相关论文: Probing Association Biases in LLM Moderation Over-…

The prevalence and impact of toxic discussions online have made content moderation crucial.Automated systems can play a vital role in identifying toxicity, and reducing the reliance on human moderation.Nevertheless, identifying toxic…

The conformity bias exhibited by large language models (LLMs) can pose a significant challenge to decision-making in LLM-based multi-agent systems (LLM-MAS). While many prior studies have treated "conformity" simply as a matter of opinion…

The recent advancement of large language models has spurred a growing trend of integrating pre-trained language model (PLM) embeddings into topic models, fundamentally reshaping how topics capture semantic structure. Classical models such…

In recent years, Large Language Models have attracted growing interest for their significant potential, though concerns have rapidly emerged regarding unsafe behaviors stemming from inherent stereotypes and biases. Most research on…

Users interacting with Large Language Models (LLMs) in a multi-turn conversation routinely refine their requests or pivot to new topics. LLMs, however, often miss these topic shifts and carry over irrelevant context from previous turns,…

Transformer-based Neural Language Models achieve state-of-the-art performance on various natural language processing tasks. However, an open question is the extent to which these models rely on word-order/syntactic or word…

Large Language Models (LLMs) have excelled at language understanding and generating human-level text. However, even with supervised training and human alignment, these LLMs are susceptible to adversarial attacks where malicious users can…

Large language models (LLMs) excel in many diverse applications beyond language generation, e.g., translation, summarization, and sentiment analysis. One intriguing application is in text classification. This becomes pertinent in the realm…

Target-dependent sentiment classification remains a challenge: modeling the semantic relatedness of a target with its context words in a sentence. Different context words have different influences on determining the sentiment polarity of a…

Pretrained neural language models (LMs) are prone to generating racist, sexist, or otherwise toxic language which hinders their safe deployment. We investigate the extent to which pretrained LMs can be prompted to generate toxic language,…

Topic models are widely used analysis techniques for clustering documents and surfacing thematic elements of text corpora. These models remain challenging to optimize and often require a "human-in-the-loop" approach where domain experts use…

Oversensitivity occurs when language models defensively reject prompts that are actually benign. This behavior not only disrupts user interactions but also obscures the boundary between harmful and harmless content. Existing benchmarks rely…

Large Language models (LLMs), such as ChatGPT, have gained popularity in recent years with the advancement of Natural Language Processing (NLP), with use cases spanning many disciplines and daily lives as well. LLMs inherit explicit and…

Large Language Models have been shown to demonstrate stereotypical biases in their representations and behavior due to the discriminative nature of the data that they have been trained on. Despite significant progress in the development of…

The detrimental effects of toxicity in competitive online video games are widely acknowledged, prompting publishers to monitor player chat conversations. This is challenging due to the context-dependent nature of toxicity, often spread…

As Large language models (LLMs) become increasingly integrated into our lives, their inherent social biases remain a pressing concern. Detecting and evaluating these biases can be challenging because they are often implicit rather than…

Recent research has highlighted that assigning specific personas to large language models (LLMs) can significantly increase harmful content generation. However, limited attention has been given to persona-driven toxicity in non-Western…

Sentiment analysis of alternative tobacco products on social media is important for tobacco control research. Large Language Models (LLMs) can help streamline the labor-intensive human sentiment analysis process. This study examined the…

A limited amount of studies investigates the role of model-agnostic adversarial behavior in toxic content classification. As toxicity classifiers predominantly rely on lexical cues, (deliberately) creative and evolving language-use can be…

Traditional neural topic models are typically optimized by reconstructing the document's Bag-of-Words (BoW) representations, overlooking contextual information and struggling with data sparsity. In this work, we propose a novel approach to…