Junbo Zhao

A Comparative Study of in-Database Inference Approaches

2022 · 2022 IEEE 38th International Conference on Data Engineering (ICDE)

In Alibaba's IoT platform, we face the challenge of processing analytical queries involving both structured and unstructured data. Normally, collaborative queries need deep learning (DL) models and relational algebras to work intertwined to produce sophisticated …

Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models

2023 · arXiv (Cornell University)

The prompt-based learning paradigm, which bridges the gap between pre-training and fine-tuning, achieves state-of-the-art performance on several NLP tasks, particularly in few-shot settings. Despite being widely applied, prompt-based learning is vulnerable to backdoor attacks. Textual …

Assessing Hidden Risks of LLMs: An Empirical Study on Robustness, Consistency, and Credibility

2023 · arXiv (Cornell University)

The recent popularity of large language models (LLMs) has brought a significant impact to boundless fields, particularly through their open-ended ecosystem such as the APIs, open-sourced models, and plugins. However, with their widespread deployment, there …

ProMix: Combating Label Noise via Maximizing Clean Sample Utility

2023

Learning with Noisy Labels (LNL) has become an appealing topic, as imperfectly annotated data are relatively cheaper to obtain. Recent state-of-the-art approaches employ specific selection mechanisms to separate clean and noisy samples and then apply …

DataMan: Data Manager for Pre-training Large Language Models

2025 · arXiv (Cornell University)

The performance emergence of large language models (LLMs) driven by data scaling laws makes the selection of pre-training data increasingly important. However, existing methods rely on limited heuristics and human intuition, lacking comprehensive and clear …

Character-level Convolutional Networks for Text Classification

2015 · arXiv (Cornell University)

This article offers an empirical exploration on the use of character-level convolutional networks (ConvNets) for text classification. We constructed several large-scale datasets to show that character-level convolutional networks could achieve state-of-the-art or competitive results. Comparisons …

Levenshtein Transformer

2019 · Neural Information Processing Systems

Modern neural sequence generation models are built to either generate tokens step-by-step from scratch or (iteratively) modify a sequence of tokens bounded by a fixed length. In this work, we develop Levenshtein Transformer, a new …