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

• URL: http://arxiv.org/abs/2504.16913v1
• Date: Wed, 23 Apr 2025 17:39:49 GMT
• Title: Tracing Thought: Using Chain-of-Thought Reasoning to Identify the LLM Behind AI-Generated Text
• Authors: Shifali Agrahari, Sanasam Ranbir Singh,
• Abstract summary: COT Fine-tuned is a novel framework for detecting AI-generated text.<n>Key innovation of our method lies in the use of Chain-of-Thought reasoning.<n>Experiments demonstrate that COT Fine-tuned high accuracy in both tasks.
• Score: 1.7034813545878589
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Learning Task Representations from In-Context Learning [73.72066284711462]
  Large language models (LLMs) have demonstrated remarkable proficiency in in-context learning. We introduce an automated formulation for encoding task information in ICL prompts as a function of attention heads. We show that our method's effectiveness stems from aligning the distribution of the last hidden state with that of an optimally performing in-context-learned model.
  arXiv  Detail & Related papers  (2025-02-08T00:16:44Z)
• Survey on Vision-Language-Action Models [0.2636873872510828]
  This work does not represent original research, but highlights how AI can help automate literature reviews. Future research will focus on developing a structured framework for AI-assisted literature reviews.
  arXiv  Detail & Related papers  (2025-02-07T11:56:46Z)
• DeTeCtive: Detecting AI-generated Text via Multi-Level Contrastive Learning [24.99797253885887]
  We argue that the key to accomplishing this task lies in distinguishing writing styles of different authors. We propose DeTeCtive, a multi-task auxiliary, multi-level contrastive learning framework. Our method is compatible with a range of text encoders.
  arXiv  Detail & Related papers  (2024-10-28T12:34:49Z)
• Is Contrasting All You Need? Contrastive Learning for the Detection and Attribution of AI-generated Text [4.902089836908786]
  WhosAI is a triplet-network contrastive learning framework designed to predict whether a given input text has been generated by humans or AI.<n>We show that our proposed framework achieves outstanding results in both the Turing Test and Authorship tasks.
  arXiv  Detail & Related papers  (2024-07-12T15:44:56Z)
• Converging Paradigms: The Synergy of Symbolic and Connectionist AI in LLM-Empowered Autonomous Agents [55.63497537202751]
  Article explores the convergence of connectionist and symbolic artificial intelligence (AI) Traditionally, connectionist AI focuses on neural networks, while symbolic AI emphasizes symbolic representation and logic. Recent advancements in large language models (LLMs) highlight the potential of connectionist architectures in handling human language as a form of symbols.
  arXiv  Detail & Related papers  (2024-07-11T14:00:53Z)
• Detecting AI-Generated Text: Factors Influencing Detectability with Current Methods [13.14749943120523]
  Knowing whether a text was produced by human or artificial intelligence (AI) is important to determining its trustworthiness.<n>State-of-the art approaches to AIGT detection include watermarking, statistical and stylistic analysis, and machine learning classification.<n>We aim to provide insight into the salient factors that combine to determine how "detectable" AIGT text is under different scenarios.
  arXiv  Detail & Related papers  (2024-06-21T18:31:49Z)
• Spotting AI's Touch: Identifying LLM-Paraphrased Spans in Text [61.22649031769564]
  We propose a novel framework, paraphrased text span detection (PTD) PTD aims to identify paraphrased text spans within a text. We construct a dedicated dataset, PASTED, for paraphrased text span detection.
  arXiv  Detail & Related papers  (2024-05-21T11:22:27Z)
• A Survey of AI-generated Text Forensic Systems: Detection, Attribution, and Characterization [13.44566185792894]
  AI-generated text forensics is an emerging field addressing the challenges of LLM misuses. We introduce a detailed taxonomy, focusing on three primary pillars: detection, attribution, and characterization. We explore available resources for AI-generated text forensics research and discuss the evolving challenges and future directions of forensic systems in an AI era.
  arXiv  Detail & Related papers  (2024-03-02T09:39:13Z)
• Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents [80.5213198675411]
  Large language models (LLMs) have dramatically enhanced the field of language intelligence. LLMs leverage the intriguing chain-of-thought (CoT) reasoning techniques, obliging them to formulate intermediate steps en route to deriving an answer. Recent research endeavors have extended CoT reasoning methodologies to nurture the development of autonomous language agents.
  arXiv  Detail & Related papers  (2023-11-20T14:30:55Z)
• Towards Possibilities & Impossibilities of AI-generated Text Detection: A Survey [97.33926242130732]
  Large Language Models (LLMs) have revolutionized the domain of natural language processing (NLP) with remarkable capabilities of generating human-like text responses. Despite these advancements, several works in the existing literature have raised serious concerns about the potential misuse of LLMs. To address these concerns, a consensus among the research community is to develop algorithmic solutions to detect AI-generated text.
  arXiv  Detail & Related papers  (2023-10-23T18:11:32Z)
• Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models [56.34029644009297]
  Large language models (LLMs) have demonstrated the ability to overcome various limitations of formal Knowledge Representation (KR) systems. LLMs excel most in abductive reasoning, followed by deductive reasoning, while they are least effective at inductive reasoning. We study single-task training, multi-task training, and "chain-of-thought" knowledge distillation fine-tuning technique to assess the performance of model.
  arXiv  Detail & Related papers  (2023-10-02T01:00:50Z)
• MAGE: Machine-generated Text Detection in the Wild [82.70561073277801]
  Large language models (LLMs) have achieved human-level text generation, emphasizing the need for effective AI-generated text detection. We build a comprehensive testbed by gathering texts from diverse human writings and texts generated by different LLMs. Despite challenges, the top-performing detector can identify 86.54% out-of-domain texts generated by a new LLM, indicating the feasibility for application scenarios.
  arXiv  Detail & Related papers  (2023-05-22T17:13:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.