# Compliance vs. Sensibility: On the Reasoning Controllability in Large Language Models

arXiv: https://arxiv.org/abs/2604.27251 · HTML: https://mlsanity.com/paper/2604.27251/

## 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 18 of its 48 references that are in the map.
- First posted on arXiv 29 Apr 2026.

## Placed in

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

## Builds on (most cited first, 18 of 18)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [A Comprehensive Study of Knowledge Editing for Large Language Models](https://mlsanity.com/paper/2401.01286/) (2024)
- [Olmo 3](https://mlsanity.com/paper/2512.13961/) (2025)
- [Are DeepSeek R1 And Other Reasoning Models More Faithful?](https://mlsanity.com/paper/2501.08156/) (2025)
- [Isambard-AI: a leadership class supercomputer optimised specifically for Artificial Intelligence](https://mlsanity.com/paper/2410.11199/) (2024)
- [Logical Reasoning in Large Language Models: A Survey](https://mlsanity.com/paper/2502.09100/) (2025)
- [Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps](https://mlsanity.com/paper/2502.14829/) (2025)
- [Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models](https://mlsanity.com/paper/2505.10554/) (2025)
- [Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering](https://mlsanity.com/paper/2505.12189/) (2025)
- [Evaluating the Logical Reasoning Abilities of Large Reasoning Models](https://mlsanity.com/paper/2505.11854/) (2025)
- [Do Language Models Follow Occam's Razor? An Evaluation of Parsimony in Inductive and Abductive Reasoning](https://mlsanity.com/paper/2509.03345/) (2025)
- [Fundamental Reasoning Paradigms Induce Out-of-Domain Generalization in Language Models](https://mlsanity.com/paper/2602.08658/) (2026)

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

- [Plan Pointers and Record-Directive Form in Budgeted Verification of Inherited Agent Memory](https://mlsanity.com/paper/2609.03450/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) acquire reasoning capabilities through shared inference patterns in pre-training data, which are further elicited via Chain-of-Thought (CoT). However, whether fundamental reasoning patterns, such as induction, deduction, and abduction, can be decoupled from specific problem instances remains a critical challenge for model controllability. In this paper, we present the first systematic investigation of this problem through the lens of reasoning conflicts, an explicit tension between parametric and contextual information induced by mandating logical schemata that deviate from those expected for a target task. Our evaluation reveals that LLMs consistently prioritize sensibility over compliance, favoring task-appropriate reasoning patterns despite conflicting instructions. We further demonstrate that reasoning conflicts are internally detectable, as confidence scores drop during conflicting episodes. Probing reveals instruction decodability even without compliance, while CKA identifies geometric differences across models and spans. Leveraging these insights, we steer models towards compliance, increasing instruction following by up to 29%. Overall, our findings establish that while LLM reasoning is anchored to concrete instances, active mechanistic interventions can effectively decouple logical schemata from data, offering a path toward improved controllability, faithfulness, and generalizability.