Cover Image

Not all tokens are created equal: Perplexity Attention Weighted Networks for AI generated text detection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Miralles-González, Pablo, Huertas-Tato, Javier, Martín, Alejandro, Camacho, David
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

On the locality bias and results in the Long Range Arena
by: Miralles-González, Pablo, et al.
Published: (2025)

LLM one-shot style transfer for Authorship Attribution and Verification
by: Miralles-González, Pablo, et al.
Published: (2025)

Pushing the boundary on Natural Language Inference
by: Miralles-González, Pablo, et al.
Published: (2025)

xList-Hate: A Checklist-Based Framework for Interpretable and Generalizable Hate Speech Detection
by: Girón, Adrián, et al.
Published: (2026)

Camouflage is all you need: Evaluating and Enhancing Language Model Robustness Against Camouflage Adversarial Attacks
by: Huertas-García, Álvaro, et al.
Published: (2024)

DisTrack: a new Tool for Semi-automatic Misinformation Tracking in Online Social Networks
by: Villar-Rodríguez, Guillermo, et al.
Published: (2024)

PART: Pre-trained Authorship Representation Transformer
by: Huertas-Tato, Javier, et al.
Published: (2022)

Humans can learn to detect AI-generated texts, or at least learn when they can't
by: Milička, Jiří, et al.
Published: (2025)

Supervised Contrastive Learning for Few-Shot AI-Generated Image Detection and Attribution
by: Urueña, Jaime Álvarez, et al.
Published: (2025)

Are generative AI text annotations systematically biased?
by: Stolwijk, Sjoerd B., et al.
Published: (2025)

Kill two birds with one stone: generalized and robust AI-generated text detection via dynamic perturbations
by: Zhou, Yinghan, et al.
Published: (2025)

LuxVeri at GenAI Detection Task 1: Inverse Perplexity Weighted Ensemble for Robust Detection of AI-Generated Text across English and Multilingual Contexts
by: Mobin, Md Kamrujjaman, et al.
Published: (2025)

LuxVeri at GenAI Detection Task 3: Cross-Domain Detection of AI-Generated Text Using Inverse Perplexity-Weighted Ensemble of Fine-Tuned Transformer Models
by: Mobin, Md Kamrujjaman, et al.
Published: (2025)

Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents
by: Wang, Haoyu, et al.
Published: (2025)

Isolating authorship from content with semantic embeddings and contrastive learning
by: Huertas-Tato, Javier, et al.
Published: (2024)

Mapping Overlaps in Benchmarks through Perplexity in the Wild
by: Wu, Siyang, et al.
Published: (2025)

HowkGPT: Investigating the Detection of ChatGPT-generated University Student Homework through Context-Aware Perplexity Analysis
by: Vasilatos, Christoforos, et al.
Published: (2023)

CLAWS:Creativity detection for LLM-generated solutions using Attention Window of Sections
by: Kim, Keuntae, et al.
Published: (2025)

Benchmark of stylistic variation in LLM-generated texts
by: Milička, Jiří, et al.
Published: (2025)

Multilingual Large Language Models do not comprehend all natural languages to equal degrees
by: Moskvina, Natalia, et al.
Published: (2026)

Rethinking GSPO: The Perplexity-Entropy Equivalence
by: Liu, Chi
Published: (2025)

On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation
by: Hsu, Chan-Jan, et al.
Published: (2026)

Can professional translators identify machine-generated text?
by: Farrell, Michael
Published: (2026)

AnomaLLMy -- Detecting anomalous tokens in black-box LLMs through low-confidence single-token predictions
by: Witold, Waligóra
Published: (2024)

Why AI-Generated Text Detection Fails: Evidence from Explainable AI Beyond Benchmark Accuracy
by: Pudasaini, Shushanta, et al.
Published: (2026)

People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text
by: Russell, Jenna, et al.
Published: (2025)

Unused information in token probability distribution of generative LLM: improving LLM reading comprehension through calculation of expected values
by: Zawistowski, Krystian
Published: (2024)

PLPP: Prompt Learning with Perplexity Is Self-Distillation for Vision-Language Models
by: Liu, Biao, et al.
Published: (2024)

Model Organisms Are Leaky: Perplexity Differencing Often Reveals Finetuning Objectives
by: Baker, Mohammed Abu, et al.
Published: (2026)

When Perplexity Lies: Generation-Focused Distillation of Hybrid Sequence Models
by: Kostelec, Juan Gabriel, et al.
Published: (2026)

Can postgraduate translation students identify machine-generated text?
by: Farrell, Michael
Published: (2025)

Differentially-private text generation degrades output language quality
by: Çano, Erion, et al.
Published: (2025)

Beyond Perplexity: A Lightweight Benchmark for Knowledge Retention in Supervised Fine-Tuning
by: Shabgahi, Soheil Zibakhsh, et al.
Published: (2026)

ReadCtrl: Personalizing text generation with readability-controlled instruction learning
by: Tran, Hieu, et al.
Published: (2024)

Prediction hubs are context-informed frequent tokens in LLMs
by: Nielsen, Beatrix M. G., et al.
Published: (2025)

Jacobian Scopes: token-level causal attributions in LLMs
by: Liu, Toni J. B., et al.
Published: (2026)

Looking beyond the next token
by: Thankaraj, Abitha, et al.
Published: (2025)

The pitfalls of next-token prediction
by: Bachmann, Gregor, et al.
Published: (2024)

Momentum Point-Perplexity Mechanics in Large Language Models
by: Tomaz, Lorenzo, et al.
Published: (2025)

Perplexity Cannot Always Tell Right from Wrong
by: Veličković, Petar, et al.
Published: (2026)