AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

LG-Bench: A Graph-Structured Evaluation Benchmark for Life Science

Lu Sun, Xiangyi Zhang, Xiangyang Zhu, Zijian Chen, Qiang Hu, Yuan Tian, Guangtao Zhai

NeurIPS 2026 · Graph learning › Knowledge and temporal graphs · approach: Temporal knowledge graph reasoning

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces LG-Bench, a graph-structured benchmark of over 10,000 multiple-choice questions across medicine, biology, and chemistry that evaluates models over the topology of scientific knowledge.

Problem

Existing life-science evaluation benchmarks flatten interconnected scientific knowledge into independent question lists, ignoring its underlying topological structure.

Approach

Organizes evaluation questions as a knowledge graph and builds a weighted evaluation over that graph, rather than scoring isolated flat questions.

Key results

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase model scale within Qwen2.5 (0.5B to 72B)Qwen2.5 · LG-Bench OverallKBS (lower is more balanced): 16.11 -> 10.26Improved
increase model scale within Qwen2.5 (14B to 72B)Qwen2.5 · LG-Bench Overallaccuracy and GCS: 83.69/70.42 -> 86.05/74.52Improved
domain-specific medical fine-tuning (Llama3-Med42-8B vs Llama-3-8b)Llama-3-8b · LG-Bench MedicineGCS (%): 54.11 -> 61.60Improved
domain-specific medical fine-tuningLlama-3-8b · LG-Bench MedicineKBS: 35.65 -> 25.61Improved
domain-specific medical fine-tuningLlama-3-8b · LG-Bench ChemistryKBS: 27.97 -> 30.78Hurt
raise similarity threshold theta from 0.4 to 0.45, 0.5, 0.6 (sparser graph) (ablation)LG-Bench graph · LG-Bench GCSGCS and model rank orderNo clear effect
vary hybrid similarity weight gamma between 0.4 and 0.6 (ablation)LG-Bench graph · LG-Benchmodel ranking: Qwen2.5-7B overall GCS 62.20 vs 62.68No clear effect
use graph-based GCS vs human expert ratings (450 questions)LG-Bench metrics · 450-question human studySpearman correlation: 0.94 for GCS, 0.90 for KBSImproved

Experimental setup

Benchmarks: LG-Bench

Metrics: weighted evaluation score

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