BoostTaxo introduces a boosting-style LLM framework for zero-shot taxonomy induction that uses hybrid candidate selection and constraint-aware calibration to achieve superior or comparable performance to prior methods on WordNet, DBLP, and SemEval-Sci benchmarks.
Large language models for generative infor- mation extraction: A survey,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
SRICL combines semantic retrieval from ESCO, in-context learning, fine-tuning, and output verification to achieve higher STRICT-F1 scores and fewer invalid or hallucinated skill spans than GPT-3.5 baselines on six public job-ad datasets.
citing papers explorer
-
BoostTaxo: Zero-Shot Taxonomy Induction via Boosting-Style Agentic Reasoning and Constraint-Aware Calibration
BoostTaxo introduces a boosting-style LLM framework for zero-shot taxonomy induction that uses hybrid candidate selection and constraint-aware calibration to achieve superior or comparable performance to prior methods on WordNet, DBLP, and SemEval-Sci benchmarks.
-
Job Skill Extraction via LLM-Centric Multi-Module Framework
SRICL combines semantic retrieval from ESCO, in-context learning, fine-tuning, and output verification to achieve higher STRICT-F1 scores and fewer invalid or hallucinated skill spans than GPT-3.5 baselines on six public job-ad datasets.