paper-with-me

Papers

Russian Texts Detoxification with Levenshtein Editing

2022-04-28 · Ilya Gusev

Text detoxification is a style transfer task of creating neutral versions of toxic texts. In this paper, we use the concept of text editing to build a two-step tagging-based detoxification model using a parallel corpus of Russian texts. With this model, we achieved the best style transfer accuracy among all models in the RUSSE Detox shared task, surpassing larger sequence-to-sequence models.

📄 PDF Abstract BibTeX arXiv:2204.13638

Code (1)

ilyagusev/rudetox 공식 구현 pytorch

Tasks

Style Transfer

Similar Papers 제목 키워드 기반

Methods for Detoxification of Texts for the Russian Language

2021-05-19 · Daryna Dementieva, Daniil Moskovskiy, Varvara Logacheva, David Dale 외

We introduce the first study of automatic detoxification of Russian texts to combat offensive language. Such a kind of textual style transfer can be used, for instance, for processing toxic content in social media. While…

Style Transfer

Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing

2025-09-24 · Yisong Xiao, Aishan Liu, Siyuan Liang, Zonghao Ying 외 arxiv

Large Language Models (LLMs) have demonstrated impressive performance across various tasks, yet they remain vulnerable to generating toxic content, necessitating detoxification strategies to ensure safe and responsible d…

The Tatoxa System for Text Detoxification in Low-Resource Languages: The Case of Tatar

2026-06-24 · Ilseyar Alimova, Bogdan Monogov, Artyom Mazur, Daniil Antonov 외 arxiv

Text detoxification, the automated detection and mitigation of abusive and harmful content, is essential for ensuring the safety of online communities and protecting users. However, low resource languages such as Tatar h…

Improving English-Russian sentence alignment through POS tagging and Damerau-Levenshtein distance

2013-08-01 · WS 2013 8 · Andrey Kutuzov
Machine TranslationPart-Of-Speech TaggingPOSPOS Tagging+2

On the Robustness of Knowledge Editing for Detoxification

2026-02-11 · Ming Dong, Shiyi Tang, Ziyan Peng, Guanyi Chen 외 arxiv

Knowledge-Editing-based (KE-based) detoxification has emerged as a promising approach for mitigating harmful behaviours in Large Language Models. Existing evaluations, however, largely rely on automatic toxicity classifi…

knowledge editing