We describe our system for Shared Task 2 of #SMM4H–HeaRD 2026, which targets the detection of insomnia in MIMIC-III clinical notes. We frame the task as evidence extraction followed by deterministic rule application, rather than end-to-end label prediction. Our system operates in two passes: (1) a Gemini 2.5 Flash large language model (LLM), invoked through typed prompts written in BAML, extracts structured evidence (sleep difficulties, daytime impairment, hypnotic medications) with verbatim character-level citations from each note; (2) a small Python rule engine deterministically applies the task’s published Insomnia rules–Definition 1, Definition 2, and Rules B and C–to derive the binary patient-level label, the rule-component labels, and their evidence spans. We submitted two test-set systems: a zero-shot variant and a retrieval-augmented few-shot variant that selects nearest-neighbor training notes via FAISS over a sentence-embedding index. Our zero-shot variant achieved F1 = 0.8108 on Subtask 1 (binary classification) and a label-classification micro-F1 of 0.7126 with partial-match span F1 = 0.6621 on Subtask 2, both above the across-team mean. We additionally evaluate a GEPA-optimized prompt variant on the validation split. We discuss two findings of methodological interest: the few-shot variant improves Subtask 1 precision but does not improve F1, and does not move the multi-label or span metrics on Subtask 2 in our submission, and pushing the deterministic rule engine to consume LLM-extracted evidence (rather than asking the LLM to emit labels directly) gives strong, easily auditable behavior on a small test set.

The proliferation of Hate Speech and misinformation in social media is fast becoming a menace to society. In compliment, the dissemination of hate-diffusing, promising and anti-oppressive messages become a unique alternative. Unfortunately, due to its complex nature as well as the relatively limited manifestation in comparison to hostile and neutral content, the identification of Hope Speech becomes a challenge. This work revolves around the detection of Hope Speech in Youtube comments, for the Shared Task on Hope Speech Detection for Equality, Diversity, and Inclusion. We achieve an f-score of 0.93, ranking 1st on the leaderboard for English comments.

Since the outbreak of COVID-19, there has been a surge of digital content on social media. The content ranges from news articles, academic reports, tweets, videos, and even memes. Among such an overabundance of data, it is crucial to distinguish which information is actually informative or merely sensational, redundant or false. This work focuses on developing such a language system that can differentiate between Informative or Uninformative tweets associated with COVID-19 for WNUT-2020 Shared Task 2. For this purpose, we employ deep transfer learning models such as BERT along other techniques such as Noisy Data Augmentation and Progress Training. The approach achieves a competitive F1-score of 0.8715 on the final testing dataset.