8 papers
Prompt reinforcing for long-term planning of large language models
Hsien-Chin Lin, Benjamin Matthias Ruppik, Carel van Niekerk +6
Large language models (LLMs) have achieved remarkable success in a wide range of natural language processing tasks and can be adapted through prompting. However, they remain subopt…
Post-Training Large Language Models via Reinforcement Learning from Self-Feedback
Carel van Niekerk, Renato Vukovic, Benjamin Matthias Ruppik +2
Large Language Models (LLMs) often produce plausible but poorly-calibrated answers, limiting their reliability on reasoning-intensive tasks. We present Reinforcement Learning from…
Emotionally Intelligent Task-oriented Dialogue Systems: Architecture, Representation, and Optimisation
Shutong Feng, Hsien-chin Lin, Nurul Lubis +5
Task-oriented dialogue (ToD) systems are designed to help users achieve specific goals through natural language interaction. While recent advances in large language models (LLMs) h…
Dialogue Ontology Relation Extraction via Constrained Chain-of-Thought Decoding
Renato Vukovic, David Arps, Carel van Niekerk +4
State-of-the-art task-oriented dialogue systems typically rely on task-specific ontologies for fulfilling user queries. The majority of task-oriented dialogue data, such as custome…
A Confidence-based Acquisition Model for Self-supervised Active Learning and Label Correction
Carel van Niekerk, Christian Geishauser, Michael Heck +6
Supervised neural approaches are hindered by their dependence on large, meticulously annotated datasets, a requirement that is particularly cumbersome for sequential tasks. The qua…
Local Topology Measures of Contextual Language Model Latent Spaces With Applications to Dialogue Term Extraction
Benjamin Matthias Ruppik, Michael Heck, Carel van Niekerk +5
A common approach for sequence tagging tasks based on contextual word representations is to train a machine learning classifier directly on these embedding vectors. This approach h…