Jiacheng Xu

Email: jcxu17 at gmail.com

Hi, I am Jiacheng Xu, a research scientist at Salesforce AI Research.

I passed my Ph.D. defense from the Department of Computer Science at the UT Austin. I worked in the Text Analysis, Understanding, and Reasoning Group under Greg Durrett. My research focuses on natural language processing and machine learning, specifically the area of text generation.

    (1) Long chain-of-actions for agentic code llms (Xu'25, Zhang'25, ongoing;) ;
    (2) Decoding algorithms to yield a massive number of high-quality and diverse outputs (XJD22, XXSZ23, SXYD23; slides) ;

Before I came to UT Austin, I obtained my bachelor's degree from Fudan University in 2017. From 2015 to 2017, I was a member of FudanNLP, advised by Prof. Xipeng Qiu.

My CV is here.

Google Scholar   Twitter   LinkedIn

Publications

CLOVER: A Test Case Generation Benchmark with Coverage, Long-Context, and Verification
Jiacheng Xu, Bo Pang, Jin Qu, Hiroaki Hayashi, Caiming Xiong, Yingbo Zhou, arXiv preprint 2025.

BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation
Bo Pang, Hanze Dong, Jiacheng Xu, Silvio Savarese, Yingbo Zhou, Caiming Xiong, arXiv preprint 2025.

Diversity empowers intelligence: Integrating expertise of software engineering agents
Kexun Zhang et al., ICLR 2025.

A Long Way to Go: Investigating Length Correlations in RLHF
Prasann Singhal, Tanya Goyal, Jiacheng Xu, Greg Durrett, COLM 2024.

Best-k Search Algorithm for Neural Text Generation
Jiacheng Xu, Caiming Xiong, Silvio Savarese, Yingbo Zhou, ACL 2023.

EEL: Efficiently Encoding Lattices for Reranking
Prasann Singhal, Jiacheng Xu, Xi Ye, Greg Durrett, ACL 2023.

Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectors
Liyan Tang, Tanya Goyal, Alexander R. Fabbri, Philippe Laban, Jiacheng Xu, Semih Yahvuz, Wojciech Kryściński, Justin F. Rousseau, Greg Durrett, ACL 2023.

Massive-scale Decoding for Text Generation using Lattices
Jiacheng Xu, Siddhartha Reddy Jonnalagadda, and Greg Durrett, NAACL 2022.

Training Dynamics for Text Summarization Models
Tanya Goyal, Jiacheng Xu, Junyi Jessy Li, and Greg Durrett, Findings of ACL 2022.

ASPECTNEWS: Aspect-Oriented Summarization of News Documents
Ojas Ahuja, Jiacheng Xu, Akshay Gupta, Kevin Horecka, and Greg Durrett, ACL 2022.

Dissecting Generation Modes for Abstractive Summarization Models via Ablation and Attribution
Jiacheng Xu, and Greg Durrett, ACL 2021. slides

Disfl-QA: A Benchmark Dataset for Understanding Disfluencies in Question Answering
Aditya Gupta, Jiacheng Xu, Shyam Upadhyay, Diyi Yang and Manaal Faruqui, Findings of ACL 2021. press

Understanding Neural Abstractive Summarization Models via Uncertainty
Jiacheng Xu, Shrey Desai, and Greg Durrett, EMNLP 2020 (short). code slides

Compressive Summarization with Plausibility and Salience Modeling
Shrey Desai, Jiacheng Xu, and Greg Durrett, EMNLP 2020.

Discourse-Aware Neural Extractive Model for Text Summarization
Jiacheng Xu, Zhe Gan, Yu Cheng and Jingjing Liu, ACL 2020. code

Neural Extractive Text Summarization with Syntactic Compression
Jiacheng Xu and Greg Durrett, EMNLP 2019. code

Spherical Latent Spaces for Stable Variational Autoencoders
Jiacheng Xu and Greg Durrett, EMNLP 2018. code slides

Incorporating Discriminator in Sentence Generation: A Gibbs Sampling Method
Jinyue Su, Jiacheng Xu, Xipeng Qiu, Xuanjing Huang, AAAI 2018.

Knowledge Graph Representation with Jointly Structural and Textual Encoding
Jiacheng Xu, Xipeng Qiu, Kan Chen, Xuanjing Huang, IJCAi 2017.

Cached Long Short-Term Memory Neural Networks for Document-Level Sentiment Classification
Jiacheng Xu, Danlu Chen, Xipeng Qiu, Xuanjing Huang, EMNLP 2016.

Service

Reviewer: ICML, COLM

AC: ACL ARR