# Tracing Thought: Using Chain-of-Thought Reasoning to Identify the LLM Behind AI-Generated Text

arXiv: https://arxiv.org/abs/2504.16913 · HTML: https://mlsanity.com/paper/2504.16913/

## 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 16 of its 21 references that are in the map.
- First posted on arXiv 23 Apr 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, 16 of 16)

- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [Defending Against Neural Fake News](https://mlsanity.com/paper/1905.12616/) (2019)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense](https://mlsanity.com/paper/2303.13408/) (2023)
- [Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2401.12070/) (2024)
- [Automatic Detection of Generated Text is Easiest when Humans are Fooled](https://mlsanity.com/paper/1911.00650/) (2019)
- [DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2306.05540/) (2023)
- [TURINGBENCH: A Benchmark Environment for Turing Test in the Age of Neural Text Generation](https://mlsanity.com/paper/2109.13296/) (2021)
- [ArguGPT: evaluating, understanding and identifying argumentative essays generated by GPT models](https://mlsanity.com/paper/2304.07666/) (2023)
- [Neural Deepfake Detection with Factual Structure of Text](https://mlsanity.com/paper/2010.07475/) (2020)
- [CoCo: Coherence-Enhanced Machine-Generated Text Detection Under Data Limitation With Contrastive Learning](https://mlsanity.com/paper/2212.10341/) (2022)
- [Towards a Robust Detection of Language Model Generated Text: Is ChatGPT that Easy to Detect?](https://mlsanity.com/paper/2306.05871/) (2023)
- [Classification of Human- and AI-Generated Texts: Investigating Features for ChatGPT](https://mlsanity.com/paper/2308.05341/) (2023)
- [Implementing BERT and fine-tuned RobertA to detect AI generated news by ChatGPT](https://mlsanity.com/paper/2306.07401/) (2023)
- [Neural Authorship Attribution: Stylometric Analysis on Large Language Models](https://mlsanity.com/paper/2308.07305/) (2023)

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

- [From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Models](https://mlsanity.com/paper/2511.12861/) (2025)
- [Findings of the Counter Turing Test: AI-Generated Text Detection](https://mlsanity.com/paper/2605.20761/) (2026)
- [Agentic and Generative AI for Open-Source Intelligence and Cyber Investigations: Taxonomy, Evaluation, Challenges, and Future Directions](https://mlsanity.com/paper/2607.03233/) (2026)

## Abstract (arXiv)

In recent years, the detection of AI-generated text has become a critical area of research due to concerns about academic integrity, misinformation, and ethical AI deployment. This paper presents COT Fine-tuned, a novel framework for detecting AI-generated text and identifying the specific language model. responsible for generating the text. We propose a dual-task approach, where Task A involves classifying text as AI-generated or human-written, and Task B identifies the specific LLM behind the text. The key innovation of our method lies in the use of Chain-of-Thought reasoning, which enables the model to generate explanations for its predictions, enhancing transparency and interpretability. Our experiments demonstrate that COT Fine-tuned achieves high accuracy in both tasks, with strong performance in LLM identification and human-AI classification. We also show that the CoT reasoning process contributes significantly to the models effectiveness and interpretability.