Lifu Huang

Lifu Huang

Auto-generated profile, based on publicly available information

Lifu Huang

Virginia Tech Virginia Tech Virginia Tech Virginia Tech

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
18 July 2023
Verified
Conference Paper
Open access
BYBarry Menglong Yao
Barry Menglong Yao
ASAditya Shah
Aditya Shah
Lichao SunLichao Sun
Lichao Sun
JCJin-Hee Cho
Jin-Hee Cho
LHLifu Huang
Lifu Huang
We propose end-to-end multimodal fact-checking and explanation generation, where the input is a claim and a large collection of web sources, including articles, images, videos, and tweets, and the goal is to assess the truthfulness of the claim by retrieving relevant evidence and predicting a truthfulness label (e.g., support, refute or not enough information), and to generate a statement to summarize and explain the reasoning and ruling process. To support this research, we construct MOCHEG, a large-scale dataset consisting of 15,601 claims where each claim is annotated with a truthfulness label and a ruling statement, and 33,880 textual paragraphs and 12,112 images in total as evidence. To establish baseline performances on MOCHEG, we experiment with several state-of-the-art neural architectures on the three pipelined subtasks: multimodal evidence retrieval, claim verification, and explanation generation, and demonstrate that the performance of the state-of-the-art end-to-end multimodal fact-checking does not provide satisfactory outcomes. To the best of our knowledge, we are the first to build the benchmark dataset and solutions for end-to-end multimodal fact-checking and explanation generation. The dataset, source code and model checkpoints are available at https://github.com/VT-NLP/Mocheg.

1 January 2025
Verified
Conference Paper
Open access
PDF file
HWHaibo Wang
Haibo Wang
ZXZhiyang Xu
Zhiyang Xu
YCYu Cheng
Yu Cheng
SDShizhe Diao
Shizhe Diao
YZYufan Zhou
Yufan Zhou
LHLifu Huang
Lifu Huang
Haibo Wang, Zhiyang Xu, Yu Cheng, Shizhe Diao, Yufan Zhou, Yixin Cao, Qifan Wang, Weifeng Ge, Lifu Huang. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.

1 January 2024
Verified
Conference Paper
Open access
PDF file
YSYing Shen
Ying Shen
ZXZhiyang Xu
Zhiyang Xu
QWQifan Wang
Qifan Wang
YCYu Cheng
Yu Cheng
WYWenpeng Yin
Wenpeng Yin
LHLifu Huang
Lifu Huang
Ying Shen, Zhiyang Xu, Qifan Wang, Yu Cheng, Wenpeng Yin, Lifu Huang. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

1 January 2024
Verified
Conference Paper
Open access
PDF file
MLMinqian Liu
Minqian Liu
YSYing Shen
Ying Shen
ZXZhiyang Xu
Zhiyang Xu
YCYixin Cao
Yixin Cao
ECEunah Cho
Eunah Cho
LHLifu Huang
Lifu Huang
Minqian Liu, Ying Shen, Zhiyang Xu, Yixin Cao, Eunah Cho, Vaibhav Kumar, Reza Ghanadan, Lifu Huang. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

1 January 2024
Verified
Conference Paper
Open access
PDF file
MBMohammad Beigi
Mohammad Beigi
YSYing Shen
Ying Shen
RYRuning Yang
Runing Yang
ZLZihao Lin
Zihao Lin
QWQifan Wang
Qifan Wang
LHLifu Huang
Lifu Huang
Mohammad Beigi, Ying Shen, Runing Yang, Zihao Lin, Qifan Wang, Ankith Mohan, Jianfeng He, Ming Jin, Chang-Tien Lu, Lifu Huang. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.

18 July 2023
Verified
Conference Paper
Open access
MLMingchen Li
Mingchen Li
LHLifu Huang
Lifu Huang
Open domain entity state tracking aims to predict reasonable state changes of entities (i.e., [attribute] of [entity] was [before_state] and [after_state] afterwards) given the action descriptions. It's important to many reasoning tasks to support human everyday activities. However, it's challenging as the model needs to predict an arbitrary number of entity state changes caused by the action while most of the entities are implicitly relevant to the actions and their attributes as well as states are from open vocabularies. To tackle these challenges, we propose a novel end-to-end Knowledge Informed framework for open domain Entity State Tracking, namely KIEST, which explicitly retrieves the relevant entities and attributes from external knowledge graph (i.e., ConceptNet) and incorporates them to autoregressively generate all the entity state changes with a novel dynamic knowledge grained encoder-decoder framework. To enforce the logical coherence among the predicted entities, attributes, and states, we design a new constraint decoding strategy and employ a coherence reward to improve the decoding process. Experimental results show that our proposed KIEST framework significantly outperforms the strong baselines on the public benchmark dataset - OpenPI