Ryan A. Rossi

Domain Switch-Aware Holistic Recurrent Neural Network for Modeling Multi-Domain User Behavior

2019

Understanding user behavior and predicting future behavior on the web is critical for providing seamless user experiences as well as increasing revenue of service providers. Recently, thanks to the remarkable success of recurrent neural networks …

On Sampling from Massive Graph Streams

2017 · arXiv (Cornell University)

We propose Graph Priority Sampling (GPS), a new paradigm for order-based reservoir sampling from massive streams of graph edges. GPS provides a general way to weight edge sampling according to auxiliary and/or size variables so …

Graph Convolutional Networks with Motif-based Attention

2019

The success of deep convolutional neural networks in the domains of computer vision and speech recognition has led researchers to investigate generalizations of the said architecture to graph-structured data. A recently-proposed method called Graph Convolutional …

Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes

2024 · arXiv (Cornell University)

Large language models (LLMs) have shown remarkable advances in language generation and understanding but are also prone to exhibiting harmful social biases. While recognition of these behaviors has generated an abundance of bias mitigation techniques, …

Personalized Federated Learning for Text Classification with Gradient-Free Prompt Tuning

2024

In this paper, we study personalized federated learning for text classification with Pretrained Language Models (PLMs).We identify two challenges in efficiently leveraging PLMs for personalized federated learning: 1) Communication.PLMs are usually large in size, inducing …

Identifying Speakers in Dialogue Transcripts: A Text-based Approach Using Pretrained Language Models

2024 · arXiv (Cornell University)

We introduce an approach to identifying speaker names in dialogue transcripts, a crucial task for enhancing content accessibility and searchability in digital media archives. Despite the advancements in speech recognition, the task of text-based speaker …

LongLaMP: A Benchmark for Personalized Long-form Text Generation

2024 · arXiv (Cornell University)

Long-text generation is seemingly ubiquitous in real-world applications of large language models such as generating an email or writing a review. Despite the fundamental importance and prevalence of long-text generation in many practical applications, existing …

CachePrune: Teaching LLMs What Not to Follow via KV-Cache Editing

2026

Rui Wang, Junda Wu, Yu Xia, Tong Yu, Ruiyi Zhang, Ryan A. Rossi, Subrata Mitra, Lina Yao, Julian McAuley. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). …

Bias and Fairness in Large Language Models: A Survey

2024 · Computational Linguistics

Abstract Rapid advancements of large language models (LLMs) have enabled the processing, understanding, and generation of human-like text, with increasing integration into systems that touch our social sphere. Despite this success, these models can learn, …