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
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.
Forward citations
Cited by 5 Pith papers
-
GRATE: Temporal Extensions for Inductive KG Foundation Models via Gated Rotary Attention
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.
-
Unveiling the Mechanisms of Multi-Hop Reasoning in Transformers via Identity Bridge
Adding identity supervision on bridge tokens enables out-of-distribution two-hop reasoning in simple transformers, with a nuclear-norm theory explaining the benefit.
-
RECIPE-TKG: From Sparse History to Structured Reasoning for LLM-based Temporal Knowledge Graph Completion
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...
-
A Multi-Expert Structural-Semantic Hybrid Framework for Unveiling Historical Patterns in Temporal Knowledge Graphs
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.
-
Towards Explainable Temporal Reasoning in Large Language Models: A Structure-Aware Generative Framework
A new benchmark (ETR) and a structure-aware LLM framework (GETER) inject temporal graph embeddings as a soft prompt to improve explainable temporal reasoning.
Discussion (0). Continue with ORCID to comment.