Pith. sign in

REVIEW 5 cited by

Chain of History: Learning and Forecasting with LLMs for Temporal Knowledge Graph Completion

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2401.06072 v2 pith:WC5QVFAE submitted 2024-01-11 cs.AI cs.CL

classification cs.AIcs.CL
keywords llmsknowledgetemporalgraphchaincompletioncomprehensiveexperiments
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Temporal Knowledge Graph Completion (TKGC) is a complex task involving the prediction of missing event links at future timestamps by leveraging established temporal structural knowledge. This paper aims to provide a comprehensive perspective on harnessing the advantages of Large Language Models (LLMs) for reasoning in temporal knowledge graphs, presenting an easily transferable pipeline. In terms of graph modality, we underscore the LLMs' prowess in discerning the structural information of pivotal nodes within the historical chain. As for the generation mode of the LLMs utilized for inference, we conduct an exhaustive exploration into the variances induced by a range of inherent factors in LLMs, with particular attention to the challenges in comprehending reverse logic. We adopt a parameter-efficient fine-tuning strategy to harmonize the LLMs with the task requirements, facilitating the learning of the key knowledge highlighted earlier. Comprehensive experiments are undertaken on several widely recognized datasets, revealing that our framework exceeds or parallels existing methods across numerous popular metrics. Additionally, we execute a substantial range of ablation experiments and draw comparisons with several advanced commercial LLMs, to investigate the crucial factors influencing LLMs' performance in structured temporal knowledge inference tasks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. GRATE: Temporal Extensions for Inductive KG Foundation Models via Gated Rotary Attention

    cs.AI 2026-07 conditional novelty 6.0 of 10

    Parameter-free gated rotary temporal messages lift NBFNet-style KG foundation models to inductive temporal link prediction without tying parameters to entities, relations, or timestamps.

  2. Unveiling the Mechanisms of Multi-Hop Reasoning in Transformers via Identity Bridge

    cs.LG 2025-09 conditional novelty 6.0 of 10

    Adding identity supervision on bridge tokens enables out-of-distribution two-hop reasoning in simple transformers, with a nuclear-norm theory explaining the benefit.

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

    cs.LG 2025-05 conditional novelty 6.0 of 10

    RECIPE-TKG combines rule-based multi-hop history sampling, contrastive LoRA fine-tuning, and test-time semantic filtering to improve LLM temporal knowledge graph completion, with Hits@10 gains up to 30.6% over prior L...

  4. A Multi-Expert Structural-Semantic Hybrid Framework for Unveiling Historical Patterns in Temporal Knowledge Graphs

    cs.CL 2025-06 conditional novelty 5.0 of 10

    MESH integrates a GCN-based structural encoder with a frozen LLM-based semantic encoder via gated expert modules that adapt to historical and non-historical events, achieving modest gains on ICEWS14 and ICEWS18.

  5. Towards Explainable Temporal Reasoning in Large Language Models: A Structure-Aware Generative Framework

    cs.CL 2025-05 conditional novelty 5.0 of 10

    A new benchmark (ETR) and a structure-aware LLM framework (GETER) inject temporal graph embeddings as a soft prompt to improve explainable temporal reasoning.

Pith tools