Preprints
- Automated reproducibility assessments in the social and behavioral sciences using large language models.
- ChinaHeritaQA: A Culturally-Grounded Visual Question Answering Dataset for World Heritage Sites in China.
- A Survey on Mental Health Datasets and Resources.
- Connecting Natural Language Processing and Survey Methodology: Potentials, Challenges, and Open Questions.
- United in Diversity? Contextual Biases in LLM-Based Predictions of the 2024 European Parliament Elections.
Peer-Reviewed Journal Articles
Peer-Reviewed Conference Papers
- Moral Lenses, Political Coordinates: Towards Ideological Positioning of Morally Conditioned LLMs.
- YUE-PUB: A Cantonese Pragmatic Understanding Benchmark.
- YUE-PUB-Speech: A Speech-based Pragmatic Understanding Benchmark for Cantonese.
- The Imperfective Paradox in Large Language Models.
- Capabilities and Evaluation Biases of Large Language Models in Classical Chinese Poetry Generation: A Case Study on Tang Poetry.
- MSMO-ABSA: Multi-Scale and Multi-Objective Optimization for Cross-Lingual Aspect-Based Sentiment Analysis.
- Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation.
- FAITH: Factuality Alignment through Integrating Trustworthiness and Honestness.
- FLAME: Empowering Frozen LLMs for Knowledge Graph Completion.
- SURE: Synergistic Uncertainty-Aware Reasoning for Multimodal Emotion Recognition in Conversations.
- Too Open for Opinion? Embracing Open-Endedness in Large Language Models for Social Simulation.
- Do Large Language Models Think Like the Brain? Sentence-Level Evidences from Layer-Wise Embeddings and fMRI.
- M-ABSA: A Multilingual Dataset for Aspect-Based Sentiment Analysis.
- Multimodal Emotion Recognition in Conversations: A Survey of Methods, Trends, Challenges and Prospects.
- Decomposed Prompting: Probing Multilingual Linguistic Structure Knowledge in Large Language Models.
- Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challenges.
- Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study.
- Why Lift so Heavy? Slimming Large Language Models by Cutting Off the Layers.
- Enhancing Multi-Epitope Vaccine Effectiveness Through State-of-the-Art Proteasomal Cleavage Prediction with Deep Learning.
- The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models.
- Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You Think.
- "My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models.
- ToPro: Token-Level Prompt Decomposition for Cross-Lingual Sequence Labeling Tasks.
- Annotation Sensitivity: Training Data Collection Methods Affect Model Performance.
- Is Prompt-Based Finetuning Always Better Than Vanilla Finetuning? Insights from Cross-Lingual Language Understanding.
Peer-Reviewed Workshop Papers
- Do LLMs Give Consistent Opinions? Evaluating Response Reliability Under Varying Likert-Scale Formulations in Survey-Style MCQA.
- Can Large Language Models Advance Crosswalks? The Case of Danish Occupation Codes.
- Aligning NLP Models with Target Population Perspectives using PAIR: Population-Aligned Instance Replication.
- Measuring Sexism in US Elections: A Comparative Analysis of X Discourse from 2020 to 2024.
- Evaluating Lexical Aspect with Large Language Models.
- Informing Climate Risk Analysis Using Textual Information — A Research Agenda.
- Order Effects in Annotation Tasks: Further Evidence of Annotation Sensitivity.
- Baby's CoThought: Leveraging Large Language Models for Enhanced Reasoning in Compact Models.
- What Cleaves? Is Proteasomal Cleavage Prediction Reaching a Ceiling?
Essays and Non-Technical Writings
- 大規模言語モデルにおける時制・アスペクト研究：未完了相パラドックスを事例として (Tense and Aspect Research in Large Language Models: The Imperfective Paradox as a Case Study).
- Mit Deutsch in das Land, mit Deutsch in die Zukunft. (With German into the Country, with German into the Future).
Book Translations (German → Chinese)
- Jon Christoph Berndt: Die stärkste Marke sind Sie selbst! (You Are the Best Brand)
- Karl-Michael Haake: Zimmerpflanzen (Indoor Plants)
- Dominic Multerer: Marken müssen bewusst Regeln brechen, um anders zu sein (Brands Must Break the Rules to Stand Out)
- Jutta Portner: Besser verhandeln. Das Trainingsbuch (Negotiate Better. The Training Book)