相关论文: Analyzing Bias in False Refusal Behavior of Large …

Many social science questions ask how linguistic properties causally affect an audience's attitudes and behaviors. Because text properties are often interlinked (e.g., angry reviews use profane language), we must control for possible latent…

Hate speech detection within a cross-lingual setting represents a paramount area of interest for all medium and large-scale online platforms. Failing to properly address this issue on a global scale has already led over time to morally…

Hate speech detection is a socially sensitive and inherently subjective task, with judgments often varying based on personal traits. While prior work has examined how socio-demographic factors influence annotation, the impact of personality…

In our era of widespread false information, human fact-checkers often face the challenge of duplicating efforts when verifying claims that may have already been addressed in other countries or languages. As false information transcends…

Conversational large language models are fine-tuned for both instruction-following and safety, resulting in models that obey benign requests but refuse harmful ones. While this refusal behavior is widespread across chat models, its…

Although large language models (LLMs) demonstrate impressive proficiency in various tasks, they present potential safety risks, such as `jailbreaks', where malicious inputs can coerce LLMs into generating harmful content bypassing safety…

Research has shown that while large language models (LLMs) can generate their responses based on cultural context, they are not perfect and tend to generalize across cultures. However, when evaluating the cultural bias of a language…

This study introduces a prescriptive annotation benchmark grounded in humanities research to ensure consistent, unbiased labeling of offensive language, particularly for casual and non-mainstream language uses. We contribute two newly…

Despite growing interest in automated hate speech detection, most existing approaches overlook the linguistic diversity of online content. Multilingual instruction-tuned large language models such as LLaMA, Aya, Qwen, and BloomZ offer…

Refusal is a key safety behavior in aligned language models, yet the internal mechanisms driving refusals remain opaque. In this work, we conduct a mechanistic study of refusal in instruction-tuned LLMs using sparse autoencoders to identify…

While large language models (LLMs) are increasingly being explored for mental health applications, recent studies reveal that they can exhibit stigma toward individuals with psychological conditions. Existing evaluations of this stigma…

The advent of Large Language Models (LLMs) has marked significant achievements in language processing and reasoning capabilities. Despite their advancements, LLMs face vulnerabilities to data poisoning attacks, where the adversary inserts…

Safety alignment approaches in large language models (LLMs) often lead to the over-refusal of benign queries, significantly diminishing their utility in sensitive scenarios. To address this challenge, we introduce FalseReject, a…

As Large Language Models (LLMs) continue to evolve, they are increasingly being employed in numerous studies to simulate societies and execute diverse social tasks. However, LLMs are susceptible to societal biases due to their exposure to…

The widespread integration of Large Language Models (LLMs) across various sectors has highlighted the need for empirical research to understand their biases, thought patterns, and societal implications to ensure ethical and effective use.…

Combating online hate speech in multilingual settings requires approaches that go beyond English-centric models and capture the cultural and linguistic diversity of global online discourse. This paper presents a comprehensive survey and…

Large language models (LLMs) are becoming increasingly important for machine learning applications. However, it can be challenging to align LLMs with our intent, particularly when we want to generate content that is preferable over others…

Large Language Models (LLMs) can generate human-like disinformation, yet their ability to personalise such content across languages and demographics remains underexplored. This study presents the first large-scale, multilingual analysis of…

Large language models are meticulously aligned to be both helpful and harmless. However, recent research points to a potential overkill which means models may refuse to answer benign queries. In this paper, we investigate the factors for…

The common toxicity and societal bias in contents generated by large language models (LLMs) necessitate strategies to reduce harm. Present solutions often demand white-box access to the model or substantial training, which is impractical…