ExaGPT uses span-level similarity retrieval from human and LLM datastores to detect machine-generated text while supplying the matching spans as human-interpretable evidence, achieving up to 37-point accuracy gains over prior interpretable detectors at 1% FPR.
ChatGPT or human? Detect and explain
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
Steer-to-Detect learns a steering vector injected into LLM hidden states to boost class separability and applies hypothesis testing with finite-sample Type I/II error guarantees for generated-text detection.
A 1.5B LLM fine-tuned on a curated rationale dataset (READ) detects AI text with explanations and reportedly outperforms much larger prompted LLMs.
A tutorial synthesizing foundations, recent models such as PALO and Maya, and low-cost methods for tri-modal multilingual AI in resource-constrained settings.
citing papers explorer
-
ExaGPT: Example-Based Machine-Generated Text Detection for Human Interpretability
ExaGPT uses span-level similarity retrieval from human and LLM datastores to detect machine-generated text while supplying the matching spans as human-interpretable evidence, achieving up to 37-point accuracy gains over prior interpretable detectors at 1% FPR.
-
Steer-to-Detect: Probing Hidden Representations for Detection of LLM-Generated Texts
Steer-to-Detect learns a steering vector injected into LLM hidden states to boost class separability and applies hypothesis testing with finite-sample Type I/II error guarantees for generated-text detection.
-
READER: Reasoning-Enhanced AI-Generated Text Detection
A 1.5B LLM fine-tuned on a curated rationale dataset (READ) detects AI text with explanations and reportedly outperforms much larger prompted LLMs.
-
Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages
A tutorial synthesizing foundations, recent models such as PALO and Maya, and low-cost methods for tri-modal multilingual AI in resource-constrained settings.