Related papers: Self-Instruct: Aligning Language Models with Self-…

Pretrained language models often do not perform tasks in ways that are in line with our preferences, e.g., generating offensive text or factually incorrect summaries. Recent work approaches the above issue by learning from a simple form of…

Large Language Models (LLMs) for public use require continuous pre-training to remain up-to-date with the latest data. The models also need to be fine-tuned with specific instructions to maintain their ability to follow instructions…

While language models have shown remarkable performance across diverse tasks, they still encounter challenges in complex reasoning scenarios. Recent research suggests that language models trained on linearized search traces toward…

Although pre-trained language models encode generic knowledge beneficial for planning and control, they may fail to generate appropriate control policies for domain-specific tasks. Existing fine-tuning methods use human feedback to address…

Instruction tuning is instrumental in enabling Large Language Models~(LLMs) to follow user instructions to complete various open-domain tasks. The success of instruction tuning depends on the availability of high-quality instruction data.…

The success of ChatGPT has recently attracted numerous efforts to replicate it, with instruction-tuning strategies being a key factor in achieving remarkable results. Instruction-tuning not only significantly enhances the model's…

Pre-trained models have achieved state-of-the-art results in various Natural Language Processing (NLP) tasks. Recent works such as T5 and GPT-3 have shown that scaling up pre-trained language models can improve their generalization…

Instruction tuning improves the reasoning abilities of large language models (LLMs), with data quality and scalability being the crucial factors. Most instruction tuning data come from human crowd-sourcing or GPT-4 distillation. We propose…

Automatic evaluation of natural language generation has long been an elusive goal in NLP.A recent paradigm fine-tunes pre-trained language models to emulate human judgements for a particular task and evaluation criterion. Inspired by the…

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…

Automated explanatory feedback systems play a crucial role in facilitating learning for a large cohort of learners by offering feedback that incorporates explanations, significantly enhancing the learning process. However, delivering such…

Large language models have the potential to generate explanations for their own predictions in a variety of styles based on user instructions. Recent research has examined whether these self-explanations faithfully reflect the models'…

We demonstrate that co-training (Blum & Mitchell, 1998) can improve the performance of prompt-based learning by using unlabeled data. While prompting has emerged as a promising paradigm for few-shot and zero-shot learning, it is often…

Prompting a pretrained language model with natural language patterns has been proved effective for natural language understanding (NLU). However, our preliminary study reveals that manual discrete prompts often lead to unstable performance…

Recently introduced instruction-paradigm empowers non-expert users to leverage NLP resources by defining a new task in natural language. Instruction-tuned models have significantly outperformed multitask learning models (without…

Unsupervised pre-training has led to much recent progress in natural language understanding. In this paper, we study self-training as another way to leverage unlabeled data through semi-supervised learning. To obtain additional data for a…

A promising paradigm for adapting instruction-tuned language models is to learn task-specific updates on a pretrained base model and subsequently merge them into the instruction-tuned model. However, existing approaches typically treat the…

Generative AI and large language models hold great promise in enhancing programming education by automatically generating individualized feedback for students. We investigate the role of generative AI models in providing human tutor-style…

Multimodal large language models (MLLMs) perform well on many vision-language tasks but often struggle with vision-centric problems that require fine-grained visual reasoning. Recent evidence suggests that this limitation arises not from…

Instruction-tuning can be substantially optimized through enhanced diversity, resulting in models capable of handling a broader spectrum of tasks. However, existing data employed for such tuning often exhibit an inadequate coverage of…