AI RESEARCH
Attribution-Guided Decoding
arXiv CS.LG
•
ArXi:2509.26307v2 Announce Type: replace The capacity of Large Language Models (LLMs) to follow complex instructions and generate factually accurate text is critical for their real-world application. However, standard decoding methods often fail to robustly satisfy these requirements, while existing control techniques frequently degrade general output quality. In this work, we