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

• URL: http://arxiv.org/abs/2605.27921v1
• Date: Wed, 27 May 2026 03:47:25 GMT
• Title: Show, Don't TELL: Explainable AI-Generated Text Detection
• Abstract summary: We develop a novel architecture, TELL, that bakes explainability from the ground-up.<n>We train TELL on a custom SFT dataset of domain-specific authorship annotations.<n>We report a high (mean 72.3%) win-rate on annotation concreteness, falsifiability, coherence, plausibility and grounding.
• Score: 0.42970700836450487
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Base Models Look Human To AI Detectors [68.7723287560362]
  We show that generated text from base models is often judged overwhelmingly human, whereas text generated by their instruction-tuned counterparts is not.<n>We propose Humanization by Iterative Paraphrasing (HIP), a detector-agnostic pipeline that minimally fine-tunes a base model into a paraphraser and applies it iteratively.<n>Our findings suggest that current detectors are tracking artifacts of instruction tuning and local context more than any in notion of machine-generated text.
  arXiv  Detail & Related papers  (2026-05-19T08:13:12Z)
• Why AI-Generated Text Detection Fails: Evidence from Explainable AI Beyond Benchmark Accuracy [0.9169660430821364]
  We propose a framework that integrates linguistic feature engineering, machine learning, and explainable AI techniques.<n>Using SHAP-based explanations, we show that the most influential features differ markedly between datasets.<n>We believe that this knowledge helps build AI detectors that are robust across different settings.
  arXiv  Detail & Related papers  (2026-03-24T12:46:15Z)
• Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection [71.59834293521074]
  We develop a framework to distinguish between human-authored and machine-generated text.<n>Our method achieves 98.3% AUROC and AUPR with only 8.9% FPR95 on DeepFake dataset.<n>Code, pretrained weights, and demo will be released.
  arXiv  Detail & Related papers  (2025-10-07T08:14:45Z)
• EditLens: Quantifying the Extent of AI Editing in Text [23.457378805409714]
  We show that AI-edited text is distinguishable from human-written and AI-generated text.<n>We train a regression model that predicts the amount of AI editing present within a text.<n>Not only do we show that AI-edited text can be detected, but also that the degree of change made by AI to human writing can be detected.
  arXiv  Detail & Related papers  (2025-10-03T16:27:48Z)
• CoCoNUTS: Concentrating on Content while Neglecting Uninformative Textual Styles for AI-Generated Peer Review Detection [60.52240468810558]
  We introduce CoCoNUTS, a content-oriented benchmark built upon a fine-grained dataset of AI-generated peer reviews.<n>We also develop CoCoDet, an AI review detector via a multi-task learning framework, to achieve more accurate and robust detection of AI involvement in review content.
  arXiv  Detail & Related papers  (2025-08-28T06:03:11Z)
• AuthorMist: Evading AI Text Detectors with Reinforcement Learning [4.806579822134391]
  AuthorMist is a novel reinforcement learning-based system to transform AI-generated text into human-like writing.<n>We show that AuthorMist effectively reduces the detectability of AI-generated text while preserving the original meaning.
  arXiv  Detail & Related papers  (2025-03-10T12:41:05Z)
• Who Writes What: Unveiling the Impact of Author Roles on AI-generated Text Detection [44.05134959039957]
  We investigate how sociolinguistic attributes-gender, CEFR proficiency, academic field, and language environment-impact state-of-the-art AI text detectors.<n>Our results reveal significant biases: CEFR proficiency and language environment consistently affected detector accuracy, while gender and academic field showed detector-dependent effects.<n>These findings highlight the crucial need for socially aware AI text detection to avoid unfairly penalizing specific demographic groups.
  arXiv  Detail & Related papers  (2025-02-18T07:49:31Z)
• ExaGPT: Example-Based Machine-Generated Text Detection for Human Interpretability [62.285407189502216]
  Detecting texts generated by Large Language Models (LLMs) could cause grave mistakes due to incorrect decisions.<n>We introduce ExaGPT, an interpretable detection approach grounded in the human decision-making process.<n>We show that ExaGPT massively outperforms prior powerful detectors by up to +40.9 points of accuracy at a false positive rate of 1%.
  arXiv  Detail & Related papers  (2025-02-17T01:15:07Z)
• Who Writes the Review, Human or AI? [0.36498648388765503]
  This study proposes a methodology to accurately distinguish AI-generated and human-written book reviews. Our approach utilizes transfer learning, enabling the model to identify generated text across different topics. The experimental results demonstrate that it is feasible to detect the original source of text, achieving an accuracy rate of 96.86%.
  arXiv  Detail & Related papers  (2024-05-30T17:38:44Z)
• On the Possibilities of AI-Generated Text Detection [76.55825911221434]
  We argue that as machine-generated text approximates human-like quality, the sample size needed for detection bounds increases. We test various state-of-the-art text generators, including GPT-2, GPT-3.5-Turbo, Llama, Llama-2-13B-Chat-HF, and Llama-2-70B-Chat-HF, against detectors, including oBERTa-Large/Base-Detector, GPTZero.
  arXiv  Detail & Related papers  (2023-04-10T17:47:39Z)
• Can AI-Generated Text be Reliably Detected? [50.95804851595018]
  Large Language Models (LLMs) perform impressively well in various applications.<n>The potential for misuse of these models in activities such as plagiarism, generating fake news, and spamming has raised concern about their responsible use.<n>We stress-test the robustness of these AI text detectors in the presence of an attacker.
  arXiv  Detail & Related papers  (2023-03-17T17:53:19Z)

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.