SenseMath: Do LLMs Have Number Sense? Evaluating Shortcut Use, Judgment, and Generation

• URL: http://arxiv.org/abs/2604.01988v1
• Date: Thu, 02 Apr 2026 12:50:42 GMT
• Title: SenseMath: Do LLMs Have Number Sense? Evaluating Shortcut Use, Judgment, and Generation
• Abstract summary: Large language models often default to step-by-step computation even when efficient numerical shortcuts are available.<n>This raises a basic question: do they exhibit number sense in a human-like behavioral sense?<n>We introduce SenseMath, a benchmark for evaluating structure-sensitive numerical reasoning in LLMs.
• Score: 21.945468909808923
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models often default to step-by-step computation even when efficient numerical shortcuts are available. This raises a basic question: do they exhibit number sense in a human-like behavioral sense, i.e., the ability to recognize numerical structure, apply shortcuts when appropriate, and avoid them when they are not? We introduce SenseMath, a controlled benchmark for evaluating structure-sensitive numerical reasoning in LLMs. SenseMath contains 4,800 items spanning eight shortcut categories and four digit scales, with matched strong-shortcut, weak-shortcut, and control variants. It supports three evaluation settings of increasing cognitive demand: Shortcut Use (whether models can apply shortcuts on shortcut-amenable problems); Applicability Judgment (whether they can recognize when a shortcut is appropriate or misleading); and Problem Generation (whether they can generate new problem items that correctly admit a given type of shortcut). Our evaluation across five LLMs, ranging from GPT-4o-mini to Llama-3.1-8B, shows a consistent pattern: when explicitly prompted, models readily adopt shortcut strategies and achieve substantial accuracy gains on shortcut-amenable items (up to 15%), yet under standard chain-of-thought prompting they spontaneously employ such strategies in fewer than 40% of cases, even when they demonstrably possess the requisite capability. Moreover, this competence is confined to the Use level; models systematically over-generalise shortcuts to problems where they do not apply, and fail to generate valid shortcut-bearing problems from scratch. Together, these results suggest that current LLMs exhibit procedural shortcut fluency without the structural understanding of when and why shortcuts work that underlies human number sense.

Related papers

• Mitigating Shortcut Reasoning in Language Models: A Gradient-Aware Training Approach [31.233459232809608]
  Shortcut-Aware Reasoning Training (SART) is a gradient-aware framework that detects and mitigates shortcut-promoting samples.<n>Our method identifies shortcut signals through gradient misalignment with validation objectives and answer-token concentration.
  arXiv  Detail & Related papers  (2026-03-21T18:17:17Z)
• The Unlearning Mirage: A Dynamic Framework for Evaluating LLM Unlearning [54.67958855362658]
  We propose a dynamic framework that stress tests unlearning using complex structured queries.<n>Our approach first elicits knowledge from the target model (pre-unlearning) and constructs targeted probes, ranging from simple queries to multi-hop chains.<n>Our framework enables practical and scalable evaluation of unlearning methods without the need for manual construction of forget test sets.
  arXiv  Detail & Related papers  (2026-03-11T19:51:33Z)
• Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching [64.74765550805024]
  Chain-of-Thought prompting elicits step-by-step problem solving, but often at the cost of excessive verbosity in intermediate outputs.<n>We propose Sketch-of-Thought (SoT), a prompting framework that integrates cognitively inspired reasoning paradigms with linguistic constraints.<n>SoT achieves token reductions of up to 84% with minimal accuracy loss across 18 reasoning datasets.
  arXiv  Detail & Related papers  (2025-03-07T06:57:17Z)
• Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models [9.854718405054589]
  Large Language Models (LLMs) have shown remarkable capabilities in various natural language processing tasks. This paper presents Shortcut Suite, a test suite designed to evaluate the impact of shortcuts on LLMs' performance.
  arXiv  Detail & Related papers  (2024-10-17T08:52:52Z)
• Subtle Errors in Reasoning: Preference Learning via Error-injected Self-editing [59.405145971637204]
  We propose a novel preference learning framework called eRror-Injected Self-Editing (RISE)<n>RISE injects predefined subtle errors into pivotal tokens in reasoning or steps to construct hard pairs for error mitigation.<n>Experiments validate the effectiveness of RISE, with preference learning on Qwen2-7B-Instruct yielding notable improvements of 3.0% on GSM8K and 7.9% on MATH with only 4.5K training samples.
  arXiv  Detail & Related papers  (2024-10-09T07:43:38Z)
• AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models [95.09157454599605]
  Large Language Models (LLMs) are becoming increasingly powerful, but they still exhibit significant but subtle weaknesses.<n>Traditional benchmarking approaches cannot thoroughly pinpoint specific model deficiencies.<n>We introduce a unified framework, AutoDetect, to automatically expose weaknesses in LLMs across various tasks.
  arXiv  Detail & Related papers  (2024-06-24T15:16:45Z)
• SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal [64.9938658716425]
  SORRY-Bench is a proposed benchmark for evaluating large language models' (LLMs) ability to recognize and reject unsafe user requests.<n>First, existing methods often use coarse-grained taxonomy of unsafe topics, and are over-representing some fine-grained topics.<n>Second, linguistic characteristics and formatting of prompts are often overlooked, like different languages, dialects, and more -- which are only implicitly considered in many evaluations.
  arXiv  Detail & Related papers  (2024-06-20T17:56:07Z)
• Break the Chain: Large Language Models Can be Shortcut Reasoners [18.047917626825548]
  Chain-of-Thought (CoT) reasoning utilize complex modules but are hampered by high token consumption, limited applicability, and challenges in thinking. This paper conducts a critical evaluation of CoT prompting, extending beyond arithmetic to include complex logical and commonsense reasoning tasks. We propose the integration of human-likes and shortcuts into language models (LMs) through "break the chain" strategies.
  arXiv  Detail & Related papers  (2024-06-04T14:02:53Z)
• Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning [28.162661418161466]
  Large language models (LLMs) have recently shown great potential for in-context learning. This paper investigates the reliance of LLMs on shortcuts or spurious correlations within prompts. We uncover a surprising finding that larger models are more likely to utilize shortcuts in prompts during inference.
  arXiv  Detail & Related papers  (2023-05-26T20:56:30Z)
• Which Shortcut Solution Do Question Answering Models Prefer to Learn? [38.36299280464046]
  Question answering (QA) models for reading comprehension tend to learn shortcut solutions rather than the solutions intended by QA datasets. We show that shortcuts that exploit answer positions and word-label correlations are preferentially learned for extractive and multiple-choice QA. We experimentally show that the learnability of shortcuts can be utilized to construct an effective QA training set.
  arXiv  Detail & Related papers  (2022-11-29T13:57:59Z)
• Why Machine Reading Comprehension Models Learn Shortcuts? [56.629192589376046]
  We argue that larger proportion of shortcut questions in training data make models rely on shortcut tricks excessively. A thorough empirical analysis shows that MRC models tend to learn shortcut questions earlier than challenging questions.
  arXiv  Detail & Related papers  (2021-06-02T08:43:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.