Lune

EMNLP Findings2025

StepKE: Stepwise Knowledge Editing for Multi-Hop Question Answering

Jaewook Lee, Dahyun Jung, Heuiseok Lim

Abstract

Knowledge editing aims to update Large Language Models (LLMs) with new information without costly retraining. However, consistently reflecting these updates in complex multihop Question Answering (QA), which demands reasoning over interconnected facts, is challenging. Many existing methods overlook the interplay with pre-existing knowledge, leading to inconsistent edit propagation. To overcome this, we introduce StepKE (Stepwise Knowledge Editing for Multi-hop QA), a novel framework for robustly integrating edited and existing knowledge for coherent multi-hop reasoning. StepKE uniquely decomposes multihop questions into sequential single-hop subquestions, retrieving relevant facts (both edited and pre-existing) from an external knowledge graph for each step. It employs context-aware prompting with prior reasoning history and finetuning for precise edit propagation. This systematic integration enables effective stepwise reasoning. Experiments show StepKE generates significantly more accurate and consistent responses than baselines, showcasing strong knowledge editing and integration in multi-hop QA.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Locating and Editing Factual Associations in GPT cites Fast Model Editing at Scale
  • Editing Large Language Models: Problems, Methods, and Opportunities cites Locating and Editing Factual Associations in GPT
  • PMET: Precise Model Editing in a Transformer cites Locating and Editing Factual Associations in GPT
  • PMET: Precise Model Editing in a Transformer cites Editing Large Language Models: Problems, Methods, and Opportunities
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on13

  1. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  2. Locating and Editing Factual Associations in GPTKevin Meng, David Bau, Alex Andonian, Yonatan BelinkovNeurIPS 2022 · 3,415 citations
  3. Fast Model Editing at ScaleEric Mitchell, Charles Lin, Antoine Bosselut, Chelsea Finn et al.ICLR 2022 · 527 citations
  4. PMET: Precise Model Editing in a TransformerXiaopeng Li, Shasha Li, Shezheng Song, Jing Yang et al.AAAI 2024 · 208 citations
  5. Editing Large Language Models: Problems, Methods, and OpportunitiesYunzhi Yao, Peng Wang, Bozhong Tian, Siyuan Cheng et al.EMNLP 2023 · 83 citations

Related papers

  1. Avoiding Knowledge Edit Skipping in Multi-hop Question Answering with Guided DecompositionYi Liu, Xiangrong Zhu, Xiangyu Liu, Wei Wei et al.EMNLP Findings 2025
  2. Robust Knowledge Editing via Explicit Reasoning Chains for Distractor-Resilient Multi-Hop QAYuchen Wu, Liang Ding, Li Shen, Dacheng TaoEMNLP Findings 2025 · 1 citation
  3. PokeMQA: Programmable knowledge editing for Multi-hop Question AnsweringHengrui Gu, Kaixiong Zhou, Xiaotian Han, Ninghao Liu et al.ACL 2024 · 7 citations
  4. Hybrid-DMKG: A Hybrid Reasoning Framework over Dynamic Multimodal Knowledge Graphs for Multimodal Multihop QA with Knowledge EditingLi Yuan, Qingfei Huang, Bingshan Zhu, Yi Cai et al.AAAI 2026
  5. Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question AnsweringYifan Lu, Yigeng Zhou, Jing Li, Yequan Wang et al.AAAI 2025 · 19 citations
Dusk over the sea between two cliffs drawn in fine vertical lines