# Propagation and Pitfalls: Reasoning-based Assessment of Knowledge Editing through Counterfactual Tasks

arXiv: https://arxiv.org/abs/2401.17585 · HTML: https://mlsanity.com/paper/2401.17585/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 41 references that are in the map.
- First posted on arXiv 31 Jan 2024.

## Builds on (most cited first, 25 of 25)

- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs](https://mlsanity.com/paper/1903.00161/) (2019)
- [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)
- [The Web as a Knowledge-base for Answering Complex Questions](https://mlsanity.com/paper/1803.06643/) (2018)
- [How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources](https://mlsanity.com/paper/2306.04751/) (2023)
- [A Survey of Hallucination in Large Foundation Models](https://mlsanity.com/paper/2309.05922/) (2023)
- [FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation](https://mlsanity.com/paper/2310.03214/) (2023)
- [MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions](https://mlsanity.com/paper/2305.14795/) (2023)
- [Modifying Memories in Transformer Models](https://mlsanity.com/paper/2012.00363/) (2020)
- [Knowledge Editing for Large Language Models: A Survey](https://mlsanity.com/paper/2310.16218/) (2023)
- [Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases](https://mlsanity.com/paper/2011.07743/) (2020)
- [Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting](https://mlsanity.com/paper/2004.12651/) (2020)
- [Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs](https://mlsanity.com/paper/2111.13654/) (2021)
- [Can LMs Learn New Entities from Descriptions? Challenges in Propagating Injected Knowledge](https://mlsanity.com/paper/2305.01651/) (2023)
- [Entity Cloze By Date: What LMs Know About Unseen Entities](https://mlsanity.com/paper/2205.02832/) (2022)
- [Meta-Learning Online Adaptation of Language Models](https://mlsanity.com/paper/2305.15076/) (2023)
- [Emptying the Ocean with a Spoon: Should We Edit Models?](https://mlsanity.com/paper/2310.11958/) (2023)
- [TAT-LLM: A Specialized Language Model for Discrete Reasoning over Tabular and Textual Data](https://mlsanity.com/paper/2401.13223/) (2024)

## Built on by (most cited first, 24 of 24)

- [Detoxifying Large Language Models via Knowledge Editing](https://mlsanity.com/paper/2403.14472/) (2024)
- [Can Knowledge Editing Really Correct Hallucinations?](https://mlsanity.com/paper/2410.16251/) (2024)
- [Cofca: A Step-Wise Counterfactual Multi-hop QA benchmark](https://mlsanity.com/paper/2402.11924/) (2024)
- [Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?](https://mlsanity.com/paper/2406.19354/) (2024)
- [Can Editing LLMs Inject Harm?](https://mlsanity.com/paper/2407.20224/) (2024)
- [Editing Conceptual Knowledge for Large Language Models](https://mlsanity.com/paper/2403.06259/) (2024)
- [CodeUpdateArena: Benchmarking Knowledge Editing on API Updates](https://mlsanity.com/paper/2407.06249/) (2024)
- [Knowledge Localization: Mission Not Accomplished? Enter Query Localization!](https://mlsanity.com/paper/2405.14117/) (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)
- [KnowTuning: Knowledge-aware Fine-tuning for Large Language Models](https://mlsanity.com/paper/2402.11176/) (2024)
- [MARS: Benchmarking the Metaphysical Reasoning Abilities of Language Models with a Multi-task Evaluation Dataset](https://mlsanity.com/paper/2406.02106/) (2024)
- [Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation](https://mlsanity.com/paper/2505.01456/) (2025)
- [On the Robustness of Editing Large Language Models](https://mlsanity.com/paper/2402.05827/) (2024)
- [Language Modeling with Editable External Knowledge](https://mlsanity.com/paper/2406.11830/) (2024)
- [COMPKE: Complex Question Answering under Knowledge Editing](https://mlsanity.com/paper/2506.00829/) (2025)
- [Improving Clinical Diagnosis with Counterfactual Multi-Agent Reasoning](https://mlsanity.com/paper/2603.27820/) (2026)
- [Composable Interventions for Language Models](https://mlsanity.com/paper/2407.06483/) (2024)
- [STACKFEED: Structured Textual Actor-Critic Knowledge Base Editing with FeedBack](https://mlsanity.com/paper/2410.10584/) (2024)
- [Keys to Robust Edits: from Theoretical Insights to Practical Advances](https://mlsanity.com/paper/2410.09338/) (2024)
- [Dynamic Retriever for In-Context Knowledge Editing via Policy Optimization](https://mlsanity.com/paper/2510.21059/) (2025)
- [ScEdit: Script-based Assessment of Knowledge Editing](https://mlsanity.com/paper/2505.23291/) (2025)
- [MAAT: Multi-phase Adapter-Aware Targeted Unlearning](https://mlsanity.com/paper/2605.30514/) (2026)
- [Popular Knowledge Propagates More Errors in LLM Knowledge Updating](https://mlsanity.com/paper/2609.08067/) (2026)
- [ALOE: Semantically Addressed Low-Rank Operators for Knowledge Editing](https://mlsanity.com/paper/2609.29269/) (2026)

## Abstract (arXiv)

Current approaches of knowledge editing struggle to effectively propagate updates to interconnected facts. In this work, we delve into the barriers that hinder the appropriate propagation of updated knowledge within these models for accurate reasoning. To support our analysis, we introduce a novel reasoning-based benchmark -- ReCoE (Reasoning-based Counterfactual Editing dataset) -- which covers six common reasoning schemes in real world. We conduct a thorough analysis of existing knowledge editing techniques, including input augmentation, finetuning, and locate-and-edit. We found that all model editing methods show notably low performance on this dataset, especially in certain reasoning schemes. Our analysis over the chain-of-thought generation of edited models further uncover key reasons behind the inadequacy of existing knowledge editing methods from a reasoning standpoint, involving aspects on fact-wise editing, fact recall ability, and coherence in generation. We will make our benchmark publicly available.