# PropMEND: Hypernetworks for Knowledge Propagation in LLMs

arXiv: https://arxiv.org/abs/2506.08920 · HTML: https://mlsanity.com/paper/2506.08920/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 46 references that are in the map.
- First posted on arXiv 10 Jun 2025.

## Builds on (most cited first, 30 of 41)

- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (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)
- [Zero-Shot Relation Extraction via Reading Comprehension](https://mlsanity.com/paper/1706.04115/) (2017)
- [The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"](https://mlsanity.com/paper/2309.12288/) (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)
- [Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors](https://mlsanity.com/paper/2211.11031/) (2022)
- [Evaluating the Ripple Effects of Knowledge Editing in Language Models](https://mlsanity.com/paper/2307.12976/) (2023)
- [Continual Pre-training of Language Models](https://mlsanity.com/paper/2302.03241/) (2023)
- [Editable Neural Networks](https://mlsanity.com/paper/2004.00345/) (2020)
- [Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue](https://mlsanity.com/paper/2401.04700/) (2024)
- [EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models](https://mlsanity.com/paper/2308.07269/) (2023)
- [How Do Large Language Models Acquire Factual Knowledge During Pretraining?](https://mlsanity.com/paper/2406.11813/) (2024)
- [Can LMs Learn New Entities from Descriptions? Challenges in Propagating Injected Knowledge](https://mlsanity.com/paper/2305.01651/) (2023)
- [Massive Editing for Large Language Models via Meta Learning](https://mlsanity.com/paper/2311.04661/) (2023)
- [Entity Cloze By Date: What LMs Know About Unseen Entities](https://mlsanity.com/paper/2205.02832/) (2022)
- [Instruction-tuned Language Models are Better Knowledge Learners](https://mlsanity.com/paper/2402.12847/) (2024)
- [Evaluating the Reversal Curse in Model Editing](https://mlsanity.com/paper/2310.10322/) (2023)
- [Reinforced Lifelong Editing for Language Models](https://mlsanity.com/paper/2502.05759/) (2025)
- [ECLeKTic: a Novel Challenge Set for Evaluation of Cross-Lingual Knowledge Transfer](https://mlsanity.com/paper/2502.21228/) (2025)
- [Propagating Knowledge Updates to LMs Through Distillation](https://mlsanity.com/paper/2306.09306/) (2023)
- [Perturbation-Restrained Sequential Model Editing](https://mlsanity.com/paper/2405.16821/) (2024)

## Built on by (most cited first, 3 of 3)

- [Scaling Laws for Hypernetwork-Based Knowledge Injection in Large Language Models](https://mlsanity.com/paper/2607.19604/) (2026)
- [Epistemic Goggles: A Pretrained Module that Induces an Epistemic Frame via Gradient Editing](https://mlsanity.com/paper/2607.01690/) (2026)
- [Revisiting Ripple Effects in Knowledge Editing through Pressure-Aware Joint Neighborhood Optimization](https://mlsanity.com/paper/2606.01610/) (2026)

## Abstract (arXiv)

Knowledge editing techniques for large language models (LLMs) can inject knowledge that is later reproducible verbatim, but they fall short on propagating that knowledge: models cannot answer questions that require reasoning with the injected knowledge. We present a hypernetwork-based approach for knowledge propagation, named PropMEND, where we meta-learn how to modify gradients of a language modeling loss to encourage injected information to propagate. Our approach extends the meta-objective of MEND [29] so that gradient updates on knowledge are transformed to enable answering multi-hop questions involving that knowledge. We show improved performance on the RippleEdit dataset, showing almost 2x accuracy on challenging multi-hop questions whose answers are not explicitly stated in the injected fact. We further introduce a new dataset, Controlled RippleEdit, to evaluate the generalization of our hypernetwork, testing knowledge propagation along relations and entities unseen during hypernetwork training. PropMEND still outperforms existing approaches in unseen entity-relation pairs, yet the performance gap decreases substantially, suggesting future work in propagating knowledge to a wide range of relations.