LLMs show structural alignment bias by invoking semantically irrelevant tools when query attributes match tool parameters, revealed via SABEval dataset and mitigated by attention rebalancing.
Parameter description, however, should contain the'<class>'placeholder if it is contextually appropriate when replaced with a specific subclass
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations
LLMs show structural alignment bias by invoking semantically irrelevant tools when query attributes match tool parameters, revealed via SABEval dataset and mitigated by attention rebalancing.