Related papers: Text Detoxification: Data Efficiency, Semantic Pre…

Texts convey sophisticated knowledge. However, texts also convey sensitive information. Despite the success of general-purpose language models and domain-specific mechanisms with differential privacy (DP), existing text sanitization…

Pre-trained language models (LMs) are shown to easily generate toxic language. In this work, we systematically explore domain-adaptive training to reduce the toxicity of language models. We conduct this study on three dimensions: training…

The quality of the dataset is crucial for ensuring optimal performance and reliability of downstream task models. However, datasets often contain noisy data inadvertently included during the construction process. Numerous attempts have been…

LLMs have demonstrated exceptional proficiency in a wide range of NLP tasks. However, a notable gap remains in practical data analysis scenarios, particularly when LLMs are required to process long sequences of unstructured documents, such…

Large language models (LLMs) frequently generate toxic content, posing significant risks for safe deployment. Current mitigation strategies often degrade generation quality or require costly human annotation. We propose CAUSALDETOX, a…

Traditionally, Text Simplification is treated as a monolingual translation task where sentences between source texts and their simplified counterparts are aligned for training. However, especially for longer input documents, summarizing the…

Depression is a growing issue in society's mental health that affects all areas of life and can even lead to suicide. Fortunately, prevention programs can be effective in its treatment. In this context, this work proposes an automatic…

Toxic interactions in open-source software development harm community collaboration. To combat this, we propose ToxiShield, a realtime browser extension that identifies and detoxifies toxic code reviews. The framework comprises three…

In this position paper, we argue that the classical evaluation on Natural Language Processing (NLP) tasks using annotated benchmarks is in trouble. The worst kind of data contamination happens when a Large Language Model (LLM) is trained on…

Data contamination has received increasing attention in the era of large language models (LLMs) due to their reliance on vast Internet-derived training corpora. To mitigate the risk of potential data contamination, LLM benchmarking has…

Despite being a unique source of information on patients' status and disease progression, clinical notes are characterized by high levels of duplication and information redundancy. In general domain text, it has been shown that…

Most existing large language models (LLMs) are expensive to adapt after deployment, especially when a task requires newly produced information or niche domain knowledge. Recent work has shown that, by manipulating and optimizing their…

Toxicity classification in textual content remains a significant problem. Data with labels from a single annotator fall short of capturing the diversity of human perspectives. Therefore, there is a growing need to incorporate crowdsourced…

This paper presents a solution for the Multilingual Text Detoxification task in the PAN-2024 competition of the SmurfCat team. Using data augmentation through machine translation and a special filtering procedure, we collected an additional…

Recently, with the help of deep learning models, significant advances have been made in different Natural Language Processing (NLP) tasks. Unfortunately, state-of-the-art models are vulnerable to noisy texts. We propose a new contextual…

Data contamination undermines the validity of Large Language Model evaluation by enabling models to rely on memorized benchmark content rather than true generalization. While prior work has proposed contamination detection methods, these…

The volume of machine-generated content online has grown dramatically due to the widespread use of Large Language Models (LLMs), leading to new challenges for content moderation systems. Conventional content moderation classifiers, which…

Large language models (LLMs) are increasingly exposed to data contamination, i.e., performance gains driven by prior exposure of test datasets rather than generalization. However, in the context of tabular data, this problem is largely…

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…

Large Language Models (LLMs) have demonstrated a powerful ability for text generation. However, achieving optimal results with a given prompt or instruction can be challenging, especially for billion-sized models. Additionally, undesired…