Related papers: Self-QA: Unsupervised Knowledge Guided Language Mo…

We introduce LingoQA, a novel dataset and benchmark for visual question answering in autonomous driving. The dataset contains 28K unique short video scenarios, and 419K annotations. Evaluating state-of-the-art vision-language models on our…

Instruction-tuned large language models have revolutionized natural language processing and have shown great potential in applications such as conversational agents. These models, such as GPT-4, can not only master language but also solve…

Modern language model-based AI systems are remarkably powerful, yet their capabilities remain fundamentally capped by their human creators in three key ways. First, although a model's weights can be updated via fine-tuning, acquiring new…

Most existing neural-based text-to-speech methods rely on extensive datasets and face challenges under low-resource condition. In this paper, we introduce a novel semi-supervised text-to-speech synthesis model that learns from both paired…

This paper shows how to construct knowledge graphs (KGs) from pre-trained language models (e.g., BERT, GPT-2/3), without human supervision. Popular KGs (e.g, Wikidata, NELL) are built in either a supervised or semi-supervised manner,…

Natural language question answering (QA) over structured data sources such as tables and knowledge graphs have been widely investigated, especially with Large Language Models (LLMs) in recent years. The main solutions include question to…

Recent advances in large language and vision-language models have enabled zero-shot inference, allowing models to solve new tasks without task-specific training. Various adaptation techniques such as prompt engineering, In-Context Learning…

Prior work has shown that finetuning large language models (LLMs) using machine-generated instruction-following data enables such models to achieve remarkable zero-shot capabilities on new tasks, and no human-written instructions are…

In the current era, a multitude of language models has emerged to cater to user inquiries. Notably, the GPT-3.5 Turbo language model has gained substantial attention as the underlying technology for ChatGPT. Leveraging extensive parameters,…

Predicting phenotypes from gene expression data is a crucial task in biomedical research, enabling insights into disease mechanisms, drug responses, and personalized medicine. Traditional machine learning and deep learning rely on…

NLP-powered automatic question generation (QG) techniques carry great pedagogical potential of saving educators' time and benefiting student learning. Yet, QG systems have not been widely adopted in classrooms to date. In this work, we aim…

Query auto completion (QAC) systems are a standard part of search engines in industry, helping users formulate their query. Such systems update their suggestions after the user types each character, predicting the user's intent using…

Can post-trained large language models (LLMs) further improve themselves using only unlabeled prompts, without external teachers or feedback from tools? We study this setting starting only from unlabeled seed questions with no ground-truth…

Most previous unsupervised domain adaptation (UDA) methods for question answering(QA) require access to source domain data while fine-tuning the model for the target domain. Source domain data may, however, contain sensitive information and…

Question-answering (QA) tasks often investigate specific question types, knowledge domains, or reasoning skills, leading to specialized models catering to specific categories of QA tasks. While recent research has explored the idea of…

Recent breakthroughs in scale have enabled the emergence of powerful generative language models, and the ability to fine-tune these models on various tasks by casting them into prompts or instructions. In this landscape, the problem of…

In self-supervised learning, one trains a model to solve a so-called pretext task on a dataset without the need for human annotation. The main objective, however, is to transfer this model to a target domain and task. Currently, the most…

Entity alignment, aiming to identify equivalent entities across different knowledge graphs (KGs), is a fundamental problem for constructing large-scale KGs. Over the course of its development, supervision has been considered necessary for…

Question answering (QA) is an important natural language processing (NLP) task and has received much attention in academic research and industry communities. Existing QA studies assume that questions are raised by humans and answers are…

Large pre-trained language models (LMs) such as GPT-3 have acquired a surprising ability to perform zero-shot learning. For example, to classify sentiment without any training examples, we can "prompt" the LM with the review and the label…