AI Paper Atlas

Research map / Large language models / Agents, code and math

Lost in Tokenization: Context as the Key to Unlocking Biomolecular Understanding in Scientific LLMs

Kai Zhuang, Jiawei Zhang, Yumou Liu, Hanqun Cao, Chunbin Gu, Mengdi Liu, Zhangyang Gao, Zitong Jerry Wang, Xuanhe Zhou, Pheng-Ann Heng, Lijun Wu, Conghui He and 1 more

ICLR 2026 · Large language models › Agents, code and math · approach: LLMs for scientific discovery

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
add raw protein sequence to the context input (ablation)Evolla · Protein QA benchmark (All)LLM-Score: 74.02 -> 70.53Hurt
add raw protein sequence to the context input (ablation)Intern-S1 · Protein QA benchmark (All)LLM-Score: 86.15 -> 84.03Hurt
add raw protein sequence to the context input (ablation)Gemini2.5 Pro · Protein QA benchmark (All)LLM-Score: 87.19 -> 86.98Hurt
add raw protein sequence to the context input (ablation)Deepseek-v3 · Protein QA benchmark (All)LLM-Score: 84.99 -> 86.03No clear effect
add context to raw sequence input (ablation)Intern-S1 · Protein QA benchmark (All)LLM-Score: 43.33 -> 84.03Improved
add context to raw sequence input (ablation)NatureLM · Protein QA benchmark (All)LLM-Score: 6.82 -> 38.86Improved
add ProTrek output to Pfam + GO context unconditionally (ablation)DeepSeek context pipeline · Protein QA benchmark (Hard subset)LLM-Score: 84.60 -> 81.56Hurt
use ProTrek only as fallback when Pfam and GO are absent (ablation)DeepSeek context pipeline · Protein QA benchmark (Hard subset)LLM-Score: 81.56 -> 84.99Improved
add Pfam to GO context (ablation)DeepSeek context pipeline · Protein QA benchmark (Hard subset)LLM-Score: 84.02 -> 84.60Improved
add ProTrek to GO context (ablation)DeepSeek context pipeline · Protein QA benchmark (Hard subset)LLM-Score: 84.02 -> 77.78Hurt
add ProTrek to Pfam context (ablation)DeepSeek context pipeline · Protein QA benchmark (Hard subset)LLM-Score: 74.90 -> 77.00Improved
replace sequence-as-modality Q-Former alignment with direct textual contextEvolla embeddings · Protein embeddings vs UniClust50 clustersARI: 0.809 -> 0.958Improved

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