# Catching rationalization in the act: detecting motivated reasoning before and after CoT via activation probing

arXiv: https://arxiv.org/abs/2603.17199 · HTML: https://mlsanity.com/paper/2603.17199/

## Key facts

- Cited by 6 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 26 of its 49 references that are in the map.
- First posted on arXiv 17 Mar 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, 26 of 26)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation](https://mlsanity.com/paper/2503.11926/) (2025)
- [LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations](https://mlsanity.com/paper/2410.02707/) (2024)
- [Open Problems in Mechanistic Interpretability](https://mlsanity.com/paper/2501.16496/) (2025)
- [Chain-of-Thought Reasoning In The Wild Is Not Always Faithful](https://mlsanity.com/paper/2503.08679/) (2025)
- [Thought Anchors: Which LLM Reasoning Steps Matter?](https://mlsanity.com/paper/2506.19143/) (2025)
- [Are DeepSeek R1 And Other Reasoning Models More Faithful?](https://mlsanity.com/paper/2501.08156/) (2025)
- [Detecting Strategic Deception Using Linear Probes](https://mlsanity.com/paper/2502.03407/) (2025)
- [Eliciting Latent Knowledge from Quirky Language Models](https://mlsanity.com/paper/2312.01037/) (2023)
- [Do language models plan ahead for future tokens?](https://mlsanity.com/paper/2404.00859/) (2024)
- [On the Hardness of Faithful Chain-of-Thought Reasoning in Large Language Models](https://mlsanity.com/paper/2406.10625/) (2024)
- [No Answer Needed: Predicting LLM Answer Accuracy from Question-Only Linear Probes](https://mlsanity.com/paper/2509.10625/) (2025)
- [Let Me Think! A Long Chain-of-Thought Can Be Worth Exponentially Many Short Ones](https://mlsanity.com/paper/2505.21825/) (2025)
- [Persona-Assigned Large Language Models Exhibit Human-Like Motivated Reasoning](https://mlsanity.com/paper/2506.20020/) (2025)
- [MONICA: Real-Time Monitoring and Calibration of Chain-of-Thought Sycophancy in Large Reasoning Models](https://mlsanity.com/paper/2511.06419/) (2025)
- [LLMs Faithfully and Iteratively Compute Answers During CoT: A Systematic Analysis With Multi-step Arithmetics](https://mlsanity.com/paper/2412.01113/) (2024)
- [Internal Chain-of-Thought: Empirical Evidence for Layer-wise Subtask Scheduling in LLMs](https://mlsanity.com/paper/2505.14530/) (2025)
- [Efficient and accurate steering of Large Language Models through attention-guided feature learning](https://mlsanity.com/paper/2602.00333/) (2026)
- [Sycophantic Anchors: Localizing and Quantifying User Agreement in Reasoning Models](https://mlsanity.com/paper/2601.21183/) (2026)
- [The Ends Justify the Thoughts: RL-Induced Motivated Reasoning in LLM CoTs](https://mlsanity.com/paper/2510.17057/) (2025)

## Built on by (most cited first, 6 of 6)

- [How Much Does a Reasoning Summary Reveal? An Observability Ladder for Large Language Models](https://mlsanity.com/paper/2608.02089/) (2026)
- [Hyperparameter Transfer in Graph Neural Networks](https://mlsanity.com/paper/2607.05017/) (2026)
- [Two Regimes of Chain-of-Thought Unfaithfulness: Metric-Based Detection Fails Where Models Are Wrong](https://mlsanity.com/paper/2607.23458/) (2026)
- [Forecasting Future Behavior as a Learning Task](https://mlsanity.com/paper/2606.11445/) (2026)
- [Committed Before Reasoning: Behavioral Reproduction and Preliminary Activation-Level Evidence of Answer Pre-Commitment in an Open-Weight LLM](https://mlsanity.com/paper/2607.16451/) (2026)
- [Does Out-of-Sight Equal Out-of-Mind in CoT Monitorability?](https://mlsanity.com/paper/2608.04928/) (2026)

## Abstract (arXiv)

Large language models (LLMs) can produce chains of thought (CoT) that do not accurately reflect the actual factors driving their answers. In multiple-choice settings with an injected hint favoring a particular option, models may shift their final answer toward the hinted option and produce a CoT that rationalizes the response without acknowledging the hint - an instance of motivated reasoning. We study this phenomenon across multiple LLM families and datasets demonstrating that motivated reasoning can be identified by probing internal activations even in cases when it cannot be easily determined from CoT. Using supervised probes trained on the model's residual stream, we show that (i) pre-generation probes, applied before any CoT tokens are generated, predict motivated reasoning as well as a LLM-based CoT monitor that accesses the full CoT trace, and (ii) post-generation probes, applied after CoT generation, outperform the same monitor. Together, these results show that motivated reasoning is detected more reliably from internal representations than from CoT monitoring. Moreover, pre-generation probing can flag motivated behavior early, potentially avoiding unnecessary generation.