@inproceedings{estuar-2026-team,
    title = "Team Gazoo! at {\#}{SMM}4{H}-{H}ea{RD} 2026: Zero-Training {NER} via Iterative {LLM} Prompt Self-Optimization for Opioid Impact Span Detection",
    author = "Estuar, Diego",
    editor = "Lopez-Garcia, Guillermo  and
      Gonzalez-Hernandez, Graciela",
    booktitle = "Proceedings of the 11th Social Media Mining for Health Research and Applications ({SMM}4{H}-{H}ea{RD} 2026) Workshop and Shared Tasks",
    month = jul,
    year = "2026",
    address = "San Diego, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.smm4h-1.6/",
    pages = "28--35",
    ISBN = "979-8-89176-432-3",
    abstract = "This paper describes the system submitted by Team Gazoo! for Task{~}7 of the {\#}SMM4H-HeaRD 2026 shared task on detecting self-reported clinical and social impacts of nonmedical opioid use in social media text. We present a zero-training, prompt-only approach that uses a large language model (GPT-5.4) with structured few-shot prompting and autonomous, iterative rule optimization. Our system encodes a domain-specific entity ontology, three core decision rules, and 65 cognitively organized few-shot examples into a single prompt, with BIO constraint enforcement applied as post-processing. Crucially, the prompt itself is refined by the LLM: at each iteration the model analyzes its own errors and proposes targeted edits to its rules and examples. Through 18 such self-refinement cycles, our system achieved an F1-Strict of 0.53 and F1-Relaxed of 0.60 on the test set, ranking first among all participating teams under both evaluation criteria."
}