Papers by Simon Münker
Fingerprinting LLMs through Survey Item Factor Correlation: A Case Study on Humor Style Questionnaire (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for evaluating LLMs focus on output accuracy, faithfulness, or alignment with human preferences, but these metrics do not capture fundamental differences in how models internally represent and relate psychological constructs. |
| Approach: | They propose to “fingerprint” LLMs through factor correlation patterns on standardized psychological assessments to deepen understanding of LLM's constructs representation. |
| Outcome: | The proposed method shows that LLMs represent constructs differently than humans . it also shows that no LLM recovers the constructs of the Humor Style Questionnaire . |
Zero-shot prompt-based classification: topic labeling in times of foundation models in German Tweets (2025.acl-srw)
Copied to clipboard
| Challenge: | Recent advances in NLP have enabled the use of text-to-text annotation without providing training samples. |
| Approach: | They propose a text-to-text interface for automatic annotation using written guidelines without providing training samples. |
| Outcome: | The proposed approach is comparable with the fine-tuned BERT but without any training data. |
Don’t Trust Generative Agents to Mimic Communication on Social Networks Unless You Benchmarked their Empirical Realism (2026.eacl-long)
Copied to clipboard
| Challenge: | Social media platforms face mounting regulatory pressure worldwide . obtaining evidence regarding platform risks remains challenging . |
| Approach: | They propose a formal framework for simulation of social networks before focusing on imitating user communication. |
| Outcome: | The proposed model can replicate human behavior with sufficient realism to perform the task. |