ALL-IN projects node features to a random shared space and uses covariance operators to produce representations invariant to input feature permutations and orthogonal transformations, enabling transfer across graph datasets.
Unigraph: Learning a cross-domain graph foundation model from natural language.ArXiv, abs/2402.13630
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
The method prompts LLMs to output both answers and references to the executed instructions, then filters out any answers not linked to the original input instructions, reducing attack success rates to zero in tested scenarios while preserving utility.
citing papers explorer
-
Bridging Input Feature Spaces Towards Graph Foundation Models
ALL-IN projects node features to a random shared space and uses covariance operators to produce representations invariant to input feature permutations and orthogonal transformations, enabling transfer across graph datasets.
-
Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction
The method prompts LLMs to output both answers and references to the executed instructions, then filters out any answers not linked to the original input instructions, reducing attack success rates to zero in tested scenarios while preserving utility.