TIGA: Tool-Grounded LLM Agents for Controlled Taxonomy Induction
Researchers introduce TIGA, a knowledge-engineering architecture that treats taxonomy induction as an iterative decision process over an explicit state and constrained action space. TIGA combines executable taxonomy-editing tools, interaction memory recording tool calls and rationales, and a runtime-adaptive organizational policy, with an optional global reviewer. Evaluated on four benchmark taxonomies with two LLM backbones, TIGA achieves the strongest structural-quality results in most configurations but does not dominate every precision measure. The gains come with substantially higher token consumption, API-call volume, and inference time, and ablation results show benefits from policy and memory components while global review depends on dataset and revision budget.
It offers a concrete agent architecture and evaluation for building valid, coherent taxonomies with LLMs, while candidly reporting quality gains and their computational costs.
Comments & Questions (0)
No comments yet
Be the first to comment!