Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations

• URL: http://arxiv.org/abs/2604.11322v1
• Date: Mon, 13 Apr 2026 11:23:36 GMT
• Title: Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations
• Abstract summary: Large language models (LLMs) have demonstrated impressive capabilities in utilizing external tools.<n>LLMs are often exposed to tools that are irrelevant to the user's query.<n>Even when a tool fails to serve the user's goal, LLMs still tend to invoke it whenever query attributes can be validly assigned to tool parameters.
• Score: 32.820855447313825
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) have demonstrated impressive capabilities in utilizing external tools. In practice, however, LLMs are often exposed to tools that are irrelevant to the user's query, in which case the desired behavior is to refrain from invocations. In this work, we identify a widespread yet overlooked mechanistic flaw in tool refusal, which we term structural alignment bias: Even when a tool fails to serve the user's goal, LLMs still tend to invoke it whenever query attributes can be validly assigned to tool parameters. To systematically study this bias, we introduce SABEval, a new dataset that decouples structural alignment from semantic relevance. Our analysis shows that structural alignment bias induces severe tool-invocation errors in LLMs, yet remains largely unaccounted for in existing evaluations. To investigate the internal mechanisms underlying this bias, we propose Contrastive Attention Attribution, which reveals two competing pathways for semantic checking and structural matching. The relative strength of these pathways drives LLMs' tool invocation decisions. Based on these findings, we further introduce a rebalancing strategy that effectively mitigates structural alignment bias, as demonstrated by extensive experiments, without degrading general tool-use capabilities.

Related papers

• Spurious Tool Use: When RL Agents Learn the Wrong Reason to Act [38.40533345940731]
  Large language model (LLM) agents increasingly interleave natural language reasoning with external tools.<n>We study when and why RL-trained agents learn shortcut tool-selection policies.
  arXiv  Detail & Related papers  (2026-09-14T19:31:04Z)
• Forgotten in Weights, Recovered by Tools: Agentic Tool Unlearning for LLM Agents [54.050506620820784]
  Agentic Tool Unlearning (ATU) aims to reduce both parametric recall and tool-mediated recovery while preserving normal tool use for retained knowledge.<n>ATU achieves a better balance between target forgetting and retained utility, making unlearning more robust under tool-augmented agent deployment.
  arXiv  Detail & Related papers  (2026-08-21T18:34:48Z)
• Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates [56.73907811047611]
  Large language models (LLMs) have demonstrated strong reasoning and tool-use capabilities.<n>LLMs often fail in real-world tool-interactions due to incorrect parameterization, poor tool selection, or misinterpretation of user intent.<n>We introduce a curriculum-inspired framework that leverages structured reasoning templates to guide LLMs through more deliberate step-by-step instructions for generating function callings.
  arXiv  Detail & Related papers  (2025-09-22T17:55:14Z)
• RefTool: Enhancing Model Reasoning with Reference-Guided Tool Creation [44.128974924517465]
  RefTool is a reference-guided framework for automatic tool creation.<n>It generates executable tools from reference content, validate them using illustrative examples, and organize them hierarchically into a toolbox.<n> Experiments on causality, physics, and chemistry benchmarks demonstrate that RefTool outperforms existing tool-creation and domain-specific reasoning methods.
  arXiv  Detail & Related papers  (2025-05-27T16:41:19Z)
• Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger [49.81945268343162]
  We propose MeCo, an adaptive decision-making strategy for external tool use.<n>MeCo quantifies metacognitive scores by capturing high-level cognitive signals in the representation space.<n>MeCo is fine-tuning-free and incurs minimal cost.
  arXiv  Detail & Related papers  (2025-02-18T15:45:01Z)
• Learning to Ask: When LLM Agents Meet Unclear Instruction [55.65312637965779]
  Large language models (LLMs) can leverage external tools for addressing a range of tasks unattainable through language skills alone.<n>We evaluate the performance of LLMs tool-use under imperfect instructions, analyze the error patterns, and build a challenging tool-use benchmark called Noisy ToolBench.<n>We propose a novel framework, Ask-when-Needed (AwN), which prompts LLMs to ask questions to users whenever they encounter obstacles due to unclear instructions.
  arXiv  Detail & Related papers  (2024-08-31T23:06:12Z)
• Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learning [57.523454568002144]
  Large language models (LLMs) have shown capabilities in commonsense reasoning and leveraging external tools. We introduce ToolRec, a framework for LLM-empowered recommendations via tool learning. We formulate the recommendation process as a process aimed at exploring user interests in attribute granularity. We consider two types of attribute-oriented tools: rank tools and retrieval tools.
  arXiv  Detail & Related papers  (2024-05-24T00:06:54Z)
• LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error [54.954211216847135]
  Existing large language models (LLMs) only reach a correctness rate in the range of 30% to 60%. We propose a biologically inspired method for tool-augmented LLMs, simulated trial and error (STE) STE orchestrates three key mechanisms for successful tool use behaviors in the biological system: trial and error, imagination, and memory.
  arXiv  Detail & Related papers  (2024-03-07T18:50:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.