6 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…
ResponseRank: Data-Efficient Reward Modeling through Preference Strength Learning
Timo Kaufmann, Yannick Metz, Daniel Keim +1
Binary choices, as often used for reinforcement learning from human feedback (RLHF), convey only the direction of a preference. A person may choose apples over oranges and bananas…
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…
Feedback Forensics: A Toolkit to Measure AI Personality
Arduin Findeis, Timo Kaufmann, Eyke Hüllermeier +1
Some traits making a "good" AI model are hard to describe upfront. For example, should responses be more polite or more casual? Such traits are sometimes summarized as model charac…
Problem Solving Through Human-AI Preference-Based Cooperation
Subhabrata Dutta, Timo Kaufmann, Goran Glavaš +7
While there is a widespread belief that artificial general intelligence (AGI) -- or even superhuman AI -- is imminent, complex problems in expert domains are far from being solved.…
Inverse Constitutional AI: Compressing Preferences into Principles
Arduin Findeis, Timo Kaufmann, Eyke Hüllermeier +2
Feedback data is widely used for fine-tuning and evaluating state-of-the-art AI models. Pairwise text preferences, where human or AI annotators select the "better" of two options,…