# Token Prediction as Implicit Classification to Identify LLM-Generated Text arXiv: https://arxiv.org/abs/2311.08723 ยท HTML: https://mlsanity.com/paper/2311.08723/ ## Key facts - Cited by 27 papers in the map (data through 14 Oct 2026). - Builds on 13 of its 20 references that are in the map. - First posted on arXiv 15 Nov 2023. ## Builds on (most cited first, 13 of 13) - [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020) - [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019) - [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022) - [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017) - [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017) - [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) - [How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection](https://mlsanity.com/paper/2301.07597/) (2023) - [GPT detectors are biased against non-native English writers](https://mlsanity.com/paper/2304.02819/) (2023) - [Automatic Detection of Machine Generated Text: A Critical Survey](https://mlsanity.com/paper/2011.01314/) (2020) - [Real or Fake? Learning to Discriminate Machine from Human Generated Text](https://mlsanity.com/paper/1906.03351/) (2019) ## Built on by (most cited first, 27 of 27) - [DeTeCtive: Detecting AI-generated Text via Multi-Level Contrastive Learning](https://mlsanity.com/paper/2410.20964/) (2024) - [Beemo: Benchmark of Expert-edited Machine-generated Outputs](https://mlsanity.com/paper/2411.04032/) (2024) - [Detecting AI-Generated Text: Factors Influencing Detectability with Current Methods](https://mlsanity.com/paper/2406.15583/) (2024) - [Ten Words Only Still Help: Improving Black-Box AI-Generated Text Detection via Proxy-Guided Efficient Re-Sampling](https://mlsanity.com/paper/2402.09199/) (2024) - [A Survey of Large Language Models on Generative Graph Analytics: Query, Learning, and Applications](https://mlsanity.com/paper/2404.14809/) (2024) - [Improving Your Model Ranking on Chatbot Arena by Vote Rigging](https://mlsanity.com/paper/2501.17858/) (2025) - [Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms](https://mlsanity.com/paper/2412.17622/) (2024) - [DETree: DEtecting Human-AI Collaborative Texts via Tree-Structured Hierarchical Representation Learning](https://mlsanity.com/paper/2510.17489/) (2025) - [A Practical Examination of AI-Generated Text Detectors for Large Language Models](https://mlsanity.com/paper/2412.05139/) (2024) - [FAID: Fine-Grained AI-Generated Text Detection Using Multi-Task Auxiliary and Multi-Level Contrastive Learning](https://mlsanity.com/paper/2505.14271/) (2025) - [Diversity Boosts AI-Generated Text Detection](https://mlsanity.com/paper/2509.18880/) (2025) - [Synthetic Lyrics Detection Across Languages and Genres](https://mlsanity.com/paper/2406.15231/) (2024) - [PhantomHunter: Detecting Unseen Privately-Tuned LLM-Generated Text via Family-Aware Learning](https://mlsanity.com/paper/2506.15683/) (2025) - [Not All Tokens Are Worth Caching: Learning Semantic-Aware Eviction for LLM Prefix Caches](https://mlsanity.com/paper/2605.18825/) (2026) - [Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring](https://mlsanity.com/paper/2502.05242/) (2025) - [Predicting Through Generation: Why Generation Is Better for Prediction](https://mlsanity.com/paper/2502.17817/) (2025) - [AI-Generated Song Detection via Lyrics Transcripts](https://mlsanity.com/paper/2506.18488/) (2025) - [Is the Digital Forensics and Incident Response Pipeline Ready for Text-Based Threats in LLM Era?](https://mlsanity.com/paper/2407.17870/) (2024) - [Two Birds with One Stone: Multi-Task Detection and Attribution of LLM-Generated Text](https://mlsanity.com/paper/2508.14190/) (2025) - [MAGA-Bench: Machine-Augment-Generated Text via Alignment Detection Benchmark](https://mlsanity.com/paper/2601.04633/) (2026) - [DetectZoo: A Unified Toolkit for AI-Generated Content Detection Across Text, Audio, and Image Modalities](https://mlsanity.com/paper/2606.04205/) (2026) - [TextMachina: Seamless Generation of Machine-Generated Text Datasets](https://mlsanity.com/paper/2401.03946/) (2024) - [Stylometry recognizes human and LLM-generated texts in short samples](https://mlsanity.com/paper/2507.00838/) (2025) - [What Are LLMs Doing to Scientific Communication? Measuring Changes in Writing Practices and Reading Experience](https://mlsanity.com/paper/2605.19936/) (2026) - [Show, Don't TELL: Explainable AI-Generated Text Detection](https://mlsanity.com/paper/2605.27921/) (2026) - [T5-CSBoost: Adversarial Perturbation Resistant LLM Fingerprinting](https://mlsanity.com/paper/2607.14113/) (2026) - [Who's Behind the Text? Robust Model Authorship Attribution](https://mlsanity.com/paper/2610.19583/) (2026) ## Abstract (arXiv) This paper introduces a novel approach for identifying the possible large language models (LLMs) involved in text generation. Instead of adding an additional classification layer to a base LM, we reframe the classification task as a next-token prediction task and directly fine-tune the base LM to perform it. We utilize the Text-to-Text Transfer Transformer (T5) model as the backbone for our experiments. We compared our approach to the more direct approach of utilizing hidden states for classification. Evaluation shows the exceptional performance of our method in the text classification task, highlighting its simplicity and efficiency. Furthermore, interpretability studies on the features extracted by our model reveal its ability to differentiate distinctive writing styles among various LLMs even in the absence of an explicit classifier. We also collected a dataset named OpenLLMText, containing approximately 340k text samples from human and LLMs, including GPT3.5, PaLM, LLaMA, and GPT2.