Tag
This paper introduces HCG-RAG, which uses schema-constrained causal graphs for retrieval-augmented generation, achieving 3-20x fewer nodes and 8x-135x fewer LLM calls while matching or exceeding baseline answer quality on medical benchmarks.
This paper proposes a schema-constrained document-level event argument extraction method using fine-tuned mid-sized open LLMs with LoRA, role-set injection, and deterministic decoding, achieving state-of-the-art results on MAVEN-ARG.
This paper presents a modular retrieval-augmented generation (RAG) pipeline for extracting structured clinical observations from conversational nurse-patient transcripts, using schema-constrained prompting and second-pass auditing with Llama and GPT backbones, achieving 80.36% F1 score.