REVIEW 4 cited by
Are Large Language Models In-Context Graph Learners?
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
Large language models (LLMs) have demonstrated remarkable in-context reasoning capabilities across a wide range of tasks, particularly with unstructured inputs such as language or images. However, LLMs struggle to handle structured data, such as graphs, due to their lack of understanding of non-Euclidean structures. As a result, without additional fine-tuning, their performance significantly lags behind that of graph neural networks (GNNs) in graph learning tasks. In this paper, we show that learning on graph data can be conceptualized as a retrieval-augmented generation (RAG) process, where specific instances (e.g., nodes or edges) act as queries, and the graph itself serves as the retrieved context. Building on this insight, we propose a series of RAG frameworks to enhance the in-context learning capabilities of LLMs for graph learning tasks. Comprehensive evaluations demonstrate that our proposed RAG frameworks significantly improve LLM performance on graph-based tasks, particularly in scenarios where a pretrained LLM must be used without modification or accessed via an API.
Forward citations
Cited by 4 Pith papers
-
Node-as-Agent: Graph Agentic Network
A node-as-agent framework where a frozen LLM plans each node's local and global message passing achieves competitive Cora accuracy without training, but uses per-dataset prompt selection and leaves label-leakage quest...
-
Are Large Language Models Good Temporal Graph Learners?
TGTalker prompts LLMs with the most recent edges and neighbor history of a temporal graph, achieving link prediction accuracy competitive with specialized temporal graph neural networks on five real-world datasets.
-
Improving LLM Reasoning with Homophily-aware Structural and Semantic Text-Attributed Graph Compression
HS2C compresses text-attributed graphs into homophily-aware community summaries that improve zero-shot LLM node classification while cutting input size.
-
GRIP: In-Parameter Graph Reasoning through Fine-Tuning Large Language Models
An LLM can memorize a knowledge graph into LoRA weights and answer relation/reasoning queries about it without graph context, but the evaluation partly trains on the test task.
Discussion (0). Continue with ORCID to comment.