7 papers
Accelerating Constrained Decoding with Token Space Compression
Michael Sullivan, Alexander Koller
To guarantee that an LLM's outputs conform to a specified structure, context-free grammar (CFG) decoding engines force the selection of next tokens that produce strings that confor…
AuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixing
Sarubi Thillainathan, Ji-Ung Lee, Michael Sullivan +1
The task of authorship style transfer involves rewriting text in the style of a target author while preserving the meaning of the original text. Existing style transfer methods tra…
GRPO is Secretly a Process Reward Model
Michael Sullivan, Alexander Koller
Process reward models (PRMs) allow for fine-grained credit assignment in reinforcement learning (RL), and seemingly contrast with outcome reward models (ORMs), which assign a singl…
Evaluating Spatiotemporal Consistency in Automatically Generated Sewing Instructions
Luisa Geiger, Mareike Hartmann, Michael Sullivan +1
In this paper, we propose a novel, automatic tree-based evaluation metric for LLM-generated step-by-step assembly instructions, that more accurately reflects spatiotemporal aspects…
Procedural Environment Generation for Tool-Use Agents
Michael Sullivan, Mareike Hartmann, Alexander Koller
Although the power of LLM tool-use agents has ignited a flurry of recent research in this area, the curation of tool-use training data remains an open problemespecially for onli…
Playpen: An Environment for Exploring Learning Through Conversational Interaction
Nicola Horst, Davide Mazzaccara, Antonia Schmidt +13
Interaction between learner and feedback-giver has come into focus recently for post-training of Large Language Models (LLMs), through the use of reward models that judge the appro…