mlsanityData to 7 Oct 2026

Temporal-Aware Heterogeneous Graph Reasoning with Multi-View Fusion for Temporal Question Answering

arXiv 2602.19569 ↗First posted 23 Feb 2026cs.CL cs.AIcited by 0

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Question Answering over Temporal Knowledge Graphs (TKGQA) has attracted growing interest for handling time-sensitive queries. However, existing methods still struggle with: 1) weak incorporation of temporal constraints in question representation, causing biased reasoning; 2) limited ability to perform explicit multi-hop reasoning; and 3) suboptimal fusion of language and graph representations. We propose a novel framework with temporal-aware question encoding, multi-hop graph reasoning, and multi-view heterogeneous information fusion. Specifically, our approach introduces: 1) a constraint-aware question representation that combines semantic cues from language models with temporal entity dynamics; 2) a temporal-aware graph neural network for explicit multi-hop reasoning via time-aware message passing; and 3) a multi-view attention mechanism for more effective fusion of question context and temporal graph knowledge. Experiments on multiple TKGQA benchmarks demonstrate consistent improvements over multiple baselines.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 27 of its 36 references that are in the map. First posted on arXiv 23 Feb 2026.

Builds on

27 of 36 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models15 Jun
  2. 2022TwiRGCN: Temporally Weighted Graph Convolution for Question Answering over Temporal Knowledge Graphs12 Oct

Other references · 25

  1. 2017Inductive Representation Learning on Large Graphscited by 6,284
  2. 2021QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answeringcited by 386
  3. 2018Learning Sequence Encoders for Temporal Knowledge Graph Completioncited by 145
  4. 2024TableBench: A Comprehensive and Complex Benchmark for Table Question Answeringcited by 127
  5. 2020Tensor Decompositions for temporal knowledge base completioncited by 115
  6. 2021Question Answering Over Temporal Knowledge Graphscited by 99
  7. 2019TEQUILA: Temporal Question Answering over Knowledge Basescited by 47
  8. 2022Contrastive Learning Reduces Hallucination in Conversationscited by 39
  9. 2023Time-aware Multiway Adaptive Fusion Network for Temporal Knowledge Graph Question Answeringcited by 27
  10. 2022Improving Time Sensitivity for Question Answering over Temporal Knowledge Graphscited by 26
  11. 2024Question Calibration and Multi-Hop Modeling for Temporal Question Answeringcited by 25
  12. 2022DABERT: Dual Attention Enhanced BERT for Semantic Matchingcited by 21
13 more
  1. 2023Dual Path Modeling for Semantic Matching by Perceiving Subtle Conflictscited by 21
  2. 2022Improving Semantic Matching through Dependency-Enhanced Pre-trained Model with Adaptive Fusioncited by 18
  3. 2022Searching for Optimal Subword Tokenization in Cross-domain NERcited by 17
  4. 2022Robust Lottery Tickets for Pre-trained Language Modelscited by 16
  5. 2025Who Stole Your Data? A Method for Detecting Unauthorized RAG Theftcited by 15
  6. 2025Progressive Mastery: Customized Curriculum Learning with Guided Prompting for Mathematical Reasoningcited by 13
  7. 2025Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performancecited by 13
  8. 2023Unleashing Potential of Evidence in Knowledge-Intensive Dialogue Generationcited by 11
  9. 2024Resolving Word Vagueness with Scenario-guided Adapter for Natural Language Inferencecited by 11
  10. 2025Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modelingcited by 11
  11. 2025HoPE: Hyperbolic Rotary Positional Encoding for Stable Long-Range Dependency Modeling in Large Language Modelscited by 10
  12. 2024Comateformer: Combined Attention Transformer for Semantic Sentence Matchingcited by 9
  13. 2025DeCoRL: Decoupling Reasoning Chains via Parallel Sub-Step Generation and Cascaded Reinforcement for Interpretable and Scalable RLHFcited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Two-stage Generative Question Answering on Temporal Knowledge Graph Using Large Language Models
  2. 2026Reinforcement Learning Enhanced Multi-hop Reasoning for Temporal Knowledge Question Answering
  3. 2025RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models
  4. 2026Let the Agent Search: Autonomous Exploration Beats Rigid Workflows in Temporal Question Answering
  5. 2025Plan of Knowledge: Retrieval-Augmented Large Language Models for Temporal Knowledge Graph Question Answering
  6. 2026SCoP: Structured Constraint Parsing for Evidence-Space Control in Temporal Knowledge Graph Question Answering
  7. 2023Fusing Temporal Graphs into Transformers for Time-Sensitive Question Answering
  8. 2025MemoTime: Memory-Augmented Temporal Knowledge Graph Enhanced Large Language Model Reasoning