A 1.5B LLM fine-tuned on a curated rationale dataset (READ) detects AI text with explanations and reportedly outperforms much larger prompted LLMs.
Token-specific watermarking with enhanced detectability and semantic coherence for large language models.arXiv preprint arXiv:2402.18059
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
LLM watermarking adoption is limited by misaligned stakeholder incentives; incentive-aligned approaches such as in-context watermarking can enable practical use in targeted domains like education and peer review.
citing papers explorer
-
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.