Skip to content
conftrace_
2026 EMNLP EMNLP 2026

Detecting Post-generation Edits to Watermarked LLM Outputs via Error-Correcting Codes

AbstractWatermarking has become a key mechanism for distinguishing AI-generated from human-written texts. In practical settings, however, content produced by large language models (LLMs) is often subject to critical post-generation edits, posing challenges for detecting and localizing such modifications. In this work, we propose incorporating error-correcting codes, specifically Varshamov-Tenengolts (VT) codes, by embedding VT code strings into watermarked LLM outputs, thus enabling post-generation edit detection of token insertions and deletions. We accompany such a watermarking procedure with a watermark detector and a post-edit detector. We evaluate our method on open-source LLM using synthetic edits and demonstrate excellent empirical performance of post-generation edit detection.

More from EMNLP 2026

All EMNLP 2026 papers →