# On the Reasoning Capacity of AI Models and How to Quantify It

arXiv: https://arxiv.org/abs/2501.13833 · HTML: https://mlsanity.com/paper/2501.13833/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 23 Jan 2025.

## Placed in

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

## Builds on (most cited first, 26 of 26)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [Adversarial Examples for Evaluating Reading Comprehension Systems](https://mlsanity.com/paper/1707.07328/) (2017)
- [GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models](https://mlsanity.com/paper/2410.05229/) (2024)
- [Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions](https://mlsanity.com/paper/2308.11483/) (2023)
- [Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks](https://mlsanity.com/paper/2307.02477/) (2023)
- [Language models show human-like content effects on reasoning tasks](https://mlsanity.com/paper/2207.07051/) (2022)
- [Impact of Pretraining Term Frequencies on Few-Shot Reasoning](https://mlsanity.com/paper/2202.07206/) (2022)
- [A Survey on Large Language Models for Critical Societal Domains: Finance, Healthcare, and Law](https://mlsanity.com/paper/2405.01769/) (2024)
- [A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners](https://mlsanity.com/paper/2406.11050/) (2024)
- [Eliminating Position Bias of Language Models: A Mechanistic Approach](https://mlsanity.com/paper/2407.01100/) (2024)
- [Large Language Models Are Not Strong Abstract Reasoners](https://mlsanity.com/paper/2305.19555/) (2023)
- [Bias Testing and Mitigation in LLM-based Code Generation](https://mlsanity.com/paper/2309.14345/) (2023)
- [Serial Position Effects of Large Language Models](https://mlsanity.com/paper/2406.15981/) (2024)
- [LogicAsker: Evaluating and Improving the Logical Reasoning Ability of Large Language Models](https://mlsanity.com/paper/2401.00757/) (2024)
- [Iteration of Thought: Leveraging Inner Dialogue for Autonomous Large Language Model Reasoning](https://mlsanity.com/paper/2409.12618/) (2024)
- [Mitigating Selection Bias with Node Pruning and Auxiliary Options](https://mlsanity.com/paper/2409.18857/) (2024)
- [Phases of learning dynamics in artificial neural networks: with or without mislabeled data](https://mlsanity.com/paper/2101.06509/) (2021)
- [Mitigate Position Bias in Large Language Models via Scaling a Single Dimension](https://mlsanity.com/paper/2406.02536/) (2024)

## Built on by (most cited first, 2 of 2)

- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [Adaptive Graph of Thoughts: Test-Time Adaptive Reasoning Unifying Chain, Tree, and Graph Structures](https://mlsanity.com/paper/2502.05078/) (2025)

## Abstract (arXiv)

Recent advances in Large Language Models (LLMs) have intensified the debate surrounding the fundamental nature of their reasoning capabilities. While achieving high performance on benchmarks such as GPQA and MMLU, these models exhibit limitations in more complex reasoning tasks, highlighting the need for more rigorous evaluation methodologies. We propose a novel phenomenological approach that goes beyond traditional accuracy metrics to probe the underlying mechanisms of model behavior, establishing a framework that could broadly impact how we analyze and understand AI systems. Using positional bias in multiple-choice reasoning tasks as a case study, we demonstrate how systematic perturbations can reveal fundamental aspects of model decision-making. To analyze these behaviors, we develop two complementary phenomenological models: a Probabilistic Mixture Model (PMM) that decomposes model responses into reasoning, memorization, and guessing components and an Information-Theoretic Consistency (ITC) analysis that quantifies the relationship between model confidence and strategy selection. Through controlled experiments on reasoning benchmarks, we show that true reasoning remains challenging for current models, with apparent success often relying on sophisticated combinations of memorization and pattern matching rather than genuine logical deduction. More fundamentally, we demonstrate that accuracy alone often overstates a model's reasoning abilities, as model behavior can be characterized through underlying mechanisms in the phase space of cognitive strategies, revealing how models dynamically balance different approaches when responding to queries. This framework enables quantitative criteria for real-world deployments, allowing applications to specify reliability thresholds based on strategy distributions rather than aggregate performance metrics.