3 papers
cs.CL2026
-CoT: Prolog-Initialized Chain-of-Thought Prompting for Multi-Hop Question-Answering
Chao Wan, Albert Gong, Mihir Mishra +3
Chain-of-Thought (CoT) prompting significantly enhances large language models' (LLMs) problem-solving capabilities, but still struggles with complex multi-hop questions, often fall…
cs.LG2025
Citegeist: Automated Generation of Related Work Analysis on the arXiv Corpus
Claas Beger, Carl-Leander Henneking
Large Language Models provide significant new opportunities for the generation of high-quality written works. However, their employment in the research community is inhibited by th…
cs.LG2025
Decoding Human Preferences in Alignment: An Improved Approach to Inverse Constitutional AI
Carl-Leander Henneking, Claas Beger
Traditional methods for aligning Large Language Models (LLMs), such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO), rely on implicit…