5 papers
The Truncation Blind Spot: How Decoding Strategies Systematically Exclude Human-Like Token Choices
Esteban Garces Arias, Nurzhan Sapargali, Christian Heumann +1
Why does machine-generated text remain detectable? We trace the answer to the decoding stage: standard strategies such as top- and nucleus sampling restrict generation to high-p…
promptolution: A Unified, Modular Framework for Prompt Optimization
Tom Zehle, Timo HeiÃ, Moritz Schlager +2
Prompt optimization has become crucial for enhancing the performance of large language models (LLMs) across a broad range of tasks. Although many research papers demonstrate its ef…
Reinforcement Learning for Latent-Space Thinking in LLMs
Enes Ãzeren, Matthias AÃenmacher
Chain-of-Thought (CoT) reasoning typically utilizes the discrete language space for thinking, which is inherently inefficient, as many generated tokens only enforce linguistic rule…
From Calculation to Adjudication: Examining LLM judges on Mathematical Reasoning Tasks
Andreas Stephan, Dawei Zhu, Matthias AÃenmacher +2
To reduce the need for human annotations, large language models (LLMs) have been proposed as judges of the quality of other candidate models. The performance of LLM judges is typic…
AI Conversational Interviewing: Transforming Surveys with LLMs as Adaptive Interviewers
Alexander Wuttke, Matthias AÃenmacher, Christopher Klamm +3
Traditional methods for eliciting people's opinions face a trade-off between depth and scale: structured surveys enable large-scale data collection but limit respondents' ability t…