← Back to all news
arXiv Machine Learning By Caleb N. Ellington, Jiaqi Wang, Sohan Addagudi, Elijah Cole

Automatic Construction of Strong Simple Baselines

Read the original on arXiv Machine Learning →

The paper proposes using large language models to automatically build simple baselines for deep learning studies in the physical and life sciences. By assembling 36 supervised classification and regression tasks from high‑impact journals, the authors show that the generated baselines recover a median of 95.5% of the performance gap between a trivial predictor and the deep learning model, and in 12 studies even match or surpass the model’s performance. The work also explores how baseline quality varies across domains, venues, and the influence of test‑time compute and contextual information.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
6d ago

Learning Scientific Trajectories to Predict Future Biomedical Discoveries

ForeSCITE is a framework that uses large language models to analyze temporal patterns in biomedical conclusions. It clusters published conclusions, estimates a direction that separates earlier from more recent findings within each cluster, and projects conclusion embeddings along these directions. The projected coordinates are decoded into natural‑language hypotheses, and retrospective evaluations show that ForeSCITE expands semantic coverage, introduces novel biomedical entity pairs, and identifies plausible CAR‑T hypotheses that experts deem biologically relevant.

By Chia-Hsuan Chang, Brian Ondov, Jiang Lv, Lan Jiang, Yunmai Wang, Haerin Song, Xueqing Peng, Qiaozhu Mei, Xiaolei Su, Hua Xu
llmsrag
More like this →
arXiv Machine Learning
4d ago

Do Language Models Know What Compelling Scientific Evidence Looks Like?

The paper introduces EDB-Bio, a benchmark of 96,000 episodes drawn from real biological studies—drug‑perturbation transcriptomics, CRISPR screens, and GWAS—to test whether language models can weigh empirical evidence and predict hypothesis truth. Initial results show that both open‑weight and frontier models are systematically underconfident, matching a trivial base‑rate forecaster in Brier score, but post‑training with proper scoring rules improves calibration and discrimination. In a downstream experiment‑selection task, a calibrated model (Ibis0) outperforms the best frontier model by 2.5×, and Bayes‑factor analysis reveals how models update beliefs, align with expert relevance judgments, and expose biases.

By Conor Igoe, Gabriel Grand, Zane Koch, Albert Bou, Eli Moss, Michaela M. Hinks, Samuel G. Rodriques, Andrew White, Siddharth Narayanan
llmsagentsbenchmarks
More like this →