Showing cs.LGShow all
3 papers · 1 filter
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…
cs.LG2025
CoCoNUT: Structural Code Understanding does not fall out of a tree
Claas Beger, Saikat Dutta
Large Language Models (LLMs) have shown impressive performance across a wide array of tasks involving both structured and unstructured textual data. Recent results on various bench…