Tianyi Zhang

Automated Transplantation and Differential Testing for Clones

2017

Code clones are common in software. When applying similar edits to clones, developers often find it difficult to examine the runtime behavior of clones. The problem is exacerbated when some clones are tested, while their …

Human-in-the-loop Schema Induction

2023

Tianyi Zhang, Isaac Tham, Zhaoyi Hou, Jiaxuan Ren, Leon Zhou, Hainiu Xu, Li Zhang, Lara J. Martin, Rotem Dror, Sha Li, Heng Ji, Martha Palmer, Susan Windisch Brown, Reece Suchocki, Chris Callison-Burch. Proceedings of the …

Human Latency Conversational Turns for Spoken Avatar Systems

2024 · arXiv (Cornell University)

A problem with many current Large Language Model (LLM) driven spoken dialogues is the response time. Some efforts such as Groq address this issue by lightning fast processing of the LLM, but we know from …

STILE: Exploring and Debugging Social Biases in Pre-trained Text Representations

2024

The recent success of Natural Language Processing (NLP) relies heavily on pre-trained text representations such as word embeddings. However, pre-trained text representations may exhibit social biases and stereotypes, e.g., disproportionately associating gender with occupations. Though …

Convolutional Unscented Kalman Filter for Multi-Object Tracking With Outliers

2024 · IEEE Transactions on Intelligent Vehicles

Multi-object tracking (MOT) is an essential technique for navigation in autonomous driving. In tracking-by-detection systems, biases, false positives, and misses, which are referred to as outliers, are inevitable due to complex traffic scenarios. Recent tracking …

AutoJournaling: A Context-Aware Journaling System Leveraging MLLMs on Smartphone Screenshots

2024 · arXiv (Cornell University)

Journaling offers significant benefits, including fostering self-reflection, enhancing writing skills, and aiding in mood monitoring. However, many people abandon the practice because traditional journaling is time-consuming, and detailed life events may be overlooked if not …

Code Comment Inconsistency Detection and Rectification Using a Large Language Model

2025

Comments are widely used in source code. If a comment is consistent with the code snippet it intends to annotate, it would aid code comprehension. Otherwise, Code Comment Inconsistency (CCI) is not only detrimental to …

BERTScore: Evaluating Text Generation with BERT

2019 · arXiv (Cornell University)

We propose BERTScore, an automatic evaluation metric for text generation. Analogously to common metrics, BERTScore computes a similarity score for each token in the candidate sentence with each token in the reference sentence. However, instead …

BERTScore: Evaluating Text Generation with BERT

2020 · arXiv (Cornell University)

We propose BERTScore, an automatic evaluation metric for text generation. Analogously to common metrics, BERTScore computes a similarity score for each token in the candidate sentence with each token in the reference sentence. However, instead …

Benchmarking Large Language Models for News Summarization

2024 · Transactions of the Association for Computational Linguistics

Abstract Large language models (LLMs) have shown promise for automatic summarization but the reasons behind their successes are poorly understood. By conducting a human evaluation on ten LLMs across different pretraining methods, prompts, and model …