Search Results for author: Zhenting Qi

Found 8 papers, 6 papers with code

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

no code implementations27 Feb 2024 Zhenting Qi, HANLIN ZHANG, Eric Xing, Sham Kakade, Himabindu Lakkaraju

Retrieval-Augmented Generation (RAG) improves pre-trained models by incorporating external knowledge at test time to enable customized adaptation.

Instruction Following Retrieval

PILLOW: Enhancing Efficient Instruction Fine-tuning via Prompt Matching

no code implementations9 Dec 2023 Zhenting Qi, Xiaoyu Tan, Shaojie Shi, Chao Qu, Yinghui Xu, Yuan Qi

Instruction fine-tuning has conventionally been employed to adapt Large Language Models (LLMs) to a variety of tasks.

In-Context Learning

RobuT: A Systematic Study of Table QA Robustness Against Human-Annotated Adversarial Perturbations

1 code implementation25 Jun 2023 Yilun Zhao, Chen Zhao, Linyong Nan, Zhenting Qi, Wenlin Zhang, Xiangru Tang, Boyu Mi, Dragomir Radev

Despite significant progress having been made in question answering on tabular data (Table QA), it's unclear whether, and to what extent existing Table QA models are robust to task-specific perturbations, e. g., replacing key question entities or shuffling table columns.

Few-Shot Learning Question Answering

QTSumm: Query-Focused Summarization over Tabular Data

2 code implementations23 May 2023 Yilun Zhao, Zhenting Qi, Linyong Nan, Boyu Mi, Yixin Liu, Weijin Zou, Simeng Han, Ruizhe Chen, Xiangru Tang, Yumo Xu, Dragomir Radev, Arman Cohan

Motivated by this, we define a new query-focused table summarization task, where text generation models have to perform human-like reasoning and analysis over the given table to generate a tailored summary.

Query-focused Summarization Table-to-Text Generation

ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples

1 code implementation22 Oct 2022 Yilun Zhao, Linyong Nan, Zhenting Qi, Rui Zhang, Dragomir Radev

Reasoning over tabular data requires both table structure understanding and a broad set of table reasoning skills.

Ranked #3 on Semantic Parsing on WikiSQL (Denotation accuracy (test) metric)

Fact Verification Question Answering +3

Weakly Supervised Two-Stage Training Scheme for Deep Video Fight Detection Model

1 code implementation23 Sep 2022 Zhenting Qi, Ruike Zhu, Zheyu Fu, Wenhao Chai, Volodymyr Kindratenko

In this paper, we propose a simple but effective method that solves the task from a new perspective: we design the fight detection model as a composition of an action-aware feature extractor and an anomaly score generator.

Action Recognition Anomaly Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.