DATA SCIENCE & SYSTEM SECURITY
PROJECTS
PEOPLE
PUBLICATIONS
PATENTS
Unstructured data is growing at an unprecedented rate, valuable knowledge, including findings, observations, business demand, opportunities, is widely recorded as texts in documents. We are developing advanced analysis engines for mining text data in documents, aiming to discover valuable knowledge from large-scale documents and provide informed decision-making for users.
This project focuses on document knowledge discovery utilizing advanced natural language processing, deep learning, and machine learning techniques. It builds innovative analytic engines to model the large amount of document data generated from various scenarios. The engines provide interpretable knowledge with low-resource requirements in different languages and domains, further helping customers understand and optimize the decision-making process.
In addition, this project focuses on advancing the state-of-the-art in NLP for document understanding. Toward this goal, efforts have been put into tasks like information extraction, language modeling, domain adaptation, intention detection, and contrastive augmentation. We also focus on providing solutions to different industries (e.g., financial, business, security, and systems) that can help customers with operation management and decision-making optimization. Some examples are document-based business matching, business process optimization, threat intelligence discovery, and log-based system management.
Team Members: Yanchi Liu, Xujiang Zhao, Wei Cheng, Haifeng Chen
This paper introduces the retrieval-augmented large language model with Definite Finite Automaton (DFA-RAG), a novel framework designed to enhance the capabilities of conversational agents using large language models (LLMs). Traditional LLMs face challenges in generating regulated and compliant responses
AI/ML techniques have been used to solve systems problems, but their applicability to customize solutions on-the-fly has been limited. Traditionally, any customization required manually changing the AI/ML model or modifying the code, configuration parameters, application settings, etc. This incurs too
Self-consistency has emerged as a powerful method for improving the accuracy of short answers generated by large language models. As previously defined, it only concerns the accuracy of a final answer parsed from generated text. In this work, we extend the idea to open response generation, by integrating
The recent progress in language-based object detection with an open-vocabulary can be largely attributed to finding better ways of leveraging large-scale data with free-form text annotations. Training from image captions with grounded bounding boxes (ground truth or pseudo-labeled) enable the models
Although planning is a crucial component of the autonomous driving stack, researchers have yet to develop robust planning algorithms that are capable of safely handling the diverse range of possible driving scenarios. Learning-based planners suffer from overfitting and poor long-tail performance. On
Large language models (LLMs) have significantly advanced the field of natural language processing (NLP), providing a highly useful, task agnostic foundation for a wide range of applications. The great promise of LLMs as general task solvers motivated people to extend their functionality largely beyond
It has been demonstrated that prompt tuning is highly effective in efficiently eliciting knowledge from language models (LMs). However, the prompt tuning still lags behind fine tuning, especially when the LMs are small. P tuning v2 (Liu et al., 2021b) makes it comparable with finetuning by adding continuous
