# SFAD: Speculative Factuality-Aware Decoding

arXiv: https://arxiv.org/abs/2609.00796 · HTML: https://mlsanity.com/paper/2609.00796/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 76 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 16 of 16)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [Measuring short-form factuality in large language models](https://mlsanity.com/paper/2411.04368/) (2024)
- [Challenges and Applications of Large Language Models](https://mlsanity.com/paper/2307.10169/) (2023)
- [HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attribution](https://mlsanity.com/paper/2307.16883/) (2023)
- [When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMs](https://mlsanity.com/paper/2511.02243/) (2025)
- [Leveraging Logical Rules in Knowledge Editing: A Cherry on the Top](https://mlsanity.com/paper/2405.15452/) (2024)
- [MONICA: Real-Time Monitoring and Calibration of Chain-of-Thought Sycophancy in Large Reasoning Models](https://mlsanity.com/paper/2511.06419/) (2025)
- [Context-aware Decoding Reduces Hallucination in Query-focused Summarization](https://mlsanity.com/paper/2312.14335/) (2023)
- [Infinite Sampling: Efficient and Stable Grouped RL Training for Large Language Models](https://mlsanity.com/paper/2506.22950/) (2025)
- [Investigating CoT Monitorability in Large Reasoning Models](https://mlsanity.com/paper/2511.08525/) (2025)
- [Tracing and Mitigating Hallucinations in Multimodal LLMs via Dynamic Attention Localization](https://mlsanity.com/paper/2509.07864/) (2025)

## Abstract (arXiv)

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 decoding framework that enhances contextual faithfulness without inference degradation. We first construct 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× speedup, offering a practical solution for efficient LLMs.