# Semantic Deception: When Reasoning Models Can't Compute an Addition

arXiv: https://arxiv.org/abs/2512.20812 · HTML: https://mlsanity.com/paper/2512.20812/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 23 of its 42 references that are in the map.
- First posted on arXiv 23 Dec 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 23 of 23)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models](https://mlsanity.com/paper/2410.05229/) (2024)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity](https://mlsanity.com/paper/2506.06941/) (2025)
- [Large Language Models for Mathematical Reasoning: Progresses and Challenges](https://mlsanity.com/paper/2402.00157/) (2024)
- [AI Alignment: A Comprehensive Survey](https://mlsanity.com/paper/2310.19852/) (2023)
- [To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning](https://mlsanity.com/paper/2409.12183/) (2024)
- [ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems](https://mlsanity.com/paper/2505.11831/) (2025)
- [Reasoning Models Can Be Effective Without Thinking](https://mlsanity.com/paper/2504.09858/) (2025)
- [The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks](https://mlsanity.com/paper/2502.08235/) (2025)
- [Large Language Models Can Learn Temporal Reasoning](https://mlsanity.com/paper/2401.06853/) (2024)
- [ARC Prize 2024: Technical Report](https://mlsanity.com/paper/2412.04604/) (2024)
- [Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data](https://mlsanity.com/paper/2407.14985/) (2024)
- [OMEGA: Can LLMs Reason Outside the Box in Math? Evaluating Exploratory, Compositional, and Transformative Generalization](https://mlsanity.com/paper/2506.18880/) (2025)
- [Fully Autonomous AI Agents Should Not be Developed](https://mlsanity.com/paper/2502.02649/) (2025)
- [Emergent Abilities in Large Language Models: A Survey](https://mlsanity.com/paper/2503.05788/) (2025)
- [Deciphering the Factors Influencing the Efficacy of Chain-of-Thought: Probability, Memorization, and Noisy Reasoning](https://mlsanity.com/paper/2407.01687/) (2024)
- [Understanding and Benchmarking Artificial Intelligence: OpenAI's o3 Is Not AGI](https://mlsanity.com/paper/2501.07458/) (2025)
- [Thinking in a Crowd: How Auxiliary Information Shapes LLM Reasoning](https://mlsanity.com/paper/2509.18163/) (2025)
- [Identifying and Mitigating the Influence of the Prior Distribution in Large Language Models](https://mlsanity.com/paper/2504.12585/) (2025)
- [Large Language Models Imitate Logical Reasoning, but at what Cost?](https://mlsanity.com/paper/2509.12645/) (2025)

## Built on by (most cited first, 1 of 1)

- [Anthropomorphism in the age of Large Language Models: An overview of potential risks and mitigations](https://mlsanity.com/paper/2609.38486/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used in situations where human values are at stake, such as decision-making tasks that involve reasoning when performed by humans. We investigate the so-called reasoning capabilities of LLMs over novel symbolic representations by introducing an experimental framework that tests their ability to process and manipulate unfamiliar symbols. We introduce semantic deceptions: situations in which symbols carry misleading semantic associations due to their form, such as being embedded in specific contexts, designed to probe whether LLMs can maintain symbolic abstraction or whether they default to exploiting learned semantic associations. We redefine standard digits and mathematical operators using novel symbols, and task LLMs with solving simple calculations expressed in this altered notation. The objective is: (1) to assess LLMs' capacity for abstraction and manipulation of arbitrary symbol systems; (2) to evaluate their ability to resist misleading semantic cues that conflict with the task's symbolic logic. Through experiments with four LLMs we show that semantic cues can significantly deteriorate reasoning models' performance on very simple tasks. They reveal limitations in current LLMs' ability for symbolic manipulations and highlight a tendency to over-rely on surface-level semantics, suggesting that chain-of-thoughts may amplify reliance on statistical correlations. Even in situations where LLMs seem to correctly follow instructions, semantic cues still impact basic capabilities. These limitations raise ethical and societal concerns, undermining the widespread and pernicious tendency to attribute reasoning abilities to LLMs and suggesting how LLMs might fail, in particular in decision-making contexts where robust symbolic reasoning is essential and should not be compromised by residual semantic associations inherited from the model's training.