Publications

A collection of my research work. († denotes equal contribution)

Showing 21 of 21 publications
Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation
Click to preview

Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation

1st Author
Qianli Wang, Van Bach Nguyen, Yihong Liu, Fedor Splitt, Nils Feldhus, Christin Seifert, Hinrich Schütze

ACL 2026

PaperCode
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
Click to preview

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Hengyuan Zhang, Zhihao Zhang, Mingyang Wang, Zunhai Su, Yiwei Wang, Qianli Wang, Shuzhou Yuan

ACL Findings 2026

The extended version accepted at Computer Science Review

PaperCode
Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge Recall
Click to preview

Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge Recall

1st Author
Qianli Wang, Mingyang Wang, Nils Feldhus, Simon Ostermann, Yuan Cao, Hinrich Schütze, Sebastian Möller

TrustNLP @ ACL 2026

Oral Presentation

Paper
Investigating the Interplay between Contextual and Parametric Chain-of-Thought Faithfulness
Click to preview

Investigating the Interplay between Contextual and Parametric Chain-of-Thought Faithfulness

1st Author
Jingyi Sun†, Qianli Wang†, Pepa Atanasova, Nils Feldhus, Isabelle Augenstein

2026

In submission. †Equal contribution.

Paper
Judge Circuits
Click to preview

Judge Circuits

Nils Feldhus, Tanja Bäumel, Elena Golimblevskaia, Qianli Wang, Van Bach Nguyen, Aaron Louis Eidt, Selin Kahvecioglu

2026

In submission

Paper
Macro: Enhancing Multilingual Counterfactual Explanations through Alignment-as-Preference Optimization
Click to preview

Macro: Enhancing Multilingual Counterfactual Explanations through Alignment-as-Preference Optimization

1st Author
Yilong Wang†, Qianli Wang†, Bohao Chu, Yihong Liu, Jing Yang, Simon Ostermann

2026

†Equal contribution. In submission (previously accepted at MeLLM @ ACL 2026, non-archival).

Paper
SimXAI: A Simple Drop-in Layer Increases Interaction Quality and Understanding in Conversational XAI
Click to preview

SimXAI: A Simple Drop-in Layer Increases Interaction Quality and Understanding in Conversational XAI

Van Bach Nguyen, Qianli Wang, Nils Feldhus, Jörg Schlötterer, Christin Seifert

2026

In submission

Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations
Click to preview

Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations

1st Author
Qianli Wang, Nils Feldhus†, Pepa Atanasova†, Fedor Splitt, Simon Ostermann, Sebastian Möller

2026

In submission

Paper
iFlip: Iterative Feedback-driven Counterfactual Example Refinement
Click to preview

iFlip: Iterative Feedback-driven Counterfactual Example Refinement

1st Author
Yilong Wang†, Qianli Wang†, Nils Feldhus

2026

In submission. †Equal contribution.

Paper
What Are We Measuring in NLG? A Meta-Analysis of Evaluation Trends 2020-2025
Click to preview

What Are We Measuring in NLG? A Meta-Analysis of Evaluation Trends 2020-2025

Jing Yang, Nils Feldhus, Salar Mohtaj, Leonhard Hennig, Qianli Wang, Eleni Metheniti, Sherzod Hakimov

2026

In submission

Paper
eTracer: Towards Traceable Text Generation via Claim-Level Grounding
Click to preview

eTracer: Towards Traceable Text Generation via Claim-Level Grounding

Bohao Chu, Qianli Wang, Hendrik Damm, Hui Wang, Ula Muhabbek, Elisabeth Livingstone, Christoph M. Friedrich

2026

In submission

PaperCode
Multilingual Datasets for Custom Input Extraction and Explanation Requests Parsing in Conversational XAI Systems
Click to preview

Multilingual Datasets for Custom Input Extraction and Explanation Requests Parsing in Conversational XAI Systems

1st Author
Qianli Wang, Tatiana Anikina, Nils Feldhus, Simon Ostermann, Fedor Splitt, Jiaao Li, Yoana Tsoneva

EMNLP Findings 2025

PaperCode
Truth or Twist? Optimal Model Selection for Reliable Label Flipping Evaluation in LLM-based Counterfactuals
Click to preview

Truth or Twist? Optimal Model Selection for Reliable Label Flipping Evaluation in LLM-based Counterfactuals

1st Author
Qianli Wang, Van Bach Nguyen, Nils Feldhus, Luis Felipe Villa-Arenas, Christin Seifert, Sebastian Möller

INLG 2025

Oral Presentation

PaperCode
FitCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generation
Click to preview

FitCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generation

1st Author
Qianli Wang, Nils Feldhus, Simon Ostermann, Luis Felipe Villa-Arenas, Sebastian Möller

ACL Findings 2025

PaperCode
Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem
Click to preview

Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem

1st Author
Qianli Wang, Tatiana Anikina†, Nils Feldhus†, Simon Ostermann, Sebastian Möller

COLING 2025

PaperCode

Beyond Transparency: Evaluating Explainability in AI-Supported Fact-Checking

Vera Schmitt, Isabel Bezzaoui, Charlott Jakob, Premtim Sahitaj, Qianli Wang, Arthur Hilbert, Max Upravitelev

Proceedings of the 4th ACM International Workshop on Multimedia AI against Disinformation 2025

Paper

CoXQL: A Dataset for Parsing Explanation Requests in Conversational XAI Systems

1st Author
Qianli Wang, Tatiana Anikina†, Nils Feldhus†, Simon Ostermann, Sebastian Möller

EMNLP Findings 2024

PaperCode
LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanations
Click to preview

LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanations

1st Author
Qianli Wang, Tatiana Anikina, Nils Feldhus, Josef Genabith, Leonhard Hennig, Sebastian Möller

HCI+NLP Workshop @ NAACL 2024

PaperCode

Anchored Alignment for Self-Explanations Enhancement

Luis Felipe Villa-Arenas, Ata Nizamoglu, Qianli Wang, Sebastian Möller

2024

In submission

Paper

Towards Modeling and Evaluating Instructional Explanations in Teacher-Student Dialogues

Nils Feldhus, Aliki Anagnostopoulou, Qianli Wang, Milad Alshomary, Henning Wachsmuth, Daniel Sonntag, Sebastian Möller

Proceedings of the 2024 International Conference on Information Technology for Social Good 2024

Paper
InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations
Click to preview

InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations

Nils Feldhus, Qianli Wang, Tatiana Anikina, Sahil Chopra, Cennet Oguz, Sebastian Möller

EMNLP Findings 2023

PaperCode