TuringQ: Benchmarking AI Comprehension in Theory of Computation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zahraei, Pardis Sadat, Asgari, Ehsaneddin
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929533659119616
author Zahraei, Pardis Sadat
Asgari, Ehsaneddin
author_facet Zahraei, Pardis Sadat
Asgari, Ehsaneddin
contents We present TuringQ, the first benchmark designed to evaluate the reasoning capabilities of large language models (LLMs) in the theory of computation. TuringQ consists of 4,006 undergraduate and graduate-level question-answer pairs, categorized into four difficulty levels and covering seven core theoretical areas. We evaluate several open-source LLMs, as well as GPT-4, using Chain of Thought prompting and expert human assessment. Additionally, we propose an automated LLM-based evaluation system that demonstrates competitive accuracy when compared to human evaluation. Fine-tuning a Llama3-8B model on TuringQ shows measurable improvements in reasoning ability and out-of-domain tasks such as algebra. TuringQ serves as both a benchmark and a resource for enhancing LLM performance in complex computational reasoning tasks. Our analysis offers insights into LLM capabilities and advances in AI comprehension of theoretical computer science.
format Preprint
id arxiv_https___arxiv_org_abs_2410_06547
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TuringQ: Benchmarking AI Comprehension in Theory of Computation
Zahraei, Pardis Sadat
Asgari, Ehsaneddin
Computation and Language
Formal Languages and Automata Theory
We present TuringQ, the first benchmark designed to evaluate the reasoning capabilities of large language models (LLMs) in the theory of computation. TuringQ consists of 4,006 undergraduate and graduate-level question-answer pairs, categorized into four difficulty levels and covering seven core theoretical areas. We evaluate several open-source LLMs, as well as GPT-4, using Chain of Thought prompting and expert human assessment. Additionally, we propose an automated LLM-based evaluation system that demonstrates competitive accuracy when compared to human evaluation. Fine-tuning a Llama3-8B model on TuringQ shows measurable improvements in reasoning ability and out-of-domain tasks such as algebra. TuringQ serves as both a benchmark and a resource for enhancing LLM performance in complex computational reasoning tasks. Our analysis offers insights into LLM capabilities and advances in AI comprehension of theoretical computer science.
title TuringQ: Benchmarking AI Comprehension in Theory of Computation
topic Computation and Language
Formal Languages and Automata Theory
url https://arxiv.org/abs/2410.06547