SOURCE-LINKED INTELLIGENCE

SFAD: Speculative Factuality-Aware Decoding

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

As one of the most critical challenges in large language models, contextual faithfulness directly determines their reliability in knowledge-intensive applications. This task is particularly challenging as it requires balancing factual consistency with generation efficiency. Contrastive decoding methods require dual forward passes (with and without context) to compare model outputs, doubling inference computational overhead, while post-training alignment demands extensive reinforcement learning with substantial computational overhead. To address this challenge, we present SFAD, a speculative de

Read original source ↗ Open in workspace

recordType

paper

region

Global