# DeepEdit: Knowledge Editing as Decoding with Constraints

arXiv: https://arxiv.org/abs/2401.10471 · HTML: https://mlsanity.com/paper/2401.10471/

## Key facts

- Cited by 33 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 32 of its 43 references that are in the map.
- First posted on arXiv 19 Jan 2024.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 30 of 32)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [Knowledge Neurons in Pretrained Transformers](https://mlsanity.com/paper/2104.08696/) (2021)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [Memory-Based Model Editing at Scale](https://mlsanity.com/paper/2206.06520/) (2022)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [GeDi: Generative Discriminator Guided Sequence Generation](https://mlsanity.com/paper/2009.06367/) (2020)
- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)
- [Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP](https://mlsanity.com/paper/2212.14024/) (2022)
- [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)
- [Generating Sequences by Learning to Self-Correct](https://mlsanity.com/paper/2211.00053/) (2022)
- [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)
- [Transformer-Patcher: One Mistake worth One Neuron](https://mlsanity.com/paper/2301.09785/) (2023)
- [COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics](https://mlsanity.com/paper/2202.11705/) (2022)
- [NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics](https://mlsanity.com/paper/2112.08726/) (2021)
- [NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints](https://mlsanity.com/paper/2010.12884/) (2020)
- [Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs](https://mlsanity.com/paper/2111.13654/) (2021)
- [Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning](https://mlsanity.com/paper/2010.05906/) (2020)
- [Tractable Control for Autoregressive Language Generation](https://mlsanity.com/paper/2304.07438/) (2023)
- [Gradient-Based Constrained Sampling from Language Models](https://mlsanity.com/paper/2205.12558/) (2022)
- [Controllable Text Generation with Neurally-Decomposed Oracle](https://mlsanity.com/paper/2205.14219/) (2022)
- [The ART of LLM Refinement: Ask, Refine, and Trust](https://mlsanity.com/paper/2311.07961/) (2023)

## Built on by (most cited first, 30 of 33)

- [Detoxifying Large Language Models via Knowledge Editing](https://mlsanity.com/paper/2403.14472/) (2024)
- [Multi-hop Question Answering under Temporal Knowledge Editing](https://mlsanity.com/paper/2404.00492/) (2024)
- [Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts](https://mlsanity.com/paper/2405.11613/) (2024)
- [In-Context Editing: Learning Knowledge from Self-Induced Distributions](https://mlsanity.com/paper/2406.11194/) (2024)
- [Can Knowledge Editing Really Correct Hallucinations?](https://mlsanity.com/paper/2410.16251/) (2024)
- [Can Editing LLMs Inject Harm?](https://mlsanity.com/paper/2407.20224/) (2024)
- [Large language models for artificial general intelligence (AGI): A survey of foundational principles and approaches](https://mlsanity.com/paper/2501.03151/) (2025)
- [Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness](https://mlsanity.com/paper/2404.00216/) (2024)
- [Adaptive Token Biaser: Knowledge Editing via Biasing Key Entities](https://mlsanity.com/paper/2406.12468/) (2024)
- [Editing the Mind of Giants: An In-Depth Exploration of Pitfalls of Knowledge Editing in Large Language Models](https://mlsanity.com/paper/2406.01436/) (2024)
- [Decoupling Reasoning and Knowledge Injection for In-Context Knowledge Editing](https://mlsanity.com/paper/2506.00536/) (2025)
- [Neighboring Perturbations of Knowledge Editing on Large Language Models](https://mlsanity.com/paper/2401.17623/) (2024)
- [Retrieval Meets Reasoning: Dynamic In-Context Editing for Long-Text Understanding](https://mlsanity.com/paper/2406.12331/) (2024)
- [StruEdit: Structured Outputs Enable the Fast and Accurate Knowledge Editing for Large Language Models](https://mlsanity.com/paper/2409.10132/) (2024)
- [CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners](https://mlsanity.com/paper/2503.16356/) (2025)
- [Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing](https://mlsanity.com/paper/2502.00602/) (2025)
- [Small Models, Big Tasks: An Exploratory Empirical Study on Small Language Models for Function Calling](https://mlsanity.com/paper/2504.19277/) (2025)
- [RIPPLECOT: Amplifying Ripple Effect of Knowledge Editing in Language Models via Chain-of-Thought In-Context Learning](https://mlsanity.com/paper/2410.03122/) (2024)
- [K-Edit: Language Model Editing with Contextual Knowledge Awareness](https://mlsanity.com/paper/2502.10626/) (2025)
- [Robust Knowledge Editing via Explicit Reasoning Chains for Distractor-Resilient Multi-Hop QA](https://mlsanity.com/paper/2509.01468/) (2025)
- [CKnowEdit: A New Chinese Knowledge Editing Dataset for Linguistics, Facts, and Logic Error Correction in LLMs](https://mlsanity.com/paper/2409.05806/) (2024)
- [PromptCD: Test-Time Behavior Enhancement via Polarity-Prompt Contrastive Decoding](https://mlsanity.com/paper/2602.20696/) (2026)
- [Outdated Issue Aware Decoding for Reasoning Questions on Edited Knowledge](https://mlsanity.com/paper/2406.02882/) (2024)
- [PFME: A Modular Approach for Fine-grained Hallucination Detection and Editing of Large Language Models](https://mlsanity.com/paper/2407.00488/) (2024)
- [EtCon: Edit-then-Consolidate for Reliable Knowledge Editing](https://mlsanity.com/paper/2512.04753/) (2025)
- [Benchmarking Safety Risks of Knowledge-Intensive Reasoning under Malicious Knowledge Editing](https://mlsanity.com/paper/2605.10146/) (2026)
- [Rule-Compliant Visual Spatial Planning for Multimodal Large Language Models](https://mlsanity.com/paper/2608.20237/) (2026)
- [ADS-Edit: A Multimodal Knowledge Editing Dataset for Autonomous Driving Systems](https://mlsanity.com/paper/2503.20756/) (2025)
- [Avoiding Knowledge Edit Skipping in Multi-hop Question Answering with Guided Decomposition](https://mlsanity.com/paper/2509.07555/) (2025)
- [Stemming Hallucination in Language Models Using a Licensing Oracle](https://mlsanity.com/paper/2511.06073/) (2025)

## Abstract (arXiv)

How to edit the knowledge in multi-step reasoning has become the major challenge in the knowledge editing (KE) of large language models (LLMs). The difficulty arises because the hallucinations of LLMs during multi-step reasoning often lead to incorrect use of new knowledge and incorrect answers. To address this issue, we design decoding constraints to "regulate" LLMs' reasoning, enhancing logical coherence when incorporating new knowledge. We propose a new KE framework: DEEPEDIT (Depth-first Search-based Constrained Decoding for Knowledge Editing), which enhances LLMs's ability to generate coherent reasoning chains with new knowledge through depth-first search. Our search selects the most important knowledge that satisfies our constraints as the reasoning step to efficiently increase the reasoning depth. In addition to DEEPEDIT, we propose two new KE benchmarks: MQUAKE-2002 and MQUAKE-HARD, which provide more precise and challenging assessments of KE approaches. Qualitatively, DEEPEDIT enables LLMs to produce succinct and coherent reasoning chains involving new knowledge. Quantitatively, it yields significant improvements on multiple KE benchmarks.