Related papers: Self-Detoxifying Language Models via Toxification …

Large language models (LLMs) learn undesirable properties during pretraining, including dangerous knowledge and toxic text generation. Just as post-training uses different objectives to shape different behaviors, we argue that unlearning…

Text detoxification is the task of transferring the style of text from toxic to neutral. While here are approaches yielding promising results in monolingual setup, e.g., (Dale et al., 2021; Hallinan et al., 2022), cross-lingual transfer for…

Prompting has become a practical method for utilizing pre-trained language models (LMs). This approach offers several advantages. It allows an LM to adapt to new tasks with minimal training and parameter updates, thus achieving efficiency…

Text Generation aims to produce plausible and readable text in a human language from input data. The resurgence of deep learning has greatly advanced this field, in particular, with the help of neural generation models based on pre-trained…

The rapid spread of misinformation on online platforms undermines trust among individuals and hinders informed decision making. This paper shows an explainable and computationally efficient pipeline to detect misinformation using…

Large transformer-based language models (LMs) trained on huge text corpora have shown unparalleled generation capabilities. However, controlling attributes of the generated language (e.g. switching topic or sentiment) is difficult without…

Large language models (LLMs) have achieved impressive results across a range of natural language processing tasks, but their potential to generate harmful content has raised serious safety concerns. Current toxicity detectors primarily rely…

Pre-trained language models (PLMs) have proven to be effective for document re-ranking task. However, they lack the ability to fully interpret the semantics of biomedical and health-care queries and often rely on simplistic patterns for…

Text detoxification has the potential to mitigate the harms of toxicity by rephrasing text to remove offensive meaning, but subtle toxicity remains challenging to tackle. We introduce MaRCo, a detoxification algorithm that combines…

Debiasing methods that seek to mitigate the tendency of Language Models (LMs) to occasionally output toxic or inappropriate text have recently gained traction. In this paper, we propose a standardized protocol which distinguishes methods…

We propose a self-correction mechanism for Large Language Models (LLMs) to mitigate issues such as toxicity and fact hallucination. This method involves refining model outputs through an ensemble of critics and the model's own feedback.…

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 classifiers, implicitly…

As Large Language Models (LLMs) achieve remarkable success across a wide range of applications, such as chatbots and code copilots, concerns surrounding the generation of harmful content have come increasingly into focus. Despite…

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…

The meanings of words and phrases depend not only on where they are used (contexts) but also on who use them (writers). Pretrained language models (PLMs) are powerful tools for capturing context, but they are typically pretrained and…

The open-endedness of large language models (LLMs) combined with their impressive capabilities may lead to new safety issues when being exploited for malicious use. While recent studies primarily focus on probing toxic outputs that can be…

Safety-aligned large language models (LLMs) sometimes falsely refuse pseudo-harmful prompts, like "how to kill a mosquito," which are actually harmless. Frequent false refusals not only frustrate users but also provoke a public backlash…

Recent years have witnessed increasing interests in prompt-based learning in which models can be trained on only a few annotated instances, making them suitable in low-resource settings. When using prompt-based learning for text…

Many efforts have been made to facilitate natural language processing tasks with pre-trained language models (LMs), and brought significant improvements to various applications. To fully leverage the nearly unlimited corpora and capture…

Social media platforms utilize Machine Learning (ML) and Artificial Intelligence (AI) powered recommendation algorithms to maximize user engagement, which can result in inadvertent exposure to harmful content. Current moderation efforts,…