From Voting to Agent Collaboration: Answer-Type-Aware LLM Pipelines for BioASQ 14b
Biomedical question answering requires not only accurate extraction of information from scientific literature but also reliable integration of evidence across multiple documents. This study presents a question-type-specific large language model (LLM) framework for BioASQ 14b Task B, designed to improve answer robustness and evidence grounding in biomedical question answering. Rather than applying a single prompting strategy to all questions, the framework selects different inference procedures for yes/no, factoid, and list questions according to their distinct reasoning and evaluation requirem
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 50%starpig1129/DATAGEN →
- PossiblePossibly related (embedding) · 49%labring/FastGPT →
- PossiblePossibly related (embedding) · 47%RAGless: Q-Q retrieval with score aggregation for closed-domain FAQ [P] →
- PossiblePossibly related (embedding) · 47%KennispuntTwente/tidyprompt →
- LinkedLinked via arxiv author · 85%Taeyun Roh →
“From Voting to Agent Collaboration: Answer-Type-Aware LLM Pipelines for BioASQ 14b”
- LinkedLinked via arxiv author · 85%Eunha Lee →
“From Voting to Agent Collaboration: Answer-Type-Aware LLM Pipelines for BioASQ 14b”
- LinkedLinked via arxiv author · 85%Wonjune Jang →
“From Voting to Agent Collaboration: Answer-Type-Aware LLM Pipelines for BioASQ 14b”
- LinkedLinked via arxiv author · 85%Sohyun Chung →
“From Voting to Agent Collaboration: Answer-Type-Aware LLM Pipelines for BioASQ 14b”