Research map / Large language models / AI and society
An Open-Ended Benchmark and Formal Framework for Adjuvant Research with MLLM
yi chen, Yu Zhang, Jian Xu, Hua Yue, Xinming Wang, Zequan Lyu, Xu-Yao Zhang, Wei Wei, Cheng-Lin 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 |
|---|---|---|---|
| closed-source instead of open-source models | MLLMs · Adjuvant open-ended Q&A | LLM Score: 7.3 vs 6.4 | Improved |
| closed-source instead of open-source models | MLLMs · Adjuvant open-ended Q&A | STS: 0.7263 vs 0.6922 | Improved |
| closed-source instead of open-source models | MLLMs · Adjuvant open-ended Q&A | BERTScore: 0.5656 vs 0.5504 | Improved |
| think models instead of inference models | MLLMs · Adjuvant open-ended Q&A | RS, IS, STS | Improved |
| scale Qwen3 from 32B to 235B | Qwen3 · Adjuvant open-ended Q&A | LLM Score: 7.6 vs 7.6 | No clear effect |
| fine-tune Qwen3 on general scientific data (ScienceOne) | Qwen3 · Adjuvant open-ended Q&A | LLM Score | Mixed |
| use DeepSeek-V3 instead of other models for hallucination rejection | DeepSeek-V3 · Adjuvant hallucination rejection | Overall HRR: LLM Score 7.8 vs HRR 2.10% | Hurt |
| use domain-specific biomedical models instead of general MLLMs | BioGPT-Large-PubMedQA · Adjuvant open-ended Q&A | LLM Score: 1.9 vs 7.3 | Hurt |
Closest papers by meaning
- Immunogenicity Prediction with Dual Attention Enables Vaccine Target Selection (ICLR 2025 · similarity 0.82)
- Antibody Design Using a Score-based Diffusion Model Guided by Evolutionary, Physical and Geometric Constraints (ICML 2024 · similarity 0.82)
- Contextualizing biological perturbation experiments through language (ICLR 2025 · similarity 0.82)
- ADIOS: Antibody Development via Opponent Shaping (ICML 2025 · similarity 0.81)
- Bayesian Optimization of Antibodies Informed by a Generative Model of Evolving Sequences (ICLR 2025 · similarity 0.81)
- Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models (ICLR 2024 · similarity 0.81)
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.
