I am a passionate AI researcher with a strong sense of responsibility for making the future a better place. I am currently pursuing my PhD (2023-2027 expected) under the joint supervision of Prof Elliott Ash & Prof Mrinmaya Sachan at ETH, and Prof Markus Leippold at UZH. I divide my time equally between both institutions.
My research focuses on AI application trustworthiness. Specifically, I am dedicated to advancing two key areas:
(1) External: Supervision for AI Applications – I work on validating NLP application outputs using external automated verifiers, ensuring they are more interpretable, efficient, and suitable for both human and machine supervision.
(2) Internal: Enhancing AI Honesty and Calibration – I aim to align AI systems to recognize their own knowledge limitations and express uncertainty appropriately. This uncertainty-awareness should generalize across various tasks, including information-seeking, reasoning, and retrieval-augmented generation.
By enhancing AI trustworthiness, I aspire to contribute to impactful domains such as NLP for climate change and Legal NLP. I like to aim high, but I always keep my feet on the ground.
If you are interested in collaborating in these areas, feel free to reach out!
PhD Student in NLP
Email: jingweini8@gmail.com
Department of Humanities, Social and Political Sciences
ETH Zürich
IFW-E-44, Haldeneggsteig 4
&
Department of Banking and Finance
University of Zürich
PLR-J-101, Plattenstr. 14
Events
- Organizing the second ClimateNLP workshop at ACL2025, Vienna. See Workshop Website.
- Organized the first ClimateNLP workshop at ACL2024, Bangkok. See Proceedings and Workshop Website.
Publications
- Navigating the Helpfulness-Truthfulness Trade-Off with Uncertainty-Aware Instruction Fine-Tuning (ACL 2025 Under Review) Tianyi Wu*, Jingwei Ni*, Bryan Hooi, Jiaheng Zhang, Elliott Ash, See-Kiong Ng, Mrinmaya Sachan, Markus Leippold
- DIRAS: Efficient LLM-Assisted Annotation of Document Relevance in Retrieval Augmented Generation (NAACL 2025 Main) Jingwei Ni, Tobias Schimanski, Meihong Lin, Mrinmaya Sachan, Elliott Ash, Markus Leippold
- ClimRetrieve: A Benchmarking Dataset for Information Retrieval from Corporate Climate Disclosures (EMNLP 2024 Main) Tobias Schimanski, Jingwei Ni, Roberto Spacey, Nicola Ranger, Markus Leippold
- Towards Faithful and Robust LLM Specialists for Evidence-Based Question-Answering (ACL 2024 Main) Tobias Schimanski*, Jingwei Ni*, Mathias Kraus, Elliott Ash, Markus Leippold
- AFaCTA: Assisting the Annotation of Factual Claim Detection with Reliable LLM Annotators (ACL 2024 Main) Jingwei Ni, Minjing Shi, Dominik Stammbach, Mrinmaya Sachan, Elliott Ash, Markus Leippold
- Automated Fact-Checking of Climate Change Claims with Large Language Models Markus Leippold, Saeid Ashraf Vaghefi, Dominik Stammbach, Veruska Muccione, Julia Bingler, Jingwei Ni, Chiara Colesanti-Senni, Tobias Wekhof, Tobias Schimanski, Glen Gostlow, Tingyu Yu, Juerg Luterbacher, Christian Huggel
- Exploring Nature: Datasets and Models for Analyzing Nature-Related Disclosures (AAAI 2024 Workshop on AI in Finance for Social Impact) Tobias Schimanski, Chiara Colesanti Senni, Glen Gostlow, Jingwei Ni, Tingyu Yu, Markus Leippold
- CHATREPORT: Democratizing Sustainability Disclosure Analysis through LLM-based Tools (EMNLP 2023 Demo) Jingwei Ni, Julia Bingler, Chiara Colesanti-Senni, Mathias Kraus, Glen Gostlow, Tobias Schimanski, Dominik Stammbach, Saeid Ashraf Vaghefi, Qian Wang, Nicolas Webersinke, Tobias Wekhof, Tingyu Yu, Markus Leippold
- When Does Aggregating Multiple Skills with Multi-Task Learning Work? A Case Study in Financial NLP (ACL 2023 Main) Jingwei Ni, Zhijing Jin, Qian Wang, Mrinmaya Sachan, Markus Leippold
- ChatClimate: Grounding Conversational AI in Climate Science (Nature Communications Earth & Environment) Saeid Ashraf Vaghefi, Qian Wang, Veruska Muccione, Jingwei Ni, Mathias Kraus, Julia Bingler, Tobias Schimanski, Chiara Colesanti-Senni, Nicolas Webersinke, Christrian Huggel, Markus Leippold
- Original or translated? A causal analysis of the impact of translationese on machine translation performance (NAACL 2022 Main) Jingwei Ni, Zhijing Jin, Markus Freitag, Mrinmaya Sachan, Bernhard Schölkopf
- Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP (EMNLP 2021 Main) Zhijing Jin, Julius von Kügelgen, Jingwei Ni, Tejas Vaidhya, Ayush Kaushal, Mrinmaya Sachan, Bernhard Schoelkopf
Education
PhD @ ETH D-GESSETH & UZH (Mar 2023 – Present)
MSc in Data Science and Machine Learning
University College London (Sept 2021 – Sept 2022)
University of Hong Kong (Sep 2017 – Sep 2021)