Publications

Improving Instruct Models for Free: A Study on Partial Adaptation.
Ozan İrsoy, Pengxiang Cheng, Jennifer L Chen, Daniel Preoțiuc-Pietro, Shiyue Zhang, and Duccio Pappadopulo. EMNLP, 2025.

Details

An Alternative to FLOPS Regularization to Effectively Productionize SPLADE-Doc.
Aldo Porco, Dhruv Mehra, Igor Malioutov, Karthik Radhakrishnan, Moniba Keymanesh, Daniel Preoțiuc-Pietro, Sean MacAvaney, and Pengxiang Cheng. SIGIR, 2025.

Details

Unsupervised Contrast-Consistent Ranking with Language Models.
Niklas Stoehr, Pengxiang Cheng, Jing Wang, Daniel Preoțiuc-Pietro, and Rajarshi Bhowmik. EACL, 2024.

Details

Overcoming Catastrophic Forgetting in Massively Multilingual Continual Learning.
Genta Winata, Lingjue Xie, Karthik Radhakrishnan, Shijie Wu, Xisen Jin, Pengxiang Cheng, Mayank Kulkarni, and Daniel Preoțiuc-Pietro. ACL Findings, 2023.

Details

Dataless Knowledge Fusion by Merging Weights of Language Models.
Xisen Jin, Xiang Ren, Daniel Preoțiuc-Pietro, and Pengxiang Cheng. ICLR, 2023.

Code Details

Attending to Entities for Better Text Understanding.
Pengxiang Cheng and Katrin Erk. AAAI, 2020.

Poster Details

The UTexas System for TAC 2019 SM-KBP Task 3: Hypothesis Detection with Graph Convolutional Networks.
Pengxiang Cheng, Alex Tomkovich, Eric Holgate, Su Wang, and Katrin Erk. TAC, 2019.

Poster

Implicit Argument Prediction as Reading Comprehension.
Pengxiang Cheng and Katrin Erk. AAAI, 2019.

Code Poster Details

The UTexas System for TAC SM-KBP Task 3: Probabilistic Generation of Coherent Hypotheses.
Pengxiang Cheng, Eric Holgate, and Katrin Erk. TAC, 2018.

Implicit Argument Prediction with Event Knowledge.
Pengxiang Cheng and Katrin Erk. NAACL, 2018.

Code Poster Details

Representing Meaning with a Combination of Logical and Distributional Models.
I. Beltagy, Stephen Roller, Pengxiang Cheng, Katrin Erk, and Raymond J. Mooney. Computational Linguistics, 2016.

Details