Hi👋, I’m Qianli Wang and work as a NLP researcher dedicated to advancing the interpretability and explainability of LLMs at XplainNLP group, Quality and Usability Lab, Technische Universität Berlin under the supervision of Sebastian Möller.
Research interests 👀
Topics of interest are post-hoc explanations (counterfactual generation, rationale generation), interactive conversational XAI systems, data-centric interpretability, evaluation for generated text.
News ✨
2024-11-08: I will be in Miami at EMNLP 2024 to present our CoXQL paper. See you in Miami 🗽!
2024-10-15: One co-authored paper about LLM self-explanation alignment is in submission!
2024-09-20: CoXQL: A Dataset for Parsing Explanation Requests in Conversational XAI Systems accepted to EMNLP 2024 Findings, which will be hold in Miami, USA 🗽!
2024-09-12: One new paper in submission: an NLG paper for improving explanations via cross-refinement (Cross-Refine).
2024-07-12: One co-authored paper - Towards Modeling and Evaluating Instructional Explanations in Teacher-Student Dialogues accepted to ACM GoodIT 2024.
2024-06-12: One new paper in submission: A question answering (resource) paper on the conversational parsing explanation requests (CoXQL).
2024-04-19: LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanations accepted to NAACL 2024 HCI+NLP workshop🛕!
2024-02-28: Two new papers in submission: A follow-up to InterroLang on the conversational examination of self-explaining LLMs (LLMCheckup) and a resource and evaluation paper on instructional explanations in teacher-student dialogues (ReWIRED).
2023-10-08: InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations accepted to EMNLP 2023 Findings🦁!
Education Background 👨🎓
2024-ongoing: Computer Science, Ph.D., Technische Universität Berlin. Supervised by Prof. Dr. Sebastian Möller.
2021-2023: Computer Science, M.Sc., Technische Universität Berlin. Supervised by Nils Feldhus and Dr.-Ing. Leonhard Hennig: A Singular LLM is all you need for dialogue-based explanation regarding NLP tasks.
2018-2021: Computer Science, B.Sc., Freie Universität Berlin. Supervised by Prof. Dr. László Kozma: Understanding and implementation of the algorithm for three-coloring in triangle-free planar graphs.
Jobs 🧑💻
2024.07 - ongoing: NLP Researcher @ Quality and Usability Lab, Technische Universität Berlin, Berlin, Germany; funded by VERANDA project.
2024.02 - ongoing: Guest Researcher @ German Research Center for Artificial Intelligence (DFKI) - SLT Group, Berlin, Germany.
2023.01 - 2024.01: Research Assistant @ German Research Center for Artificial Intelligence (DFKI) - SLT Group, Berlin, Germany.