Related papers: Russian Texts Detoxification with Levenshtein Edit…

Text detoxification aims to minimize the risk of language models producing toxic content. Existing detoxification methods of directly constraining the model output or further training the model on the non-toxic corpus fail to achieve a…

Harmful and offensive communication or content is detrimental to social bonding and the mental state of users on social media platforms. Text detoxification is a crucial task in natural language processing (NLP), where the goal is removing…

Transformer-based Language Models (LMs) have achieved impressive results on natural language understanding tasks, but they can also generate toxic text such as insults, threats, and profanity, limiting their real-world applications. To…

Prior works on detoxification are scattered in the sense that they do not cover all aspects of detoxification needed in a real-world scenario. Notably, prior works restrict the task of developing detoxification models to only a seen subset…

Edit-based approaches have recently shown promising results on multiple monolingual sequence transduction tasks. In contrast to conventional sequence-to-sequence (Seq2Seq) models, which learn to generate text from scratch as they are…

We propose a novel scheme to use the Levenshtein Transformer to perform the task of word-level quality estimation. A Levenshtein Transformer is a natural fit for this task: trained to perform decoding in an iterative manner, a Levenshtein…

We present UniDetox, a universally applicable method designed to mitigate toxicity across various large language models (LLMs). Previous detoxification methods are typically model-specific, addressing only individual models or model…

In this work, we introduce our solution for the Multilingual Text Detoxification Task in the PAN-2025 competition for the ylmmcl team: a robust multilingual text detoxification pipeline that integrates lexicon-guided tagging, a fine-tuned…

We present a novel approach for disentangling the content of a text image from all aspects of its appearance. The appearance representation we derive can then be applied to new content, for one-shot transfer of the source style to new…

Due to language models' propensity to generate toxic or hateful responses, several techniques were developed to align model generations with users' preferences. Despite the effectiveness of such methods in improving the safety of model…

Despite the remarkable achievements of language models (LMs) across a broad spectrum of tasks, their propensity for generating toxic outputs remains a prevalent concern. Current solutions involving finetuning or auxiliary models usually…

In this paper, we present a system for information extraction from scientific texts in the Russian language. The system performs several tasks in an end-to-end manner: term recognition, extraction of relations between terms, and term…

Recent breakthroughs in Large Language Models (LLMs) have revealed remarkable generative capabilities and emerging self-regulatory mechanisms, including self-correction and self-rewarding. However, current detoxification techniques rarely…

Existing approaches for Large language model (LLM) detoxification generally rely on training on large-scale non-toxic or human-annotated preference data, designing prompts to instruct the LLM to generate safe content, or modifying the model…

Language models (LMs) can reproduce (or amplify) toxic language seen during training, which poses a risk to their practical application. In this paper, we conduct extensive experiments to study this phenomenon. We analyze the impact of…

Text style transfer is the task of transferring the style of text having certain stylistic attributes, while preserving non-stylistic or content information. In this work we introduce the Generative Style Transformer (GST) - a new approach…

Text sanitization aims to rewrite parts of a document to prevent disclosure of personal information. The central challenge of text sanitization is to strike a balance between privacy protection (avoiding the leakage of personal information)…

Editing raster text is a promising but challenging task. We propose to apply text vectorization for the task of raster text editing in display media, such as posters, web pages, or advertisements. In our approach, instead of applying image…

This paper investigates using knowledge editing techniques to detoxify Large Language Models (LLMs). We construct a benchmark, SafeEdit, which covers nine unsafe categories with various powerful attack prompts and equips comprehensive…

Large language models (LLMs) exhibit impressive language capabilities but remain vulnerable to malicious prompts and jailbreaking attacks. Existing knowledge editing methods for LLM detoxification face two major challenges. First, they…