NCO: A Versatile Plug-in for Handling Negative Constraints in Decoding

Excerpt

arXiv:2605.10065v2 Announce Type: replace-cross Abstract: Controlling Large Language Models (LLMs) to prevent the generation of undesirable content, such as profanity and personally identifiable information (PII), has become increasingly critical. While earlier approaches relied on post-processing or resampling, recent research has shifted towards constrained decoding methods that control outputs during generation to mitigate high computational costs and quality degradation. However, preventing