Saved in:
Bibliographic Details
Main Authors: Wang, Lei, Dong, Shan, Xu, Yuhui, Dong, Hanze, Wang, Yalu, Saha, Amrita, Lim, Ee-Peng, Xiong, Caiming, Sahoo, Doyen
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.04698
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917796122722304
author Wang, Lei
Dong, Shan
Xu, Yuhui
Dong, Hanze
Wang, Yalu
Saha, Amrita
Lim, Ee-Peng
Xiong, Caiming
Sahoo, Doyen
author_facet Wang, Lei
Dong, Shan
Xu, Yuhui
Dong, Hanze
Wang, Yalu
Saha, Amrita
Lim, Ee-Peng
Xiong, Caiming
Sahoo, Doyen
contents Recent large language models (LLMs) have demonstrated versatile capabilities in long-context scenarios. Although some recent benchmarks have been developed to evaluate the long-context capabilities of LLMs, there is a lack of benchmarks evaluating the mathematical reasoning abilities of LLMs over long contexts, which is crucial for LLMs' application in real-world scenarios. In this paper, we introduce MathHay, an automated benchmark designed to assess the long-context mathematical reasoning capabilities of LLMs. Unlike previous benchmarks like Needle in a Haystack, which focus primarily on information retrieval within long texts, MathHay demands models with both information-seeking and complex mathematical reasoning abilities. We conduct extensive experiments on MathHay to assess the long-context mathematical reasoning abilities of eight top-performing LLMs. Even the best-performing model, Gemini-1.5-Pro-002, still struggles with mathematical reasoning over long contexts, achieving only 51.26% accuracy at 128K tokens. This highlights the significant room for improvement on the MathHay benchmark.
format Preprint
id arxiv_https___arxiv_org_abs_2410_04698
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs
Wang, Lei
Dong, Shan
Xu, Yuhui
Dong, Hanze
Wang, Yalu
Saha, Amrita
Lim, Ee-Peng
Xiong, Caiming
Sahoo, Doyen
Computation and Language
Recent large language models (LLMs) have demonstrated versatile capabilities in long-context scenarios. Although some recent benchmarks have been developed to evaluate the long-context capabilities of LLMs, there is a lack of benchmarks evaluating the mathematical reasoning abilities of LLMs over long contexts, which is crucial for LLMs' application in real-world scenarios. In this paper, we introduce MathHay, an automated benchmark designed to assess the long-context mathematical reasoning capabilities of LLMs. Unlike previous benchmarks like Needle in a Haystack, which focus primarily on information retrieval within long texts, MathHay demands models with both information-seeking and complex mathematical reasoning abilities. We conduct extensive experiments on MathHay to assess the long-context mathematical reasoning abilities of eight top-performing LLMs. Even the best-performing model, Gemini-1.5-Pro-002, still struggles with mathematical reasoning over long contexts, achieving only 51.26% accuracy at 128K tokens. This highlights the significant room for improvement on the MathHay benchmark.
title MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs
topic Computation and Language
url https://arxiv.org/abs/2410.04698