Related papers: RecipeGPT: Generative Pre-training Based Cooking R…
Grammatical error correction aims to correct ungrammatical sentences automatically. Recently, some work has demonstrated the excellent capabilities of closed-source Large Language Models (LLMs, e.g., ChatGPT) in grammatical error…
A multi-turn dialogue always follows a specific topic thread, and topic shift at the discourse level occurs naturally as the conversation progresses, necessitating the model's ability to capture different topics and generate topic-aware…
Large pre-trained language models have exhibited unprecedented capabilities in producing high-quality text via prompting techniques. This fact introduces new possibilities for data collection and annotation, particularly in situations where…
Recent advancements in Natural Language Processing (NLP) have led to the development of NLP-based recommender systems that have shown superior performance. However, current models commonly treat items as mere IDs and adopt discriminative…
Large Language Models (LLMs) have attained the impressive capability to resolve a wide range of NLP tasks by fine-tuning high-quality instruction data. However, collecting human-written data of high quality, especially multi-turn dialogues,…
Expository documents are vital resources for conveying complex information to readers. Despite their usefulness, writing expository text by hand is a challenging process that requires careful content planning, obtaining facts from multiple…
In recent years, large neural networks for natural language generation (NLG) have made leaps and bounds in their ability to generate fluent text. However, the tasks of evaluating quality differences between NLG systems and understanding how…
AI tools, particularly large language modules, have recently proven their effectiveness within learning management systems and online education programmes. As feedback continues to play a crucial role in learning and assessment in schools,…
While many BERT-based cross-modal pre-trained models produce excellent results on downstream understanding tasks like image-text retrieval and VQA, they cannot be applied to generation tasks directly. In this paper, we propose XGPT, a new…
A major challenge in the field of Text Generation is evaluation: Human evaluations are cost-intensive, and automated metrics often display considerable disagreement with human judgments. In this paper, we propose a statistical model of Text…
Automatically generating feedback via large language models (LLMs) in intelligent tutoring systems and online learning platforms has the potential to improve the learning outcomes of many students. However, both feedback generation and…
While GPT-2 generates sentences that are remarkably human-like, longer documents can ramble and do not follow human-like writing structure. We study the problem of imposing structure on long-range text. We propose a novel controlled text…
Prompt learning for vision-language models, e.g., CoOp, has shown great success in adapting CLIP to different downstream tasks, making it a promising solution for federated learning due to computational reasons. Existing prompt learning…
The rapid improvement of language models has raised the specter of abuse of text generation systems. This progress motivates the development of simple methods for detecting generated text that can be used by and explained to non-experts. We…
Recent advances in large language models (LLMs) and the abundance of food data have resulted in studies to improve food understanding using LLMs. Despite several recommendation systems utilizing LLMs and Knowledge Graphs (KGs), there has…
Recently, some E-commerce sites launch a new interaction box called Tips on their mobile apps. Users can express their experience and feelings or provide suggestions using short texts typically several words or one sentence. In essence,…
Existing generative pre-trained language models (e.g., GPT) focus on modeling the language structure and semantics of general texts. However, those models do not consider the numerical properties of numbers and cannot perform robustly on…
We introduce Reprompting, an iterative sampling algorithm that automatically learns the Chain-of-Thought (CoT) recipes for a given task without human intervention. Through Gibbs sampling, Reprompting infers the CoT recipes that work…
Incorporating external knowledge into the response generation process is essential to building more helpful and reliable dialog agents. However, collecting knowledge-grounded conversations is often costly, calling for a better pre-trained…
Decompilation converts machine code into human-readable form, enabling analysis and debugging without source code. However, fidelity issues often degrade the readability and semantic accuracy of decompiled output. Existing methods, such as…