相关论文: Perplexed by Quality: A Perplexity-based Method fo…

Generative AI systems powered by Large Language Models (LLMs) usually use content moderation to prevent harmful content spread. To evaluate the robustness of content moderation, several metamorphic testing techniques have been proposed to…

Parallel Data Curation (PDC) techniques aim to filter out noisy parallel sentences from web-mined corpora. Ranking sentence pairs using similarity scores on sentence embeddings derived from Pre-trained Multilingual Language Models…

Existing detoxification methods for large language models mainly focus on post-training stage or inference time, while few tackle the source of toxicity, namely, the dataset itself. Such training-based or controllable decoding approaches…

In recent years, the use of large language models (LLMs) for text classification has attracted widespread attention. Despite this, the classification accuracy of LLMs has not yet universally surpassed that of smaller models. LLMs can…

The exponential increase in scientific literature and online information necessitates efficient methods for extracting knowledge from textual data. Natural language processing (NLP) plays a crucial role in addressing this challenge,…

Large language models (LLMs) have been increasingly applied to automated harmful content detection tasks, assisting moderators in identifying policy violations and improving the overall efficiency and accuracy of content review. However,…

The effectiveness of large language models (LLMs) is often hindered by duplicated data in their extensive pre-training datasets. Current approaches primarily focus on detecting and removing duplicates, which risks the loss of valuable…

A common use of NLP is to facilitate the understanding of large document collections, with a shift from using traditional topic models to Large Language Models. Yet the effectiveness of using LLM for large corpus understanding in real-world…

Unstructured text from legal, medical, and administrative sources offers a rich but underutilized resource for research in public health and the social sciences. However, large-scale analysis is hampered by two key challenges: the presence…

Exploring the data sources used to train Large Language Models (LLMs) is a crucial direction in investigating potential copyright infringement by these models. While this approach can identify the possible use of copyrighted materials in…

We introduce a state-of-the-art approach for URL categorization that leverages the power of Large Language Models (LLMs) to address the primary objectives of web content filtering: safeguarding organizations from legal and ethical risks,…

Data contamination in model evaluation is getting increasingly prevalent as the massive training corpora of large language models often unintentionally include benchmark samples. Therefore, contamination analysis has became an inevitable…

To support safety and inclusion in online communications, significant efforts in NLP research have been put towards addressing the problem of abusive content detection, commonly defined as a supervised classification task. The research…

Recent advances in large language models (LLMs) have demonstrated strong performance on simple text classification tasks, frequently under zero-shot settings. However, their efficacy declines when tackling complex social media challenges…

Online toxic content has grown into a pervasive phenomenon, intensifying during times of crisis, elections, and social unrest. A significant amount of research has been focused on detecting or analyzing toxic content using machine-learning…

As Large Language Models (LLMs) become increasingly widespread, understanding how specific training data shapes their outputs is crucial for transparency, accountability, privacy, and fairness. To explore how LLMs leverage and replicate…

Large Language Models (LLMs) have been shown to generate harmful content. However, the underlying causes of such behavior remain under explored. We propose a causal mediation analysis-based approach to identify the causal factors…

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…

This article presents a hybrid methodology for building a multilingual corpus designed to support the study of emerging concepts in the humanities and social sciences (HSS), illustrated here through the case of ``non-technological…

Recent advances in large language models (LLMs) have led to their extensive global deployment, and ensuring their safety calls for comprehensive and multilingual toxicity evaluations. However, existing toxicity benchmarks are overwhelmingly…