Tag
This paper describes a hybrid multi-agent LLM system for conversational depression screening submitted to the eRisk 2026 challenge, using either a paid GPT-5-nano or open-source Gemma 27B model with algorithmic guidance (dialogue tree, reliability-weighted aggregation, cluster-based imputation) to achieve competitive BDI-II assessment at lower cost.
Introduces PAJAMA, a hybrid evaluation system that improves upon the LLM-as-a-judge approach by extracting rubrics and executing them programmatically, pushing the Pareto frontier of speed, cost, and transparency.
This paper presents ClaMPAPP, a hybrid architecture that uses an LLM as an interface to extract features from clinical narratives, which are then passed to an XGBoost classifier for pediatric appendicitis diagnosis, demonstrating improved robustness and safety over end-to-end LLM baselines.
EverydayGPT introduces Confidence-Gated Routing (CGR), a mechanism that per query decides whether to use RAG, direct GPT generation, or refusal, achieving 120x latency reduction on 85% of queries while maintaining answer quality, as demonstrated on a 500-question benchmark.