Related papers: CodeGENCAT: Generative Computerized Adaptive Testi…
Accurate knowledge selection is critical in knowledge-grounded dialogue systems. Towards a closer look at it, we offer a novel perspective to organize existing literature, i.e., knowledge selection coupled with, after, and before…
Many modern AI question-answering systems convert text into vectors and retrieve the closest matches to a user question. While effective for topical similarity, similarity scores alone do not explain why some retrieved text can serve as…
Code generation aims to automatically generate code snippets of specific programming language according to natural language descriptions. The continuous advancements in deep learning, particularly pre-trained models, have empowered the code…
Test-time adaptation offers a promising avenue for improving reasoning performance in large language models without additional supervision, but existing approaches often apply a uniform optimization objective across all inputs, leading to…
In this paper, we present a new open source toolkit for automatic speech recognition (ASR), named CAT (CRF-based ASR Toolkit). A key feature of CAT is discriminative training in the framework of conditional random field (CRF), particularly…
We present CODE-GEN, a human-in-the-Loop, retrieval-augmented generation (RAG)-based agentic AI system for generating context-aligned multiple-choice questions to develop student code reasoning and comprehension abilities. CODE-GEN employs…
Transformers achieve strong performance across diverse domains but implicitly assume Euclidean geometry in their attention mechanisms, limiting their effectiveness on data with non-Euclidean structure. While recent extensions to hyperbolic…
Generative Artificial Intelligence (AI), particularly tools like OpenAI's popular ChatGPT, is reshaping the landscape of computer science research. Used wisely, these tools can boost the productivity of a computer research scientist. This…
Inductive knowledge graph completion (KGC) aims to predict missing triples with unseen entities. Recent works focus on modeling reasoning paths between the head and tail entity as direct supporting evidence. However, these methods depend…
Knowledge tracing (KT) in programming education presents unique challenges due to the complexity of coding tasks and the diverse methods students use to solve problems. Although students' questions often contain valuable signals about their…
The rapid evolution of artificial intelligence (AI), specifically large language models (LLMs), has opened opportunities for various educational applications. This paper explored the feasibility of utilizing ChatGPT, one of the most popular…
Pre-trained Generative models such as BART, T5, etc. have gained prominence as a preferred method for text generation in various natural language processing tasks, including abstractive long-form question answering (QA) and summarization.…
Content is created for a well-defined purpose, often described by a metric or signal represented in the form of structured information. The relationship between the goal (metrics) of target content and the content itself is non-trivial.…
Expanding existing learning systems to provide high-quality customized models for more domains, such as new users, is challenged by the limited labeled data and the data and device heterogeneities. While knowledge distillation methods could…
This study explores the problem solving capabilities of ChatGPT and its prospective applications in standardized test preparation, focusing on the GRE quantitative exam. Prior research has shown great potential for the utilization of…
Current language models decode text token by token according to probabilistic distribution, and determining the appropriate candidates for the next token is crucial to ensure generation quality. This study introduces adaptive decoding, a…
The new capabilities of generative artificial intelligence tools Generative AI, such as ChatGPT, allow users to interact with the system in intuitive ways, such as simple conversations, and receive (mostly) good-quality answers. These…
Knowledge-intensive language tasks (KILT) usually require a large body of information to provide correct answers. A popular paradigm to solve this problem is to combine a search system with a machine reader, where the former retrieves…
In this study, we implement a novel BERT architecture for multitask fine-tuning on three downstream tasks: sentiment classification, paraphrase detection, and semantic textual similarity prediction. Our model, Multitask BERT, incorporates…
Conditional generative models map input variables to complex, high-dimensional distributions, enabling realistic sample generation in a diverse set of domains. A critical challenge with these models is the absence of calibrated uncertainty,…