2 papers
cs.CL2026
CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning
Congmin Zheng, Jiachen Zhu, Jianghao Lin +6
Process Reward Models (PRMs) play a central role in evaluating and guiding multi-step reasoning in large language models (LLMs), especially for mathematical problem solving. Howeve…
cs.AI2025
Exploring the Potential of Citiverses for Regulatory Learning
Isabelle Hupont, Marisa Ponti, Sven Schade
Citiverses hold the potential to support regulatory learning by offering immersive, virtual environments for experimenting with policy scenarios and technologies. This paper propos…