Hugging Face Daily Papers · · 4 min read

Show, Don't TELL: Explainable AI-Generated Text Detection

Mirrored from Hugging Face Daily Papers for archival readability. Support the source by reading on the original site.

Show, Don't TELL: Explainable AI-Generated Text Detection. We think this is the way forward to build trust in AI Text Detectors. Happy to discuss and get feedback!</p>\n","updatedAt":"2026-06-02T23:49:26.916Z","author":{"_id":"68fa7c73f382c0374680ad98","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/68fa7c73f382c0374680ad98/tPafIo_THzTDrZ98Nc77a.jpeg","fullname":"Suraj Ranganath","name":"suraj-ranganath","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":1,"identifiedLanguage":{"language":"en","probability":0.9463134407997131},"editors":["suraj-ranganath"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/68fa7c73f382c0374680ad98/tPafIo_THzTDrZ98Nc77a.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.27921","authors":[{"_id":"6a1f686ae292c1c78ecb1262","name":"Aldan Creo","hidden":false},{"_id":"6a1f686ae292c1c78ecb1263","name":"Suraj Ranganath","hidden":false}],"publishedAt":"2026-05-27T00:00:00.000Z","submittedOnDailyAt":"2026-06-02T00:00:00.000Z","title":"Show, Don't TELL: Explainable AI-Generated Text Detection","submittedOnDailyBy":{"_id":"68fa7c73f382c0374680ad98","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/68fa7c73f382c0374680ad98/tPafIo_THzTDrZ98Nc77a.jpeg","isPro":false,"fullname":"Suraj Ranganath","user":"suraj-ranganath","type":"user","name":"suraj-ranganath"},"summary":"Research on AI-generated text detection has presented a number of approaches to discern human from AI prose, some of which achieving high in-distribution performance. However, real-world applicability has stalled because their outputs are misaligned with the needs of users, such as professors, who are presented with a numeric score that has no attached explanation. We tackle this issue with a novel architecture, TELL, that bakes explainability from the ground-up. While our system still offers a numerical score like other detectors for comparability, TELL takes a fundamentally different approach where we aim to show the user the \"tells\" by which the model believes a text is AI or human-written, to empower the user to decide who wrote a text using their own judgment and understanding of the context of the writing and its alleged author. We train TELL on a custom SFT dataset of domain-specific authorship annotations, and further refine the system using GRPO with curriculum learning to improve performance. We achieve competitive performance with state-of-the-art detectors (AUROC 0.927) while natively providing annotations that explain the basis for the detector's decision. We further evaluate the quality of our explanations using a dataset of human annotations and report a high (mean 72.3%) win-rate on annotation concreteness, falsifiability, coherence, plausibility and grounding, allowing users to critically think and decide for themselves. Our work thus reframes the problem of AI-generated text detection in a human-centric perspective and paves the way for a new family of detectors that focus on native explainability.","upvotes":0,"discussionId":"6a1f686ae292c1c78ecb1264","projectPage":"https://ai-tells.tech/","githubRepo":"https://github.com/ACMCMC/TELL","githubRepoAddedBy":"user","ai_summary":"A novel AI-generated text detection system named TELL is introduced that combines high-performance detection with native explainability by showing specific textual indicators that help users make informed judgments about authorship.","ai_keywords":["AI-generated text detection","explainability","TELL architecture","SFT dataset","GRPO","curriculum learning","AUROC","human-centric perspective"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct","githubStars":0},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[],"acceptLanguages":["en"]}">
Papers
arxiv:2605.27921

Show, Don't TELL: Explainable AI-Generated Text Detection

Published on May 27
· Submitted by
Suraj Ranganath
on Jun 2
Authors:
,

Abstract

A novel AI-generated text detection system named TELL is introduced that combines high-performance detection with native explainability by showing specific textual indicators that help users make informed judgments about authorship.

Research on AI-generated text detection has presented a number of approaches to discern human from AI prose, some of which achieving high in-distribution performance. However, real-world applicability has stalled because their outputs are misaligned with the needs of users, such as professors, who are presented with a numeric score that has no attached explanation. We tackle this issue with a novel architecture, TELL, that bakes explainability from the ground-up. While our system still offers a numerical score like other detectors for comparability, TELL takes a fundamentally different approach where we aim to show the user the "tells" by which the model believes a text is AI or human-written, to empower the user to decide who wrote a text using their own judgment and understanding of the context of the writing and its alleged author. We train TELL on a custom SFT dataset of domain-specific authorship annotations, and further refine the system using GRPO with curriculum learning to improve performance. We achieve competitive performance with state-of-the-art detectors (AUROC 0.927) while natively providing annotations that explain the basis for the detector's decision. We further evaluate the quality of our explanations using a dataset of human annotations and report a high (mean 72.3%) win-rate on annotation concreteness, falsifiability, coherence, plausibility and grounding, allowing users to critically think and decide for themselves. Our work thus reframes the problem of AI-generated text detection in a human-centric perspective and paves the way for a new family of detectors that focus on native explainability.

Community

Show, Don't TELL: Explainable AI-Generated Text Detection. We think this is the way forward to build trust in AI Text Detectors. Happy to discuss and get feedback!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images

· Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2605.27921 in a model README.md to link it from this page.

Datasets citing this paper 2

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2605.27921 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

Discussion (0)

Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.

Sign in →

No comments yet. Sign in and be the first to say something.

More from Hugging Face Daily Papers