Yifan Ding

Yifan Ding

Auto-generated profile, based on publicly available information

Yifan Ding

University of Notre Dame 2 Amazon

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
YDYifan Ding
Yifan Ding
MFMatthew Facciani
Matthew Facciani
EJEllen Joyce
Ellen Joyce
APAmrit Poudel
Amrit Poudel
SBSanmitra Bhattacharya
Sanmitra Bhattacharya
TWTim Weninger
Tim Weninger
Question answering systems are rapidly advancing, but their opaque nature may impact user trust. We explored trust through an anti-monitoring framework, where trust is predicted to be correlated with presence of citations and inversely related to checking citations. We tested this hypothesis with a live question-answering experiment that presented text responses generated using a commercial Chatbot along with varying citations (zero, one, or five), both relevant and random, and recorded if participants checked the citations and their self-reported trust in the generated responses. We found a significant increase in trust when citations were present, a result that held true even when the citations were random; we also found a significant decrease in trust when participants checked the citations. These results highlight the importance of citations in enhancing trust in AI-generated content.

1 January 2022
Verified
Conference Paper
Open access
PDF file
YDYifan Ding
Yifan Ding
YLYan Liang
Yan Liang
NZNasser Zalmout
Nasser Zalmout
XLXian Li
Xian Li
CGChristan Grant
Christan Grant
TWTim Weninger
Tim Weninger
Yifan Ding, Yan Liang, Nasser Zalmout, Xian Li, Christan Grant, Tim Weninger. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track. 2022.

2 June 2021 in arXiv
Verified
Preprint
Open access
PDF file
YDYifan Ding
Yifan Ding
NBNicholas Botzer
Nicholas Botzer
TWTim Weninger
Tim Weninger
Classifiers commonly make use of pre-annotated datasets, wherein a model is evaluated by pre-defined metrics on a held-out test set typically made of human-annotated labels. Metrics used in these evaluations are tied to the availability of well-defined ground truth labels, and these metrics typically do not allow for inexact matches. These noisy ground truth labels and strict evaluation metrics may compromise the validity and realism of evaluation results. In the present work, we discuss these concerns and conduct a systematic posthoc verification experiment on the entity linking (EL) task. Unlike traditional methodologies, which asks annotators to provide free-form annotations, we ask annotators to verify the correctness of annotations after the fact (i.e., posthoc). Compared to pre-annotation evaluation, state-of-the-art EL models performed extremely well according to the posthoc evaluation methodology. Posthoc validation also permits the validation of the ground truth dataset. Surprisingly, we find predictions from EL models had a similar or higher verification rate than the ground truth. We conclude with a discussion on these findings and recommendations for future evaluations.

20 February 2024 in arXiv
Verified
Preprint
Open access
PDF file
YDYifan Ding
Yifan Ding
QZQingkai Zeng
Qingkai Zeng
TWTim Weninger
Tim Weninger
Entity Linking (EL) is an essential and challenging task in natural language processing that seeks to link some text representing an entity within a document or sentence with its corresponding entry in a dictionary or knowledge base. Most existing approaches focus on creating elaborate contextual models that look for clues the words surrounding the entity-text to help solve the linking problem. Although these fine-tuned language models tend to work, they can be unwieldy, difficult to train, and do not transfer well to other domains. Fortunately, Large Language Models (LLMs) like GPT provide a highly-advanced solution to the problems inherent in EL models, but simply naive prompts to LLMs do not work well. In the present work, we define ChatEL, which is a three-step framework to prompt LLMs to return accurate results. Overall the ChatEL framework improves the average F1 performance across 10 datasets by more than 2%. Finally, a thorough error analysis shows many instances with the ground truth labels were actually incorrect, and the labels predicted by ChatEL were actually correct. This indicates that the quantitative results presented in this paper may be a conservative estimate of the actual performance. All data and code are available as an open-source package on GitHub at https://github.com/yifding/In_Context_EL.

21 May 2025 in arXiv
Verified
Preprint
Open access
PDF file
TMTianyi Ma
Tianyi Ma
YQYiyue Qian
Yiyue Qian
ZZZheyuan Zhang
Zheyuan Zhang
ZWZehong Wang
Zehong Wang
XQXiaoye Qian
Xiaoye Qian
YYYanfang Ye
Yanfang Ye
The exponential growth of data-driven systems and AI technologies has intensified the demand for high-quality web-sourced datasets. While existing datasets have proven valuable, conventional web data collection approaches face significant limitations in terms of human effort and scalability. Current data-collecting solutions fall into two categories: wrapper-based methods that struggle with adaptability and reproducibility, and large language model (LLM)-based approaches that incur substantial computational and financial costs. To address these challenges, we propose AutoData, a novel multi-agent system for Automated web Data collection, that requires minimal human intervention, i.e., only necessitating a natural language instruction specifying the desired dataset. In addition, AutoData is designed with a robust multi-agent architecture, featuring a novel oriented message hypergraph coordinated by a central task manager, to efficiently organize agents across research and development squads. Besides, we introduce a novel hypergraph cache system to advance the multi-agent collaboration process that enables efficient automated data collection and mitigates the token cost issues prevalent in existing LLM-based systems. Moreover, we introduce Instruct2DS, a new benchmark dataset supporting live data collection from web sources across three domains: academic, finance, and sports. Comprehensive evaluations over Instruct2DS and three existing benchmark datasets demonstrate AutoData's superior performance compared to baseline methods. Case studies on challenging tasks such as picture book collection and paper extraction from surveys further validate its applicability. Our source code and dataset are available at https://github.com/GraphResearcher/AutoData.

25 September 2020 in arXiv
Verified
Preprint
Open access
PDF file
YDYifan Ding
Yifan Ding
NBNicholas Botzer
Nicholas Botzer
TWTim Weninger
Tim Weninger
Modern deep learning systems like PyTorch and Tensorflow are able to train enormous models with billions (or trillions) of parameters on a distributed infrastructure. These systems require that the internal nodes have the same memory capacity and compute performance. Unfortunately, most organizations, especially universities, have a piecemeal approach to purchasing computer systems resulting in a heterogeneous infrastructure, which cannot be used to compute large models. The present work describes HetSeq, a software package adapted from the popular PyTorch package that provides the capability to train large neural network models on heterogeneous infrastructure. Experiments with transformer translation and BERT language model shows that HetSeq scales over heterogeneous systems. HetSeq can be easily extended to other models like image classification. Package with supported document is publicly available at https://github.com/yifding/hetseq.