# Mechanistic Evidence for Faithfulness Decay in Chain-of-Thought Reasoning

arXiv: https://arxiv.org/abs/2602.11201 · HTML: https://mlsanity.com/paper/2602.11201/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 21 of its 39 references that are in the map.
- First posted on arXiv 4 Feb 2026.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 21 of 21)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [Causal Abstractions of Neural Networks](https://mlsanity.com/paper/2106.02997/) (2021)
- [ProcessBench: Identifying Process Errors in Mathematical Reasoning](https://mlsanity.com/paper/2412.06559/) (2024)
- [Faithful Chain-of-Thought Reasoning](https://mlsanity.com/paper/2301.13379/) (2023)
- [The Geometry of Categorical and Hierarchical Concepts in Large Language Models](https://mlsanity.com/paper/2406.01506/) (2024)
- [Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning](https://mlsanity.com/paper/2402.13950/) (2024)
- [Wait, Wait, Wait... Why Do Reasoning Models Loop?](https://mlsanity.com/paper/2512.12895/) (2025)
- [Normalized AOPC: Fixing Misleading Faithfulness Metrics for Feature Attribution Explainability](https://mlsanity.com/paper/2408.08137/) (2024)
- [R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?](https://mlsanity.com/paper/2510.08189/) (2025)

## Built on by (most cited first, 9 of 9)

- [Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models?](https://mlsanity.com/paper/2603.22582/) (2026)
- [Measuring Faithfulness Depends on How You Measure: Classifier Sensitivity in LLM Chain-of-Thought Evaluation](https://mlsanity.com/paper/2603.20172/) (2026)
- [Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models](https://mlsanity.com/paper/2603.26410/) (2026)
- [Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning](https://mlsanity.com/paper/2605.24286/) (2026)
- [When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel](https://mlsanity.com/paper/2605.11746/) (2026)
- [Measuring and curing reasoning rigidity: from decorative chain-of-thought to genuine faithfulness](https://mlsanity.com/paper/2603.22816/) (2026)
- [Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs](https://mlsanity.com/paper/2606.27378/) (2026)
- [Mechanistic Interpretability of Chain-of-Thought Reasoning via Sequential Activation Patching](https://mlsanity.com/paper/2608.22332/) (2026)
- [LLM Reasoning Is Latent, Not the Chain of Thought](https://mlsanity.com/paper/2604.15726/) (2026)

## Abstract (arXiv)

Chain-of-Thought (CoT) explanations are widely used to interpret how language models solve complex problems, yet it remains unclear whether these step-by-step explanations reflect how the model actually reaches its answer, or merely post-hoc justifications. We propose Normalized Logit Difference Decay (NLDD), a metric that measures whether individual reasoning steps are faithful to the model's decision-making process. Our approach corrupts individual reasoning steps from the explanation and measures how much the model's confidence in its answer drops, to determine if a step is truly important. By standardizing these measurements, NLDD enables rigorous cross-model comparison across different architectures. Testing three model families across syntactic, logical, and arithmetic tasks, we discover a consistent Reasoning Horizon (k*) at 70--85% of chain length, beyond which reasoning tokens have little or negative effect on the final answer. We also find that models can encode correct internal representations while completely failing the task. These results show that accuracy alone does not reveal whether a model actually reasons through its chain. NLDD offers a way to measure when CoT matters.