# Cognition-of-Thought Elicits Social-Aligned Reasoning in Large Language Models

arXiv: https://arxiv.org/abs/2509.23441 · HTML: https://mlsanity.com/paper/2509.23441/

## Key facts

- Cited by 3 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 9 of its 56 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## 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, 9 of 9)

- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [Improve Mathematical Reasoning in Language Models by Automated Process Supervision](https://mlsanity.com/paper/2406.06592/) (2024)
- [TrustLLM: Trustworthiness in Large Language Models](https://mlsanity.com/paper/2401.05561/) (2024)
- [KTO: Model Alignment as Prospect Theoretic Optimization](https://mlsanity.com/paper/2402.01306/) (2024)
- [LLM Critics Help Catch LLM Bugs](https://mlsanity.com/paper/2407.00215/) (2024)
- [Human Decision-making is Susceptible to AI-driven Manipulation](https://mlsanity.com/paper/2502.07663/) (2025)
- [Less is More: Improving LLM Alignment via Preference Data Selection](https://mlsanity.com/paper/2502.14560/) (2025)
- [Towards Exception Safety Code Generation with Intermediate Representation Agents Framework](https://mlsanity.com/paper/2410.06949/) (2024)

## Built on by (most cited first, 3 of 3)

- [LH-Deception: Simulating and Understanding LLM Deceptive Behaviors in Long-Horizon Interactions](https://mlsanity.com/paper/2510.03999/) (2025)
- [Generalization or Memorization: Dynamic Decoding for Mode Steering](https://mlsanity.com/paper/2510.22099/) (2025)
- [Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding](https://mlsanity.com/paper/2606.21906/) (2026)

## Abstract (arXiv)

Large language models (LLMs) excel at complex reasoning but can still exhibit harmful behaviors. Current alignment strategies typically embed safety into model weights, making these controls implicit, static, and difficult to modify. This paper introduces Cognition-of-Thought (CooT), a novel decoding-time framework that equips LLMs with an explicit cognitive self-monitoring loop. CooT couples a standard text Generator with a cognitive Perceiver that continuously monitors the unfolding sequence. The Perceiver uses a structured, precedence-based hierarchy of principles (e.g., safety over obedience) to detect potential misalignments as they arise. When violations are flagged, CooT intervenes by rolling back the generation to the point of error and regenerating under injected guidance that combines universal social priors with context-specific warnings. CooT thus transforms alignment from a fixed property into an explicit, dynamic, and auditable process active during inference, allowing for flexible policy updates without retraining the model. Extensive experiments across multiple benchmarks and model families confirm that CooT consistently improves safety and social reasoning performance.