SFAD: Speculative Factuality-Aware Decoding

2026-09-01

AI Summary

为解决大语言模型在知识密集型应用中的上下文忠实性问题，提出SFAD框架，通过推测解码增强忠实性且不降低推理效率。

Abstract

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 \textbf{SFAD}, a speculative decoding framework that enhances contextual faithfulness without inference degradation. We first construct \textbf{ConFide}, a preference dataset with fine-grained atomic perturbations, to train a context-faithful draft model via Direct Preference Optimization. During inference, Epistemic Friction detects potential hallucinations by quantifying distributional tension weighted by specialist certainty. When friction exceeds the threshold, Asymmetric Logit Steering refines the target distribution through residual-based logit injection; otherwise, standard speculation proceeds. Extensive experiments demonstrate that SFAD substantially improves faithfulness while achieving $2.48\times$ speedup, offering a practical solution for efficient LLMs.

Problem

• contextual faithfulness
• large language models
• generation efficiency
• factual consistency

Innovation

• Speculative Factuality-Aware Decoding
• Epistemic Friction
• Asymmetric Logit Steering
• Direct Preference Optimization