Salvato in:
Dettagli Bibliografici
Autori principali: Nagarkar, Crish, Bogachev, Leonid, Sharoff, Serge
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2601.14479
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911388804317184
author Nagarkar, Crish
Bogachev, Leonid
Sharoff, Serge
author_facet Nagarkar, Crish
Bogachev, Leonid
Sharoff, Serge
contents This paper investigates the ability of large language models (LLMs) to solve statistical tasks, as well as their capacity to assess the quality of reasoning. While state-of-the-art LLMs have demonstrated remarkable performance in a range of NLP tasks, their competence in addressing even moderately complex statistical challenges is not well understood. We have fine-tuned selected open-source LLMs on a specially developed dataset to enhance their statistical reasoning capabilities, and compared their performance with the human scores used as a benchmark. Our results show that the fine-tuned models achieve better performance on advanced statistical tasks on the level comparable to a statistics student. Fine-tuning demonstrates architecture-dependent improvements, with some models showing significant performance gains, indicating clear potential for deployment in educational technology and statistical analysis assistance systems. We also show that LLMs themselves can be far better judges of the answers quality (including explanation and reasoning assessment) in comparison to traditional metrics, such as BLEU or BertScore. This self-evaluation capability enables scalable automated assessment for statistical education platforms and quality assurance in automated analysis tools. Potential applications also include validation tools for research methodology in academic and industry settings, and quality control mechanisms for data analysis workflows.
format Preprint
id arxiv_https___arxiv_org_abs_2601_14479
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Can LLM Reasoning Be Trusted? A Comparative Study: Using Human Benchmarking on Statistical Tasks
Nagarkar, Crish
Bogachev, Leonid
Sharoff, Serge
Computation and Language
This paper investigates the ability of large language models (LLMs) to solve statistical tasks, as well as their capacity to assess the quality of reasoning. While state-of-the-art LLMs have demonstrated remarkable performance in a range of NLP tasks, their competence in addressing even moderately complex statistical challenges is not well understood. We have fine-tuned selected open-source LLMs on a specially developed dataset to enhance their statistical reasoning capabilities, and compared their performance with the human scores used as a benchmark. Our results show that the fine-tuned models achieve better performance on advanced statistical tasks on the level comparable to a statistics student. Fine-tuning demonstrates architecture-dependent improvements, with some models showing significant performance gains, indicating clear potential for deployment in educational technology and statistical analysis assistance systems. We also show that LLMs themselves can be far better judges of the answers quality (including explanation and reasoning assessment) in comparison to traditional metrics, such as BLEU or BertScore. This self-evaluation capability enables scalable automated assessment for statistical education platforms and quality assurance in automated analysis tools. Potential applications also include validation tools for research methodology in academic and industry settings, and quality control mechanisms for data analysis workflows.
title Can LLM Reasoning Be Trusted? A Comparative Study: Using Human Benchmarking on Statistical Tasks
topic Computation and Language
url https://arxiv.org/abs/2601.14479