AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

AFD-INSTRUCTION: A Comprehensive Antibody Instruction Dataset with Functional Annotations for LLM-Based Understanding and Design

Ling Luo, Wenbin Jiang, Hongyuan Chang, Xinkang Wang, Xushi Zhang, Yueting Xiong, Mengsha Tong, Rongshan Yu

ICLR 2026 · Large language models › Instruction and fine-tuning · approach: Calibration and knowledge in LLM tuning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
instruction-tune on AFD-InstructionQwen2-7B · Antibody disease association classificationaccuracy: 32.96 -> 87.83Improved
instruction-tune on AFD-InstructionLLaMA-8B · Antibody disease association classificationaccuracy: 6.19 -> 85.11Improved
instruction-tune on AFD-InstructionQwen2-7B · Antibody binding classificationaccuracy: 53.42 -> 87.81Improved
instruction-tune on AFD-InstructionLLaMA-8B · Antibody mechanism classificationaccuracy: 59.72 -> 92.91Improved
instruction-tune on AFD-InstructionQwen2-7B · Antibody class classificationaccuracy: 90.47 -> 98.86Improved
instruction-tune on AFD-InstructionQwen2-7B · Antibody function classificationaccuracy: 64.59 -> 85.01Improved
scale tuned model from 8B to 70BLLaMAB · Antibody understanding (accuracy)accuracy: 87.01 -> 88.35No clear effect
instruction-tune on AFD-InstructionQwen2-7B · Disease captionROUGE-L: 33.37 -> 61.81Improved
instruction-tune on AFD-InstructionLLaMA-8B · Binding captionROUGE-L: 22.47 -> 37.33Improved
instruction-tune on AFD-Instruction vs strongest antibody-specific modelLLaMA-8B · CDR-H3 designSRR: 0.852 -> 0.884Improved
instruction-tune on AFD-Instruction vs general LLMQwen · CDR-H3 designSRR: 0.163 -> 0.875Improved
instruction-tune on AFD-Instruction vs antibody-specific modelLLaMA-70B · CDR-H3 designipTM: 0.423 -> 0.491Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy