Project Grant 2545884
- This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Project Grant award (CFDA 47.070) for $385,000 will enable the University of Maryland, College Park to develop artificial intelligence (AI) systems that can provide personalized, appropriate responses to users based on their individual background and needs. The project aims to first construct a diverse dataset to characterize preferred responses from different user groups, and then use this to train AI...
- This Project Grant award of $347,549 from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program supports research to advance interactive language systems that can critically reason about and synthesize information from rich knowledge sources. The research aims to develop data-centric and algorithmic approaches to model the complexities of real-world scenarios, where users' questions are ambiguous, answers continuously change based on context, and...
- This award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) provides $360,000 to the University of Illinois to develop "HPCGPT", a question-answering service that leverages generative AI and integrates data sources to enhance the user support services at academic high-performance computing (HPC) centers. In collaboration with Princeton University and Rutgers University, the project aims to improve the quality,...
- This Project Grant award of $175,000 from the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) program advances trustworthy artificial intelligence (AI) by developing methods to integrate large language models with structured knowledge graphs. The research, conducted by the University of California, Merced, aims to create more reliable and accurate AI-powered question answering systems. The key technical advances include synergistic knowledge...
- This $340,217 federal Project Grant award, effective August 1, 2025 through July 31, 2030, was provided by the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) to the University of Maryland, College Park. The project aims to develop innovative AI-based tools to help individuals with limited proficiency in the majority language improve their language skills for effective information seeking in daily activities. The digital...
- This $300,000 Project Grant award was provided by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CISE) federal grant program (CFDA 47.070) to Cornell University. The grant aims to develop new evaluation concepts and technologies for assessing and improving large language models (LLMs) used in text summarization and generation applications. The project will create a concept taxonomy and customized reward models to evaluate LLM responses across...
- This $449,966 Project Grant award from the National Science Foundation's (NSF) Social, Behavioral, and Economic Sciences (SBE) program (CFDA 47.075) supports research to quantify and analyze the concept of "question under discussion" in naturalistic discourse and investigate how uncertainty regarding the relevant question impacts language comprehension. The project aims to construct open-access corpora for naturalistic discourse in two languages, with rich annotation of question...
- This Project Grant award from the National Science Foundation (NSF) under CFDA Program 47.070 (Computer and Information Science and Engineering) provides $145,000 to develop a time series text-based cross-modality question answering (QA) system. The award aims to address three key challenges in using large language models (LLMs) for time series data analysis: (1) lack of high-quality text information aligned with time series data, (2) under-research in deep learning models that can reason with...
- This $392,993 Project Grant from the National Science Foundation's Computer and Information Science and Engineering program aims to develop more accessible and reliable machine translation technology. The University of Maryland, College Park will work with sub-awardee University of California, Berkeley to advance natural language processing and human-computer interaction techniques. Specifically, the project will create a conversational bot to guide lay users through text-based machine...
- This $546,000 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) will support research at the Pennsylvania State University (Penn State) to advance trustworthy, human-centered summarization capabilities utilizing large language models. The research aims to develop novel summarization techniques that incorporate fine-grained user preferences, address fairness and bias, and honor human knowledge. The...
This Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program, CFDA 47.070, aims to enable automatic question-answering systems to produce paragraph-level answers. The $426,960 award to the University of Maryland, College Park, made on September 1, 2025, will focus on three core areas: developing multilingual long-form question-answering datasets, creating new modeling approaches that integrate retrieved documents with language model knowledge, and engaging domain experts to evaluate generated answers. This research will expand prior English-centric work on long-form question answering and investigate knowledge transfer across languages, with the goal of enabling more nuanced and comprehensive responses to complex questions.
Mod # | Description | ReasonForModification | Federal Obligation | Date |
|---|---|---|---|---|
| Not listed | $427.0k | 8/20/25 |