pith. sign in

arxiv: 2401.09395 · v6 · pith:4YU3NEOQnew · submitted 2024-01-17 · 💻 cs.CL

Evaluating LLMs' Mathematical and Coding Competency through Ontology-guided Interventions

classification 💻 cs.CL
keywords reasoningcodingllmsmodelstasksdatasetsmathontology
0
0 comments X
read the original abstract

Recent advancements in Large Language Models (LLMs) have showcased striking results on existing logical reasoning benchmarks, with some models even surpassing human performance. However, the true depth of their competencies and robustness in reasoning tasks remains an open question. To this end, in this paper, we focus on two popular reasoning tasks: arithmetic reasoning and code generation. Particularly, we introduce (i) a general ontology of perturbations for math and coding questions, (ii) a semi-automatic method to apply these perturbations, and (iii) two datasets, GSMORE and HUMANEVAL-CORE, respectively, of perturbed math and coding problems to probe LLM capabilities in numeric reasoning and coding tasks. Through comprehensive evaluations of both closed-source and open-source LLMs, we show a significant performance drop across all the models against the perturbed questions, suggesting that the current LLMs lack robust problem solving skills and structured reasoning abilities in many areas, as defined by our ontology. We open-source the datasets and source codes at: https://github.com/declare-lab/LLM-ReasoningTest.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Decomposed Trust: Privacy, Adversarial Robustness, Ethics, and Fairness in Low-Rank LLMs

    cs.LG 2025-11 unverdicted novelty 7.0

    Low-rank compression preserves training-data privacy and improves adversarial robustness but weakens personal-information protection, reduces ethical behavior in zero-shot use, and harms fairness.

  2. GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models

    cs.LG 2024-10 accept novelty 7.0

    LLMs display high variance and major accuracy drops on GSM-Symbolic variants of grade-school math problems, indicating they replicate training patterns rather than execute logical reasoning.

  3. Hallucination is Inevitable: An Innate Limitation of Large Language Models

    cs.CL 2024-01 conditional novelty 7.0

    Hallucinations are inevitable in LLMs because they cannot learn all computable functions according to learning theory.

  4. Disentangling Mathematical Reasoning in LLMs: A Methodological Investigation of Internal Mechanisms

    cs.CL 2026-04 unverdicted novelty 6.0

    Proficient LLMs detect arithmetic tasks early but output correct answers only in final layers, with attention and MLP modules dividing labor in a way absent from less proficient models.

  5. In Context Learning and Reasoning for Symbolic Regression with Large Language Models

    cs.CL 2024-10 unverdicted novelty 5.0

    GPT-4 models rediscover Langmuir isotherms and produce fits on Nikuradse pipe-flow data via iterative chain-of-thought prompting with scientific context and external code feedback.