# Answer-Centric or Reasoning-Driven? Uncovering the Latent Memory Anchor in LLMs

arXiv: https://arxiv.org/abs/2506.17630 · HTML: https://mlsanity.com/paper/2506.17630/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 26 of its 52 references that are in the map.
- First posted on arXiv 21 Jun 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)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [Large Language Models for Mathematical Reasoning: Progresses and Challenges](https://mlsanity.com/paper/2402.00157/) (2024)
- [Chain-of-Thought Reasoning In The Wild Is Not Always Faithful](https://mlsanity.com/paper/2503.08679/) (2025)
- [Benchmark Data Contamination of Large Language Models: A Survey](https://mlsanity.com/paper/2406.04244/) (2024)
- [Holistic Evaluation of Language Models](https://mlsanity.com/paper/2211.09110/) (2022)
- [On Memorization of Large Language Models in Logical Reasoning](https://mlsanity.com/paper/2410.23123/) (2024)
- [Yara Parser: A Fast and Accurate Dependency Parser](https://mlsanity.com/paper/1503.06733/) (2015)
- [MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations](https://mlsanity.com/paper/2502.06453/) (2025)
- [Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?](https://mlsanity.com/paper/2504.06514/) (2025)
- [An Open Source Data Contamination Report for Large Language Models](https://mlsanity.com/paper/2310.17589/) (2023)
- [Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation](https://mlsanity.com/paper/2502.17521/) (2025)
- [Can Large Language Models Understand Symbolic Graphics Programs?](https://mlsanity.com/paper/2408.08313/) (2024)
- [Mathematical Reasoning in Large Language Models: Assessing Logical and Arithmetic Errors across Wide Numerical Ranges](https://mlsanity.com/paper/2502.08680/) (2025)
- [What Do Learning Dynamics Reveal About Generalization in LLM Reasoning?](https://mlsanity.com/paper/2411.07681/) (2024)
- [The Order Effect: Investigating Prompt Sensitivity to Input Order in LLMs](https://mlsanity.com/paper/2502.04134/) (2025)
- [Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems?](https://mlsanity.com/paper/2504.00509/) (2025)
- [Beyond Math: Stories as a Testbed for Memorization-Constrained Reasoning in LLMs](https://mlsanity.com/paper/2412.14368/) (2024)
- [Patterns Over Principles: The Fragility of Inductive Reasoning in LLMs under Noisy Observations](https://mlsanity.com/paper/2502.16169/) (2025)
- [Exploring LLM Reasoning Through Controlled Prompt Variations](https://mlsanity.com/paper/2504.02111/) (2025)
- [Predicting the Performance of Black-box LLMs through Follow-up Queries](https://mlsanity.com/paper/2501.01558/) (2025)
- [Memorize or Generalize? Evaluating LLM Code Generation with Code Rewriting](https://mlsanity.com/paper/2503.02296/) (2025)
- [The Challenge of Identifying the Origin of Black-Box Large Language Models](https://mlsanity.com/paper/2503.04332/) (2025)
- [Neuron-Level Differentiation of Memorization and Generalization in Large Language Models](https://mlsanity.com/paper/2412.18497/) (2024)

## Abstract (arXiv)

While Large Language Models (LLMs) demonstrate impressive reasoning capabilities, growing evidence suggests much of their success stems from memorized answer-reasoning patterns rather than genuine inference. In this work, we investigate a central question: are LLMs primarily anchored to final answers or to the textual pattern of reasoning chains? We propose a five-level answer-visibility prompt framework that systematically manipulates answer cues and probes model behavior through indirect, behavioral analysis. Experiments across state-of-the-art LLMs reveal a strong and consistent reliance on explicit answers. The performance drops by 26.90% when answer cues are masked, even with complete reasoning chains. These findings suggest that much of the reasoning exhibited by LLMs may reflect post-hoc rationalization rather than true inference, calling into question their inferential depth. Our study uncovers the answer-anchoring phenomenon with rigorous empirical validation and underscores the need for a more nuanced understanding of what constitutes reasoning in LLMs.