Search Results for author: Xuchao Zhang

Found 39 papers, 14 papers with code

Exploring LLM-based Agents for Root Cause Analysis

no code implementations7 Mar 2024 Devjeet Roy, Xuchao Zhang, Rashi Bhave, Chetan Bansal, Pedro Las-Casas, Rodrigo Fonseca, Saravan Rajmohan

Lastly, we conduct a case study with a team at Microsoft to equip the ReAct agent with tools that give it access to external diagnostic services that are used by the team for manual RCA.

Management Retrieval

Uncertainty Decomposition and Quantification for In-Context Learning of Large Language Models

1 code implementation15 Feb 2024 Chen Ling, Xujiang Zhao, Wei Cheng, Yanchi Liu, Yiyou Sun, Xuchao Zhang, Mika Oishi, Takao Osaki, Katsushi Matsuda, Jie Ji, Guangji Bai, Liang Zhao, Haifeng Chen

Existing works have been devoted to quantifying the uncertainty in LLM's response, but they often overlook the complex nature of LLMs and the uniqueness of in-context learning.

Hallucination In-Context Learning

Automated Root Causing of Cloud Incidents using In-Context Learning with GPT-4

no code implementations24 Jan 2024 Xuchao Zhang, Supriyo Ghosh, Chetan Bansal, Rujia Wang, Minghua Ma, Yu Kang, Saravan Rajmohan

The results reveal that our in-context learning approach outperforms the previous fine-tuned large language models such as GPT-3 by an average of 24. 8\% across all metrics, with an impressive 49. 7\% improvement over the zero-shot model.

In-Context Learning

Open-ended Commonsense Reasoning with Unrestricted Answer Scope

no code implementations18 Oct 2023 Chen Ling, Xuchao Zhang, Xujiang Zhao, Yanchi Liu, Wei Cheng, Mika Oishi, Takao Osaki, Katsushi Matsuda, Haifeng Chen, Liang Zhao

In this work, we leverage pre-trained language models to iteratively retrieve reasoning paths on the external knowledge base, which does not require task-specific supervision.

Question Answering Retrieval

PACE-LM: Prompting and Augmentation for Calibrated Confidence Estimation with GPT-4 in Cloud Incident Root Cause Analysis

no code implementations11 Sep 2023 Dylan Zhang, Xuchao Zhang, Chetan Bansal, Pedro Las-Casas, Rodrigo Fonseca, Saravan Rajmohan

Major cloud providers have employed advanced AI-based solutions like large language models to aid humans in identifying the root causes of cloud incidents.

Decision Making

TART: Improved Few-shot Text Classification Using Task-Adaptive Reference Transformation

1 code implementation3 Jun 2023 Shuo Lei, Xuchao Zhang, Jianfeng He, Fanglan Chen, Chang-Tien Lu

Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieve state-of-the-art performance.

Few-Shot Text Classification Meta-Learning +1

Time Series Contrastive Learning with Information-Aware Augmentations

1 code implementation21 Mar 2023 Dongsheng Luo, Wei Cheng, Yingheng Wang, Dongkuan Xu, Jingchao Ni, Wenchao Yu, Xuchao Zhang, Yanchi Liu, Yuncong Chen, Haifeng Chen, Xiang Zhang

A key component of contrastive learning is to select appropriate augmentations imposing some priors to construct feasible positive samples, such that an encoder can be trained to learn robust and discriminative representations.

Contrastive Learning Open-Ended Question Answering +2

Knowledge-enhanced Neural Machine Reasoning: A Review

no code implementations4 Feb 2023 Tanmoy Chowdhury, Chen Ling, Xuchao Zhang, Xujiang Zhao, Guangji Bai, Jian Pei, Haifeng Chen, Liang Zhao

Knowledge-enhanced neural machine reasoning has garnered significant attention as a cutting-edge yet challenging research area with numerous practical applications.

Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models

no code implementations10 Jan 2023 Toufique Ahmed, Supriyo Ghosh, Chetan Bansal, Thomas Zimmermann, Xuchao Zhang, Saravan Rajmohan

In this work, we do the first large-scale study to evaluate the effectiveness of these models for helping engineers root cause and mitigate production incidents.

Management Question Answering +1

DeepGAR: Deep Graph Learning for Analogical Reasoning

1 code implementation19 Nov 2022 Chen Ling, Tanmoy Chowdhury, Junji Jiang, Junxiang Wang, Xuchao Zhang, Haifeng Chen, Liang Zhao

As the most well-known computational method of analogical reasoning, Structure-Mapping Theory (SMT) abstracts both target and base subjects into relational graphs and forms the cognitive process of analogical reasoning by finding a corresponding subgraph (i. e., correspondence) in the target graph that is aligned with the base graph.

Graph Learning

CAT: Beyond Efficient Transformer for Content-Aware Anomaly Detection in Event Sequences

1 code implementation ACM SIGKDD Conference on Knowledge Discovery and Data Mining 2022 Shengming Zhang, Yanchi Liu, Xuchao Zhang, Wei Cheng, Haifeng Chen, Hui Xiong

It is critical and important to detect anomalies in event sequences, which becomes widely available in many application domains. In-deed, various efforts have been made to capture abnormal patterns from event sequences through sequential pattern analysis or event representation learning. However, existing approaches usually ignore the semantic information of event content. To this end, in this paper, we propose a self-attentive encoder-decoder transformer framework, Content-Aware Transformer(CAT), for anomaly detection in event sequences. In CAT, the encoder learns preamble event sequence representations with content awareness, and the decoder embeds sequences under detection into a latent space, where anomalies are distinguishable. Specifically, the event content is first fed to a content-awareness layer, generating representations of each event. The encoder accepts preamble event representation sequence, generating feature maps. In the decoder, an additional token is added at the beginning of the sequence under detection, denoting the sequence status. A one-class objective together with sequence reconstruction loss is collectively applied to train our framework under the label efficiency scheme. Furthermore, CAT is optimized under a scalable and efficient setting. Finally, extensive experiments on three real-world datasets demonstrate the superiority of CAT.

Anomaly Detection

SEED: Sound Event Early Detection via Evidential Uncertainty

no code implementations5 Feb 2022 Xujiang Zhao, Xuchao Zhang, Wei Cheng, Wenchao Yu, Yuncong Chen, Haifeng Chen, Feng Chen

Sound Event Early Detection (SEED) is an essential task in recognizing the acoustic environments and soundscapes.

Event Detection Sound Event Detection

Do Multi-Lingual Pre-trained Language Models Reveal Consistent Token Attributions in Different Languages?

no code implementations23 Dec 2021 Junxiang Wang, Xuchao Zhang, Bo Zong, Yanchi Liu, Wei Cheng, Jingchao Ni, Haifeng Chen, Liang Zhao

During the past several years, a surge of multi-lingual Pre-trained Language Models (PLMs) has been proposed to achieve state-of-the-art performance in many cross-lingual downstream tasks.

Zero-Shot Cross-Lingual Machine Reading Comprehension via Inter-sentence Dependency Graph

1 code implementation1 Dec 2021 Liyan Xu, Xuchao Zhang, Bo Zong, Yanchi Liu, Wei Cheng, Jingchao Ni, Haifeng Chen, Liang Zhao, Jinho D. Choi

We target the task of cross-lingual Machine Reading Comprehension (MRC) in the direct zero-shot setting, by incorporating syntactic features from Universal Dependencies (UD), and the key features we use are the syntactic relations within each sentence.

Machine Reading Comprehension Sentence

Information-Aware Time Series Meta-Contrastive Learning

no code implementations29 Sep 2021 Dongsheng Luo, Wei Cheng, Yingheng Wang, Dongkuan Xu, Jingchao Ni, Wenchao Yu, Xuchao Zhang, Yanchi Liu, Haifeng Chen, Xiang Zhang

How to find the desired augmentations of time series data that are meaningful for given contrastive learning tasks and datasets remains an open question.

Contrastive Learning Meta-Learning +4

Code Editing from Few Exemplars by Adaptive Multi-Extent Composition

no code implementations29 Sep 2021 Peizhao Li, Xuchao Zhang, Ziyu Yao, Wei Cheng, Haifeng Chen, Hongfu Liu

To achieve this, we propose a machine learning approach to adapt the editorial style derived from few exemplars to a query code snippet.

Boosting Cross-Lingual Transfer via Self-Learning with Uncertainty Estimation

1 code implementation EMNLP 2021 Liyan Xu, Xuchao Zhang, Xujiang Zhao, Haifeng Chen, Feng Chen, Jinho D. Choi

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.

Cross-Lingual Transfer named-entity-recognition +4

Unsupervised Document Embedding via Contrastive Augmentation

1 code implementation26 Mar 2021 Dongsheng Luo, Wei Cheng, Jingchao Ni, Wenchao Yu, Xuchao Zhang, Bo Zong, Yanchi Liu, Zhengzhang Chen, Dongjin Song, Haifeng Chen, Xiang Zhang

We present a contrasting learning approach with data augmentation techniques to learn document representations in an unsupervised manner.

Contrastive Learning Data Augmentation +4

Dynamic Gaussian Mixture based Deep Generative Model For Robust Forecasting on Sparse Multivariate Time Series

1 code implementation3 Mar 2021 Yinjun Wu, Jingchao Ni, Wei Cheng, Bo Zong, Dongjin Song, Zhengzhang Chen, Yanchi Liu, Xuchao Zhang, Haifeng Chen, Susan Davidson

Forecasting on sparse multivariate time series (MTS) aims to model the predictors of future values of time series given their incomplete past, which is important for many emerging applications.

Clustering Time Series +1

Aspect-based Sentiment Classification via Reinforcement Learning

no code implementations1 Jan 2021 Lichen Wang, Bo Zong, Yunyu Liu, Can Qin, Wei Cheng, Wenchao Yu, Xuchao Zhang, Haifeng Chen, Yun Fu

As texts always contain a large proportion of task-irrelevant words, accurate alignment between aspects and their sentimental descriptions is the most crucial and challenging step.

Classification General Classification +4

Semantic Editing On Segmentation Map Via Multi-Expansion Loss

no code implementations16 Oct 2020 Jianfeng He, Xuchao Zhang, Shuo Lei, Shuhui Wang, Qingming Huang, Chang-Tien Lu, Bei Xiao

Each MEx area has the mask area of the generation as the majority and the boundary of original context as the minority.

Image Inpainting Segmentation

Few-Shot Semantic Segmentation Augmented with Image-Level Weak Annotations

no code implementations3 Jul 2020 Shuo Lei, Xuchao Zhang, Jianfeng He, Fanglan Chen, Chang-Tien Lu

Despite the great progress made by deep neural networks in the semantic segmentation task, traditional neural-networkbased methods typically suffer from a shortage of large amounts of pixel-level annotations.

Few-Shot Semantic Segmentation Segmentation +1

Corpus-level and Concept-based Explanations for Interpretable Document Classification

1 code implementation24 Apr 2020 Tian Shi, Xuchao Zhang, Ping Wang, Chandan K. Reddy

In this paper, we propose a corpus-level explanation approach, which aims to capture causal relationships between keywords and model predictions via learning the importance of keywords for predicted labels across a training corpus based on attention weights.

Classification Decision Making +2

Modeling the Relationship between User Comments and Edits in Document Revision

no code implementations IJCNLP 2019 Xuchao Zhang, Dheeraj Rajagopal, Michael Gamon, Sujay Kumar Jauhar, Chang-Tien Lu

Thus, in this paper we explore the relationship between comments and edits by defining two novel, related tasks: Comment Ranking and Edit Anchoring.

Management

Mitigating Uncertainty in Document Classification

1 code implementation NAACL 2019 Xuchao Zhang, Fanglan Chen, Chang-Tien Lu, Naren Ramakrishnan

The uncertainty measurement of classifiers' predictions is especially important in applications such as medical diagnoses that need to ensure limited human resources can focus on the most uncertain predictions returned by machine learning models.

Document Classification General Classification +2

Robust Regression via Online Feature Selection under Adversarial Data Corruption

no code implementations5 Feb 2019 Xuchao Zhang, Shuo Lei, Liang Zhao, Arnold P. Boedihardjo, Chang-Tien Lu

The presence of data corruption in user-generated streaming data, such as social media, motivates a new fundamental problem that learns reliable regression coefficient when features are not accessible entirely at one time.

feature selection regression

Water Disaggregation via Shape Features based Bayesian Discriminative Sparse Coding

no code implementations26 Aug 2018 Bingsheng Wang, Xuchao Zhang, Chang-Tien Lu, Feng Chen

As the issue of freshwater shortage is increasing daily, it is critical to take effective measures for water conservation.

Distributed Self-Paced Learning in Alternating Direction Method of Multipliers

no code implementations6 Jul 2018 Xuchao Zhang, Liang Zhao, Zhiqian Chen, Chang-Tien Lu

One key issue in SPL is the training process required for each instance weight depends on the other samples and thus cannot easily be run in a distributed manner in a large-scale dataset.

Multimodal Storytelling via Generative Adversarial Imitation Learning

no code implementations5 Dec 2017 Zhiqian Chen, Xuchao Zhang, Arnold P. Boedihardjo, Jing Dai, Chang-Tien Lu

Deriving event storylines is an effective summarization method to succinctly organize extensive information, which can significantly alleviate the pain of information overload.

Imitation Learning

Online and Distributed Robust Regressions under Adversarial Data Corruption

no code implementations2 Oct 2017 Xuchao Zhang, Liang Zhao, Arnold P. Boedihardjo, Chang-Tien Lu

In today's era of big data, robust least-squares regression becomes a more challenging problem when considering the adversarial corruption along with explosive growth of datasets.

regression

Cannot find the paper you are looking for? You can Submit a new open access paper.