetic instruction data from state-of-the-art proprietary models like ChatGPT and GPT-4. However, the innate nature of…

Recent approaches have explored language-guided classifiers capable of classifying examples from novel tasks when provided with task-specific natural language explanations, instructions or prompts (Sanh et al., 2022; R. Menon et al., 2022).…

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…

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…

Despite the effectiveness of vision-language supervised fine-tuning in enhancing the performance of Vision Large Language Models (VLLMs). However, existing visual instruction tuning datasets include the following limitations: (1)…

Although deep reinforcement learning has recently been very successful at learning complex behaviors, it requires a tremendous amount of data to learn a task. One of the fundamental reasons causing this limitation lies in the nature of the…