Show, Don't TELL: Explainable AI-Generated Text Detection
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!
Models citing this paper 0
No model linking this paper
Datasets citing this paper 2
suraj-ranganath/unified_tell_dataset
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper