Research map / Large language models / Instruction and fine-tuning
SPR-RAFT: Parameter-Efficient Regression-Aware Fine-Tuning for Biomedical LLM Regression
Yuanlin Yang, Chenhui Li, Xuhao Guo, Anqi Zhang, Hoi Leong Lee, Haodong Liu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add GLS correlation-aware fusion instead of naive IVW (ablation) | SPR-RAFT · TrialBench Duration Phase I | MAE: 0.73 -> 0.70 | Improved |
| add regression head to soft prompt (ablation) | SPR-RAFT · TrialBench Duration Phase I | MAE: 0.78 -> 0.70 | Improved |
| add soft prompt to regression head (ablation) | SPR-RAFT · TrialBench Duration Phase I | MAE: 0.74 -> 0.70 | Improved |
| lengthen soft prompt from 16 to 32 (ablation) | SPR-RAFT · TrialBench Duration Phase I | MAE: 0.72 -> 0.70 | Improved |
| lengthen soft prompt from 32 to 64 (ablation) | SPR-RAFT · TrialBench Duration Phase I | MAE: 0.70 -> 0.69 | No clear effect |
| swap Qwen3-4B for Llama-3.2-3B backbone (ablation) | SPR-RAFT · TrialBench Duration Phase I | MAE: 0.70 -> 0.93 | Hurt |
| swap Qwen3-4B for Gemma3-4B backbone (ablation) | SPR-RAFT · TrialBench Duration Phase I | MAE: 0.70 -> 0.80 | Hurt |
| scale backbone from Qwen3-4B to Qwen3-8B (ablation) | SPR-RAFT · TrialBench Duration Phase I | MAE: 0.70 -> 0.68 | No clear effect |
| use SPR-RAFT instead of RAFT on Llama-3.2-3B | backbone · TrialBench Duration Phase I | MAE: 1.92 -> 0.93 | Improved |
| use SPR-RAFT instead of RAFT on Qwen3-8B | backbone · TrialBench Duration Phase I | MAE: 0.88 -> 0.68 | Improved |
| fuse head and text branches instead of text-only (ablation) | SPR-RAFT · uncertainty diagnostic | MSE: 1.345 -> 1.129 | Improved |
| use SPR-RAFT instead of RAFT | LLM regression · NHANES (2007-2018) | AUC: 0.75 -> 0.84 | Improved |
Closest papers by meaning
- BioXArena: Benchmarking LLM Agents on Multi-Modal Biomedical Machine Learning Tasks (NeurIPS 2026 · similarity 0.84)
- Small Models are LLM Knowledge Triggers for Medical Tabular Prediction (ICLR 2025 · similarity 0.84)
- Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains (ICML 2024 · similarity 0.84)
- Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation (NeurIPS 2026 · similarity 0.83)
- FunctionEvolve: Structure-Guided Symbolic Regression with LLMs (NeurIPS 2026 · similarity 0.83)
- CGBench: Benchmarking Language Model Scientific Reasoning for Clinical Genetics Research (NeurIPS 2025 · similarity 0.83)
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.
