Author

Benjamin Matthias Ruppik

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Jul 2025

Post-Training Large Language Models via Reinforcement Learning from Self-Feedback

Reinforcement Learning from Self-Feedback (RLSF) is presented, a post-training stage that utilises the model's intrinsic confidence as a self-generated reward and affirms reinforcement learning on intrinsic model behaviour as a principled and data-efficient component of the LLM post-training pipeline.

Carel van Niekerk, Renato Vukovic, Benjamin Matthias Ruppik et al. · arXiv.org · 13 citations · ⚡1

#natural language process... Open access Jul 2025

All Learning Has an Emotional Basis, So Does Task-Oriented Dialogue

A novel end-to-end framework that combines fully lexicalised representations with an LLM backbone for improved semantic accuracy and employs online reinforcement learning with short-term emotional and long-term task-success rewards for joint optimisation of emotional interaction and task success is proposed.

Shutong Feng, Hsien-Chin Lin, Nurul Lubis et al. · Transactions of the Associat... · 2 citations