Salvato in:
Dettagli Bibliografici
Autori principali: Fan, Jingxuan, Martinson, Sarah, Wang, Erik Y., Hausknecht, Kaylie, Brenner, Jonah, Liu, Danxian, Peng, Nianli, Wang, Corey, Brenner, Michael P.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2410.09988
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910744501551104
author Fan, Jingxuan
Martinson, Sarah
Wang, Erik Y.
Hausknecht, Kaylie
Brenner, Jonah
Liu, Danxian
Peng, Nianli
Wang, Corey
Brenner, Michael P.
author_facet Fan, Jingxuan
Martinson, Sarah
Wang, Erik Y.
Hausknecht, Kaylie
Brenner, Jonah
Liu, Danxian
Peng, Nianli
Wang, Corey
Brenner, Michael P.
contents Advanced applied mathematics problems are underrepresented in existing Large Language Model (LLM) benchmark datasets. To address this, we introduce HARDMath, a dataset inspired by a graduate course on asymptotic methods, featuring challenging applied mathematics problems that require analytical approximation techniques. These problems demand a combination of mathematical reasoning, computational tools, and subjective judgment, making them difficult for LLMs. Our framework auto-generates a large number of problems with solutions validated against numerical ground truths. We evaluate both open- and closed-source LLMs on HARDMath-mini, a sub-sampled test set of 366 problems, as well as on 40 word problems formulated in applied science contexts. Even leading closed-source models like GPT-4 achieve only 43.8% overall accuracy with few-shot Chain-of-Thought prompting, and all models demonstrate significantly lower performance compared to results on existing mathematics benchmark datasets. We additionally conduct a detailed error analysis to gain insights into the failure cases of LLMs. These results demonstrate limitations of current LLM performance on advanced graduate-level applied math problems and underscore the importance of datasets like HARDMath to advance mathematical abilities of LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2410_09988
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HARDMath: A Benchmark Dataset for Challenging Problems in Applied Mathematics
Fan, Jingxuan
Martinson, Sarah
Wang, Erik Y.
Hausknecht, Kaylie
Brenner, Jonah
Liu, Danxian
Peng, Nianli
Wang, Corey
Brenner, Michael P.
Machine Learning
Artificial Intelligence
Advanced applied mathematics problems are underrepresented in existing Large Language Model (LLM) benchmark datasets. To address this, we introduce HARDMath, a dataset inspired by a graduate course on asymptotic methods, featuring challenging applied mathematics problems that require analytical approximation techniques. These problems demand a combination of mathematical reasoning, computational tools, and subjective judgment, making them difficult for LLMs. Our framework auto-generates a large number of problems with solutions validated against numerical ground truths. We evaluate both open- and closed-source LLMs on HARDMath-mini, a sub-sampled test set of 366 problems, as well as on 40 word problems formulated in applied science contexts. Even leading closed-source models like GPT-4 achieve only 43.8% overall accuracy with few-shot Chain-of-Thought prompting, and all models demonstrate significantly lower performance compared to results on existing mathematics benchmark datasets. We additionally conduct a detailed error analysis to gain insights into the failure cases of LLMs. These results demonstrate limitations of current LLM performance on advanced graduate-level applied math problems and underscore the importance of datasets like HARDMath to advance mathematical abilities of LLMs.
title HARDMath: A Benchmark Dataset for Challenging Problems in Applied Mathematics
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2410.09988