paper-with-me

홈 › Papers

CURIE: Evaluating LLMs On Multitask Scientific Long Context Understanding and Reasoning

2025-03-14 · HAO CUI, Zahra Shamsi, Gowoon Cheon, Xuejian Ma, Shutong Li, Maria Tikhanovskaya, Peter Norgaard, Nayantara Mudur, Martyna Plomecka, Paul Raccuglia, Yasaman Bahri, Victor V. Albert, Pranesh Srinivasan, Haining Pan, Philippe Faist, Brian Rohr, Ekin Dogus Cubuk, Muratahan Aykol, Amil Merchant, Michael J. Statt, Dan Morris, Drew Purves, Elise Kleeman, Ruth Alcantara, Matthew Abraham, Muqthar Mohammad, Ean Phing VanLee, Chenfei Jiang, Elizabeth Dorfman, Eun-Ah Kim, Michael P Brenner, Viren Jain, Sameera Ponda, Subhashini Venugopalan

Scientific problem-solving involves synthesizing information while applying expert knowledge. We introduce CURIE, a scientific long-Context Understanding,Reasoning and Information Extraction benchmark to measure the potential of Large Language Models (LLMs) in scientific problem-solving and assisting scientists in realistic workflows. This benchmark introduces ten challenging tasks with a total of 580 problems and solution pairs curated by experts in six disciplines - materials science, condensed matter physics, quantum computing, geospatial analysis, biodiversity, and proteins - covering both experimental and theoretical work-flows in science. We evaluate a range of closed and open LLMs on tasks in CURIE which requires domain expertise, comprehension of long in-context information,and multi-step reasoning. While Gemini Flash 2.0 and Claude-3 show consistent high comprehension across domains, the popular GPT-4o and command-R+ fail dramatically on protein sequencing tasks. With the best performance at 32% there is much room for improvement for all models. We hope that insights gained from CURIE can guide the future development of LLMs in sciences. Evaluation code and data are in https://github.com/google/curie

📄 PDF Abstract BibTeX arXiv:2503.13517

Code (1)

google/curie 공식 구현

Tasks

Long-Context Understanding

Similar Papers 제목 키워드 기반

Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agents

2025-02-22 · Patrick Tser Jern Kon, Jiachen Liu, Qiuyi Ding, Yiming Qiu 외

Scientific experimentation, a cornerstone of human progress, demands rigor in reliability, methodical control, and interpretability to yield meaningful results. Despite the growing capabilities of large language models (…

AI Agent

Explainable AI for Curie Temperature Prediction in Magnetic Materials

2025-08-09 · M. Adeel Ajaib, Fariha Nasir, Abdul Rehman arxiv

We explore machine learning techniques for predicting Curie temperatures of magnetic materials using the NEMAD database. By augmenting the dataset with composition-based and domain-aware descriptors, we evaluate the perf…

Finding Symmetry Breaking Order Parameters with Euclidean Neural Networks

2020-07-04 · Tess E. Smidt, Mario Geiger, Benjamin Kurt Miller

Curie's principle states that "when effects show certain asymmetry, this asymmetry must be found in the causes that gave rise to them". We demonstrate that symmetry equivariant neural networks uphold Curie's principle an…

SCALAR: Scientific Citation-based Live Assessment of Long-context Academic Reasoning

2025-02-19 · Renxi Wang, Honglin Mu, Liqun Ma, Lizhi Lin 외

Evaluating large language models' (LLMs) long-context understanding capabilities remains challenging. We present SCALAR (Scientific Citation-based Live Assessment of Long-context Academic Reasoning), a novel benchmark th…

Long-Context Understanding

CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation

2023-11-14 · Weixiang Yan, Haitian Liu, Yunkun Wang, Yunzhe Li 외

Large Language Models (LLMs) have demonstrated remarkable performance on assisting humans in programming and facilitating programming automation. However, existing benchmarks for evaluating the code understanding and gen…

Code Generation