Retrieval-augmented Decoding for Improving Truthfulness in Open-ended Generation

ArXi:2508.02184v2 Announce Type: replace Ensuring truthfulness in large language models (LLMs) remains a critical challenge for reliable text generation. While supervised fine-tuning and reinforcement learning with human feedback have shown promise, they require a substantial amount of annotated data and computational resources, limiting scalability. In contrast, decoding-time interventions offer lightweight alternatives without model re