mlsanityData to 7 Oct 2026

Multi-hop Question Answering under Temporal Knowledge Editing

arXiv 2404.00492 ↗First posted 30 Mar 2024cs.CL cs.AI cs.LGcited by 36

Not on the map. Why?

Abstract (arXiv)

Multi-hop question answering (MQA) under knowledge editing (KE) has garnered significant attention in the era of large language models. However, existing models for MQA under KE exhibit poor performance when dealing with questions containing explicit temporal contexts. To address this limitation, we propose a novel framework, namely TEMPoral knowLEdge augmented Multi-hop Question Answering (TEMPLE-MQA). Unlike previous methods, TEMPLE-MQA first constructs a time-aware graph (TAG) to store edit knowledge in a structured manner. Then, through our proposed inference path, structural retrieval, and joint reasoning stages, TEMPLE-MQA effectively discerns temporal contexts within the question query. Experiments on benchmark datasets demonstrate that TEMPLE-MQA significantly outperforms baseline models. Additionally, we contribute a new dataset, namely TKEMQA, which serves as the inaugural benchmark tailored specifically for MQA with temporal scopes.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). Builds on 38 of its 50 references that are in the map. First posted on arXiv 30 Mar 2024.

Builds on

38 of 50 references.

References · 38

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  3. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  4. 2023A Survey of Large Language Modelscited by 2,537
  5. 2022Mass-Editing Memory in a Transformercited by 976
  6. 2022Towards Reasoning in Large Language Models: A Surveycited by 593
  7. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 554
  8. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 550
  9. 2021Editing Factual Knowledge in Language Modelscited by 548
  10. 2021Fast Model Editing at Scalecited by 491
  11. 2022Memory-Based Model Editing at Scalecited by 443
  12. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 326
26 more
  1. 2023MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questionscited by 292
  2. 2023Can We Edit Factual Knowledge by In-Context Learning?cited by 284
  3. 2022Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptorscited by 267
  4. 2023Evaluating the Ripple Effects of Knowledge Editing in Language Modelscited by 238
  5. 2020Modifying Memories in Transformer Modelscited by 222
  6. 2023Knowledge Editing for Large Language Models: A Surveycited by 189
  7. 2023PMET: Precise Model Editing in a Transformercited by 170
  8. 2020Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgettingcited by 169
  9. 2024A Comprehensive Study of Knowledge Editing for Large Language Modelscited by 157
  10. 2023An LLM can Fool Itself: A Prompt-Based Adversarial Attackcited by 111
  11. 2021Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefscited by 79
  12. 2024MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learningcited by 63
  13. 2023Meta-Learning Online Adaptation of Language Modelscited by 43
  14. 2021High Dimensional Differentially Private Stochastic Optimization with Heavy-tailed Datacited by 42
  15. 2024WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editingcited by 40
  16. 2024DeepEdit: Knowledge Editing as Decoding with Constraintscited by 33
  17. 2022SEAT: Stable and Explainable Attentioncited by 25
  18. 2023PokeMQA: Programmable knowledge editing for Multi-hop Question Answeringcited by 23
  19. 2023Differentially Private Natural Language Models: Recent Advances and Future Directionscited by 20
  20. 2023Practical Differentially Private and Byzantine-resilient Federated Learningcited by 18
  21. 2023History Matters: Temporal Knowledge Editing in Large Language Modelcited by 17
  22. 2023Faithful Question Answering with Monte-Carlo Planningcited by 16
  23. 2020Fine-Grained Named Entity Typing over Distantly Supervised Data Based on Refined Representationscited by 12
  24. 2021Faster Rates of Private Stochastic Convex Optimizationcited by 12
  25. 2024See the Unseen: Better Context-Consistent Knowledge-Editing by Noisescited by 5
  26. 2024Revisiting Differentially Private Hyper-parameter Tuningcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 15; 2025: 14; 2026: 7.

36 papers.

Sort:

By area:

  1. 2024Graph Retrieval-Augmented Generation: A Surveycited by 320
  2. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  3. 2024Locate-then-edit for Multi-hop Factual Recall under Knowledge Editingcited by 36
  4. 2024Can Knowledge Editing Really Correct Hallucinations?cited by 28
  5. 2024Editable Concept Bottleneck Modelscited by 22
  6. 2024Can Editing LLMs Inject Harm?cited by 22
  7. 2025Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMscited by 20
  8. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Surveycited by 18
  9. 2025Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Modelscited by 16
  10. 2024A Hopfieldian View-based Interpretation for Chain-of-Thought Reasoningcited by 15
  11. 2024CypherBench: Towards Precise Retrieval over Full-scale Modern Knowledge Graphs in the LLM Eracited by 13
  12. 2025Towards User-level Private Reinforcement Learning with Human Feedbackcited by 13
24 more
  1. 2025CODEMENV: Benchmarking Large Language Models on Code Migrationcited by 13
  2. 2024OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing Systemcited by 12
  3. 2024Leveraging Logical Rules in Knowledge Editing: A Cherry on the Topcited by 11
  4. 2025Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoningcited by 11
  5. 2024Understanding Reasoning in Chain-of-Thought from the Hopfieldian Viewcited by 10
  6. 2024Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answeringcited by 10
  7. 2025PIXEL: Adaptive Steering Via Position-wise Injection with eXact Estimated Levels under Subspace Calibrationcited by 10
  8. 2024MQA-KEAL: Multi-hop Question Answering under Knowledge Editing for Arabic Languagecited by 9
  9. 2026Predicting LLM Output Length via Entropy-Guided Representationscited by 9
  10. 2024Towards Multi-dimensional Explanation Alignment for Medical Classificationcited by 6
  11. 2025COMPKE: Complex Question Answering under Knowledge Editingcited by 6
  12. 2025OntoRAG: Enhancing Question-Answering through Automated Ontology Derivation from Unstructured Knowledge Basescited by 3
  13. 2025The Compositional Architecture of Regret in Large Language Modelscited by 3
  14. 2025Tracing and Mitigating Hallucinations in Multimodal LLMs via Dynamic Attention Localizationcited by 3
  15. 2026Understanding the Dynamics of Demonstration Conflict in In-Context Learningcited by 2
  16. 2024Review-Then-Refine: A Dynamic Framework for Multi-Hop Question Answering with Temporal Adaptabilitycited by 1
  17. 2025Knowledge Editing for Multi-Hop Question Answering Using Semantic Analysiscited by 1
  18. 2025A-IPO: Adaptive Intent-driven Preference Optimizationcited by 1
  19. 2026Controllable Concept Bottleneck Modelscited by 1
  20. 2026PRISM Edit: One Vector for All Temporal Answerscited by 1
  21. 2025Consistency-Aware Parameter-Preserving Knowledge Editing Framework for Multi-Hop Question Answeringcited by 0
  22. 2026Multi-Adapter Representation Interventions via Energy Calibrationcited by 0
  23. 2026ChartWalker: Benchmarking the Cross-Chart RAG Task with Hierarchical Knowledge Graphscited by 0
  24. 2026Multimodal Graph RAG for Long-range Visually Rich Document Understandingcited by 0