most citedCitegeist: Automated Generation of Related Work Analysis on the arXiv Corpus

1 citations · 2 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2025★ 1 cited

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★ 1 cited

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…