Zhenting Qi

I am a first year Master’s student in Computational Science Engineering at Harvard University. Prior to Harvard, I received dual bachelor’s degree in Computer Engineering from UIUC and ZJU with highest honors.

Previously, I worked as research intern at Yale (2022-2023) with Professor Dragomir R. Radev, and at UIUC (2022) with Professor Volodymyr Kindratenko.

I am open to research or internship opportunities! Please contact me at zhentingqi[AT]g[DOT]harvard[DOT]edu.

CV Scholar Github Twitter

My research interest lies in Natural Language Processing (NLP). My long-term research goal is to build intelligent and reliable AI systems for the benefit of human society. Motivated by this goal, I am currently interested in the following topics (w/o particular order)

1) Reasoning: Why do current reasoning paradigms work? How can we design AIs to perform human-like reasoning?

2) Safety: How do we enhance the controllability, reliability, and robustness of AI? How can we design scalable method to ensure AIs’ safety while we are improving their capabilities?

For more information, please see Google Scholar, Semantic Scholar and DBLP.

Oct 10, 2023: Our papers QTSumm: A New Benchmark for Query-Focused Table Summarization, PILLOW: Efficient Instruction Fine-tuning via Prompt Matching under Low-Resource Settings (oral), Self-Criticism: Aligning Large Language Models with their Understanding of Helpfulness, Honesty, and Harmlessness (oral) has been accepted to EMNLP 2023.
Sep 1, 2023: I started a new journey at Harvard!
Jun 25, 2023: I graduated from Zhejiang University (ZJU) as an Outstanding Graduate.
Jun 01, 2023: I graduated from University of Illinois at Urbana-Champaign (UIUC) with Graduation with Highest Honors.
May 02, 2023: Our papers RobuT: A Systematic Study of Table QA Robustness Against Human-Annotated Adversarial Perturbations, SaFER: A Robust and Efficient Framework for Fine-tuning BERT-based Classifier with Noisy Labels, OpenRT: An Open-source Framework for Reasoning Over Tabular Data has been accepted to ACL 2023.
Feb 21, 2023: Our paper LoFT: Enhancing Faithfulness and Diversity for Table-to-Text Generation via Logic Form Control (oral) has been accepted to EACL 2023.
Oct 01, 2022: Our paper ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples has been accepted by EMNLP 2022.
May 25, 2022: I joined Yale LILY lab as a research intern.

Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems

Zhenting Qi, Hanlin Zhang, Eric Xing, Sham Kakade, Himabindu Lakkaraju

ICLR 2024 Workshop on Navigating and Addressing Data Problems for Foundation Models (DPFM)

We show that an adversary can exploit LMs' instruction-following capabilities to easily extract text data verbatim from the datastore of RAG systems built with instruction-tuned LMs via prompt injection.

PDF arXiv

PILLOW: Enhancing Efficient Instruction Fine-tuning via Prompt Matching

Zhenting Qi*, Xiaoyu Tan*, Shaojie Shi, Chao Qu, Yinghui Xu, Yuan Qi

EMNLP 2023, Industry Track Oral Presentation

We improve LoRA-finetuned LLMs with a prompt matching framework and reached performance on par with full SFT.

PDF arXiv

QTSumm: A New Benchmark for Query-Focused Table Summarization

Yilun Zhao, Zhenting Qi, Lingyong Nan, Boyu Mi, Yixin Liu, Weijin Zou, Simeng Han, Xiangru Tang, Yumo Xu, Arman Cohan, Dragomir Radev

EMNLP 2023

We introduce a new benchmark named QTSUMM for query-focused table summarization, which contains 7,111 human-annotated query-summary pairs over 2,934 tables covering diverse topics.

PDF arXiv

SaFER: A Robust and Efficient Framework for Finetuning BERT-based Classifier with Noisy Labels

Zhenting Qi*, Xiaoyu Tan*, Chao Qu, Yinghui Xu, Yuan Qi

ACL 2023, Industry Track

We propose a robust and efficient fine-tuning framework for BERT-based text classifiers, combating label noises without access to any clean data for training or validation.

PDF

LoFT: Enhancing Faithfulness and Diversity for Table-to-Text Generation via Logic Form Control

Yilun Zhao*, Zhenting Qi*, Lingyong Nan, Lorenzo Flores, Dragomir Radev

EACL 2023, Short Paper Oral Presentation

LOFT utilizes logic forms as fact verifiers and content planners to control Logical Table-to-Text generation.

Project Page PDF arXiv Code

FOLIO: Natural Language Reasoning with First-Order Logic

Simeng Han, Hailey Schoelkopf, Yilun Zhao, Zhenting Qi, Martin Riddell, Luke Benson, Lucy Sun, Ekaterina Zubova, Yujie Qiao, Matthew Burtell, David Peng, Jonathan Fan, Yixin Liu, Brian Wong, Malcolm Sailor, Ansong Ni, Lingyong Nan, Jungo Kasai, Tao Yu, Rui Zhang, Shafiq Joty, Alexander Fabbri, Wojciech Kryscinski, Xi Lin, Caiming Xiong, Dragomir Radev

Preprint 2022

We present FOLIO, a human-annotated, open-domain, and logically complex and diverse dataset for reasoning in natural language (NL), equipped with first order logic (FOL) annotations.