PROJECTS
PEOPLE
PUBLICATIONS
PATENTS
Data Science and System Security
Xujiang Zhao is a researcher in the Data Science & System Security department at NEC Laboratories America, based in Princeton, New Jersey. He holds a B.S. in Civil Engineering from Chongqing University and an M.S. in Computer Science from the University of Science and Technology of China. He earned his PhD in Computer Science from the University of Texas at Dallas, and his academic training provided a strong foundation in both theoretical and applied aspects of computing, which continues to shape his contributions at NEC.
At NEC Labs, Zhao’s research focuses on aligning large language models (LLMs) with human intent through techniques that enhance explainability, factual consistency, uncertainty estimation, and robustness. He develops methods that make LLMs more transparent and reliable, ensuring that they can be applied in sensitive, high-stakes environments. A key area of his work is building collaborative agent systems that integrate LLMs with domain-specific expertise and human feedback loops, enabling AI to work more effectively as a partner in decision-making.
Beyond language alignment, Zhao explores applications in image–text retrieval, synthetic media detection, and multi-agent reasoning, areas that are increasingly critical for enterprise knowledge management, misinformation defense, and the verification of AI-generated content. By combining fundamental advances in machine learning with applied research, his work pushes forward the responsible and practical use of foundation models across industries.
Overview: 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.
Our researcher Xujiang Zhao will present “Uncertainty Quantification and Reasoning for Reliable AI” at Brigham Young University on Thursday, Sept. 25 at 11 a.m. in TMCB 1170. The seminar explores how statistical modeling and reasoning frameworks can strengthen trustworthy AI, making systems more
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. However, directly applying LLMs to solve sophisticated problems in specific domains meets many hurdles, caused
Large language models (LLMs) integrated into multi-step agent systems enable complex decision-making processes across various applications. However, their outputs often lack reliability, making uncertainty estimation crucial. Existing uncertainty estimation methods primarily focus on final-step outputs,
The Out-of-Distribution (OOD) problem in graph-structured data is becoming increasingly important in various areas of research and applications, including social network recommendation [36], protein function detection [9, 21], etc. Furthermore, owing to the inherent multi-label properties of nodes, multi-label
Prompt tuning is highly effective in efficiently extracting knowledge from foundation models, encompassing both language, vision, and vision-language models. However, the efficacy of employing fixed soft prompts with a predetermined position for concatenation with inputs for all instances, irrespective
Large Language Models (LLMs) exhibit potential artificial generic intelligence recently, however, their usage is costly with high response latency. Given mixed LLMs with their own strengths and weaknesses, LLM routing aims to identify the most suitable model for each query in the stream to maximize response
We frame code generation as a black-box optimization problem within the code space and demonstrate how optimization-inspired techniques can enhance inference scaling. Based on this perspective, we propose SCATTERED FOREST SEARCH (SFS), a novel approach that improves solution diversity and better exploits
The proliferation of Large Language Models (LLMs) has driven considerable interest in fine-tuning them with domain-specific data to create specialized language models. Nevertheless, such domain-specific fine-tuning data often contains contextually sensitive personally identifiable information (PII).
Recognizing domain generalization as a commonplace challenge in machine learning, data distribution might progressively evolve across a continuum of sequential domains in practical scenarios. While current methodologies primarily concentrate on bolstering model effectiveness within these new domains,
The objective of change point detection is to identify abrupt changes at potentially multiple points within a data sequence. This task is particularly challenging in the online setting where various types of changes can occur, including shifts in both the marginal and joint distributions of the data.
Neural language models for commonsense reasoning often formulate the problem as a QA task and make predictions based on learned representations of language after fine-tuning. However, without providing any fine-tuning data and pre-defined answer candidates, can neural language models still answer commonsense
Large Language Models (LLMs) have exhibited remarkable proficiency across a wide array of NLP tasks. However, the escalation in model size also engenders substantial deployment costs. While few efforts have explored model pruning techniques to reduce the size of LLMs, they mainly center on general or
In-context learning has emerged as a groundbreaking ability of Large Language Models (LLMs) and revolutionized various fields by providing a few task-relevant demonstrations in the prompt. However, trustworthy issues with LLMs response, such as hallucination, have also been actively discussed. Existing
In today’s world, with its complex global supply chains, the difficulties and uncertainties we face offer both challenges and opportunities for making things better, especially in terms of efficiency and sustainability. These challenges grow due to unpredictable events, such as natural disasters, unexpected
Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text, typically in the form of (subject, relation, object) triples. Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods
Open-ended Commonsense Reasoning is defined as solving a commonsense question without providing 1) a short list of answer candidates and 2) a pre-defined answer scope. Conventional ways of formulating the commonsense question into a question-answering form or utilizing external knowledge to learn retrieval-based
Graph neural networks (GNNs) have achieved great success in dealing with graph-structured data that are prevalent in the real world. The core of graph neural networks is the message passing mechanism that aims to generate the embeddings of nodes by aggregating the neighboring node information. However,
For example, in machine translation tasks, to achieve bidirectional translation between two languages, the source corpus is often used as the target corpus, which involves the training of two models with opposite directions. The question of which one can adapt most quickly to a domain shift is of significant
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
Early event detection aims to detect events even before the event is complete. However, most of the existing methods focus on an event with a single label but fail to be applied to cases with multiple labels. Another non-negligible issue for early event detection is a prediction with overconfidence due
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
Sound Event Early Detection (SEED) is an essential task in recognizing the acoustic environments and soundscapes. However, most of the existing methods focus on the offline sound event detection, which suffers from the over-confidence issue of early-stage event detection and usually yield unreliable
Recent multilingual pre-trained language models have achieved remarkable zero-shot performance, where the model is only finetuned on one source language and directly evaluated on target languages. In this work, we propose a self-learning framework that further utilizes unlabeled data of target languages,
