mlsanityData to 14 Oct 2026

RECIPE-TKG: From Sparse History to Structured Reasoning for LLM-based Temporal Knowledge Graph Completion

arXiv 2505.17794 ↗First posted 23 May 2025cs.LGcited by 0

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

Abstract (arXiv)

Temporal Knowledge Graphs (TKGs) represent dynamic facts as timestamped relations between entities. TKG completion involves forecasting missing or future links, requiring models to reason over time-evolving structure. While LLMs show promise for this task, existing approaches often overemphasize supervised fine-tuning and struggle particularly when historical evidence is limited or missing. We introduce RECIPE-TKG, a lightweight and data-efficient framework designed to improve accuracy and generalization in settings with sparse historical context. It combines (1) rule-based multi-hop retrieval for structurally diverse history, (2) contrastive fine-tuning of lightweight adapters to encode relational semantics, and (3) test-time semantic filtering to iteratively refine generations based on embedding similarity. Experiments on four TKG benchmarks show that RECIPE-TKG outperforms previous LLM-based approaches, achieving up to 30.6% relative improvement in Hits@10. Moreover, our proposed framework produces more semantically coherent predictions, even for the samples with limited historical context.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 11 of its 28 references that are in the map. First posted on arXiv 23 May 2025.

Builds on

11 of 28 references.

References · 11

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  2. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  3. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,392
  4. 2021TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecastingcited by 67
  5. 2025A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoningcited by 40
  6. 2023Temporal Knowledge Graph Forecasting Without Knowledge Using In-Context Learningcited by 37
  7. 2023GenTKG: Generative Forecasting on Temporal Knowledge Graph with Large Language Modelscited by 30
  8. 2025Tina: Tiny Reasoning Models via LoRAcited by 25
  9. 2024Chain of History: Learning and Forecasting with LLMs for Temporal Knowledge Graph Completioncited by 10
  10. 2015Learning with Memory Embeddingscited by 8
  11. 2025Predictive AI with External Knowledge Infusion: Datasets and Benchmarks for Stock Marketscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Chain-of-History Reasoning for Temporal Knowledge Graph Forecasting
  2. 2024Deja vu: Contrastive Historical Modeling with Prefix-tuning for Temporal Knowledge Graph Reasoning
  3. 2025MemoTime: Memory-Augmented Temporal Knowledge Graph Enhanced Large Language Model Reasoning
  4. 2025Towards Foundation Model on Temporal Knowledge Graph Reasoning
  5. 2025A Multi-Expert Structural-Semantic Hybrid Framework for Unveiling Historical Patterns in Temporal Knowledge Graphs
  6. 2026LLM-Guided Knowledge Distillation for Temporal Knowledge Graph Reasoning
  7. 2025DyG-RAG: Dynamic Graph Retrieval-Augmented Generation with Event-Centric Reasoning
  8. 2025T-GRAG: A Dynamic GraphRAG Framework for Resolving Temporal Conflicts and Redundancy in Knowledge Retrieval