Jing Yang

MAR 2052,

Marchstrasse 23

Berlin, Germany

I am a post-doc researcher at the XplaiNLP group in TU Berlin led by Dr. Vera Schmitt, and the Berlin Institute for the Foundations of Learning (BIFOLD). My current research project (FakeXplain) is a BIFOLD agility project related to generating natural language explanations for AI-based disinformation detection.

I completed my Bachelor’s degree in Information and Computing Science at the Hubei University of Technology in China, followed by a Master’s degree in Computer Science at Hunan University, China. My Master’s dissertation is related to identifying 3D printed objects and printers with Digital Forensics and Machine Learning. After obtaining my Master’s degree in 2019, I pursued a PhD at the RECOD.ai lab from the University of Campinas in Brazil, under the supervision of Prof. Anderson Rocha. During 2022-2023, I did a research internship at the Ubiquitous Knowledge Processing (UKP) lab in TU Darmstadt. My PhD thesis was related to improving fact-checking efficiency and explainability with few-shot learning and large language models.

My research interests are:

Natural language explanation generation
Large language model tuning/prompting
Synthetic text evaluation
Human preference study on text generation
Applications and social impacts of large language models

news

Apr 03, 2025	Our TACL paper is now published in MIT Press: Self-Rationalization in the Wild: A Large-scale Out-of-Distribution Evaluation on NLI-related tasks Open Access. Feel free to check out!
Jan 09, 2025	Our TACL paper was recently accepted! A big thank to the co-authors: Max Glockner, Anderson Rocha and Iryna Guverych.
Jan 08, 2025	Posting the first update of my website!

selected publications

ICASSP
Explainable Fact-checking through Question Answering

Jing Yang, Didier Vega-Oliveros, Taı́s Seibt, and 1 more author

In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022

Abs Bib PDF Code

Misleading or false information has been creating chaos in some places around the world. To mitigate this issue, many researchers have proposed automated fact-checking methods to fight the spread of fake news. However, most methods cannot explain the reasoning behind their decisions, failing to build trust between machines and humans using such technology. Trust is essential for fact-checking to be applied in the real world. Here, we address fact-checking explainability through question answering. In particular, we propose generating questions and answers from claims and answering the same questions from evidence. We also propose an answer comparison model with an attention mechanism attached to each question. Leveraging question answering as a proxy, we break down automated fact-checking into several steps — this separation aids models’ explainability as it allows for more detailed analysis of their decision-making processes. Experimental results show that the proposed model can achieve state-of-the-art performance while providing reasonable explainable capabilities.
@inproceedings{yang2021explainable, title = {Explainable Fact-checking through Question Answering}, author = {Yang, Jing and Vega-Oliveros, Didier and Seibt, Ta{\'\i}s and Rocha, Anderson}, booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, year = {2022}, organization = {IEEE}, }
WIFS
Scalable Fact-checking with Human-in-the-Loop

Jing Yang, Didier Vega-Oliveros, Tais Seibt, and 1 more author

In 2021 IEEE International Workshop on Information Forensics and Security (WIFS), 2021

Abs DOI Bib PDF Code

Researchers have been investigating automated solutions for fact-checking in various fronts. However, current approaches often overlook the fact that information released every day is escalating, and a large amount of them overlap. Intending to accelerate fact-checking, we bridge this gap by proposing a new pipeline – grouping similar messages and summarizing them into aggregated claims. Specifically, we first clean a set of social media posts (e.g., tweets) and build a graph of all posts based on their semantics; Then, we perform two clustering methods to group the messages for further claim summarization. We evaluate the summaries both quantitatively with ROUGE scores and qualitatively with human evaluation. We also generate a graph of summaries to verify that there is no significant overlap among them. The results reduced 28,818 original messages to 700 summary claims, showing the potential to speed up the fact-checking process by organizing and selecting representative claims from massive disorganized and redundant messages.
@inproceedings{yang2021scalable, title = {Scalable Fact-checking with Human-in-the-Loop}, author = {Yang, Jing and Vega-Oliveros, Didier and Seibt, Tais and Rocha, Anderson}, booktitle = {2021 IEEE International Workshop on Information Forensics and Security (WIFS)}, year = {2021}, doi = {10.1109/WIFS53200.2021.9648388}, organization = {IEEE}, }

WIFS

Take It Easy: Label-Adaptive Self-Rationalization for Fact Verification and Explanation Generation

Jing Yang, and Anderson Rocha

In 2024 IEEE International Workshop on Information Forensics and Security (WIFS), 2024

Bib Code

@inproceedings{yang2024take,
  title = {Take It Easy: Label-Adaptive Self-Rationalization for Fact Verification and Explanation Generation},
  author = {Yang, Jing and Rocha, Anderson},
  booktitle = {2024 IEEE International Workshop on Information Forensics and Security (WIFS)},
  pages = {1--6},
  year = {2024},
  organization = {IEEE},
}

TACL

Self-Rationalization in the Wild: A Large-scale Out-of-Distribution Evaluation on NLI-related tasks

Jing Yang, Max Glockner, Anderson Rocha, and 1 more author

Transactions of the Association for Computational Linguistics, 2025

Bib Code

@article{yang2025self,
  title = {Self-Rationalization in the Wild: A Large-scale Out-of-Distribution Evaluation on NLI-related tasks},
  author = {Yang, Jing and Glockner, Max and Rocha, Anderson and Gurevych, Iryna},
  journal = {Transactions of the Association for Computational Linguistics},
  volume = {13},
  pages = {314--342},
  year = {2025},
}