Picture for Frauke Kreuter

Frauke Kreuter

Human Preferences in Large Language Model Latent Space: A Technical Analysis on the Reliability of Synthetic Data in Voting Outcome Prediction

Add code
Feb 22, 2025
Viaarxiv icon

Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challenges

Add code
Feb 17, 2025
Viaarxiv icon

Correcting Annotator Bias in Training Data: Population-Aligned Instance Replication (PAIR)

Add code
Jan 12, 2025
Viaarxiv icon

Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study

Add code
Dec 17, 2024
Viaarxiv icon

Problem Solving Through Human-AI Preference-Based Cooperation

Add code
Aug 15, 2024
Viaarxiv icon

The Missing Link: Allocation Performance in Causal Machine Learning

Add code
Jul 15, 2024
Viaarxiv icon

The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models

Add code
Jun 16, 2024
Figure 1 for The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models
Figure 2 for The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models
Figure 3 for The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models
Figure 4 for The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Models
Viaarxiv icon

Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models

Add code
Jun 13, 2024
Viaarxiv icon

Decomposed Prompting: Unveiling Multilingual Linguistic Structure Knowledge in English-Centric Large Language Models

Add code
Feb 28, 2024
Figure 1 for Decomposed Prompting: Unveiling Multilingual Linguistic Structure Knowledge in English-Centric Large Language Models
Figure 2 for Decomposed Prompting: Unveiling Multilingual Linguistic Structure Knowledge in English-Centric Large Language Models
Figure 3 for Decomposed Prompting: Unveiling Multilingual Linguistic Structure Knowledge in English-Centric Large Language Models
Figure 4 for Decomposed Prompting: Unveiling Multilingual Linguistic Structure Knowledge in English-Centric Large Language Models
Viaarxiv icon

"My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models

Add code
Feb 22, 2024
Figure 1 for "My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models
Figure 2 for "My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models
Figure 3 for "My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models
Figure 4 for "My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models
Viaarxiv icon