# Reason-KE++: Aligning the Process, Not Just the Outcome, for Faithful LLM Knowledge Editing

arXiv: https://arxiv.org/abs/2511.12661 · HTML: https://mlsanity.com/paper/2511.12661/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 24 of its 24 references that are in the map.
- First posted on arXiv 16 Nov 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 24 of 24)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild](https://mlsanity.com/paper/2503.18892/) (2025)
- [LIMO: Less is More for Reasoning](https://mlsanity.com/paper/2502.03387/) (2025)
- [Editing Large Language Models: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2305.13172/) (2023)
- [MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions](https://mlsanity.com/paper/2305.14795/) (2023)
- [Can We Edit Factual Knowledge by In-Context Learning?](https://mlsanity.com/paper/2305.12740/) (2023)
- [Evaluating the Ripple Effects of Knowledge Editing in Language Models](https://mlsanity.com/paper/2307.12976/) (2023)
- [Modifying Memories in Transformer Models](https://mlsanity.com/paper/2012.00363/) (2020)
- [Revisiting Demonstration Selection Strategies in In-Context Learning](https://mlsanity.com/paper/2401.12087/) (2024)
- [Uncovering Overfitting in Large Language Model Editing](https://mlsanity.com/paper/2410.07819/) (2024)
- [Unsupervised Dense Retrieval with Relevance-Aware Contrastive Pre-Training](https://mlsanity.com/paper/2306.03166/) (2023)
- [Knowledge Editing through Chain-of-Thought](https://mlsanity.com/paper/2412.17727/) (2024)
- [PokeMQA: Programmable knowledge editing for Multi-hop Question Answering](https://mlsanity.com/paper/2312.15194/) (2023)
- [Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answering](https://mlsanity.com/paper/2403.19631/) (2024)
- [DUnE: Dataset for Unified Editing](https://mlsanity.com/paper/2311.16087/) (2023)
- [Robust Knowledge Editing via Explicit Reasoning Chains for Distractor-Resilient Multi-Hop QA](https://mlsanity.com/paper/2509.01468/) (2025)
- [Edit Once, Update Everywhere: A Simple Framework for Cross-Lingual Knowledge Synchronization in LLMs](https://mlsanity.com/paper/2502.14645/) (2025)

## Built on by (most cited first, 1 of 1)

- [Diagnosing and Mitigating Thinking Collapse in On-Policy Self-Distillation](https://mlsanity.com/paper/2607.10805/) (2026)

## Abstract (arXiv)

Aligning Large Language Models (LLMs) to be faithful to new knowledge in complex, multi-hop reasoning tasks is a critical, yet unsolved, challenge. We find that SFT-based methods, e.g., Reason-KE, while state-of-the-art, suffer from a "faithfulness gap": they optimize for format mimicry rather than sound reasoning. This gap enables the LLM's powerful parametric priors to override new contextual facts, resulting in critical factual hallucinations (e.g., incorrectly reasoning "Houston" from "NASA" despite an explicit edit). To solve this core LLM alignment problem, we propose Reason-KE++, an SFT+RL framework that instills process-level faithfulness. Its core is a Stage-aware Reward mechanism that provides dense supervision for intermediate reasoning steps (e.g., Decomposition, Sub-answer Correctness). Crucially, we identify that naive outcome-only RL is a deceptive trap for LLM alignment: it collapses reasoning integrity (e.g., 19.00% Hop acc) while superficially boosting final accuracy. Our process-aware framework sets a new SOTA of 95.48% on MQUAKE-CF-3k (+5.28%), demonstrating that for complex tasks, aligning the reasoning process is essential for building trustworthy LLMs.