2 papers
cs.AI2026
Are Reasoning LLMs Robust to Interventions on Their Chain-of-Thought?
Alexander von Recum, Leander Girrbach, Zeynep Akata
Reasoning LLMs (RLLMs) generate step-by-step chains of thought (CoTs) before giving an answer, which improves performance on complex tasks and makes reasoning more transparent. But…
cs.AI2024
Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs
Alexander von Recum, Christoph Schnabl, Gabor Hollbeck +3
Refusals - instances where large language models (LLMs) decline or fail to fully execute user instructions - are crucial for both AI safety and AI capabilities and the reduction of…