5 papers
Calibrated Preference Learning: The Case of Label Ranking
Santo M. A. R. Thies, Viktor Bengs, Timo Kaufmann +2
Calibration, the alignment of predicted probabilities with true outcome frequencies, is essential for reliable decision-making. While extensively studied for classification and reg…
Linear-LLM-SCM: Benchmarking LLMs for Coefficient Elicitation in Linear-Gaussian Causal Models
Kanta Yamaoka, Sumantrak Mukherjee, Thomas Gärtner +5
Large language models (LLMs) have shown potential in identifying qualitative causal relations, but their ability to perform quantitative causal reasoning---estimating effect sizes…
A Survey of Reinforcement Learning from Human Feedback
Timo Kaufmann, Paul Weng, Viktor Bengs +1
Reinforcement learning from human feedback (RLHF) is a variant of reinforcement learning (RL) that learns from human feedback instead of relying on an engineered reward function. B…
Co-Exploration and Co-Exploitation via Shared Structure in Multi-Task Bandits
Sumantrak Mukherjee, Serafima Lebedeva, Valentin Margraf +6
We propose a novel Bayesian framework for efficient exploration in contextual multi-task multi-armed bandit settings, where the context is only observed partially and dependencies…
A calibration test for evaluating set-based epistemic uncertainty representations
Mira Jürgens, Thomas Mortier, Eyke Hüllermeier +2
The accurate representation of epistemic uncertainty is a challenging yet essential task in machine learning. A widely used representation corresponds to convex sets of probabilist…