Related papers: Bridging the Multilingual Safety Divide: Efficient…

Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows. This paper surveys research in the…

Recent developments in balancing the usefulness and safety of Large Language Models (LLMs) have raised a critical question: Are mainstream NLP tasks adequately aligned with safety consideration? Our study, focusing on safety-sensitive…

As online communication increasingly incorporates under-represented languages and colloquial dialects, standard translation systems often fail to preserve local slang, code-mixing, and culturally embedded markers of harmful speech.…

The rapid development in large language models (LLMs) has transformed the landscape of natural language processing and understanding (NLP/NLU), offering significant benefits across various domains. However, when applied to scientific…

Recent advances in LLMs have enhanced AI capabilities, but also increased the risk posed by malicious requests, highlighting the need for effective LLM safeguards to detect such queries. Existing approaches largely rely on classifier-based…

Large Language Model (LLM) safety is inherently pluralistic, reflecting variations in moral norms, cultural expectations, and demographic contexts. Yet, existing alignment datasets such as ANTHROPIC-HH and DICES rely on demographically…

Given the growing influence of language model-based agents on high-stakes societal decisions, from public policy to healthcare, ensuring their beneficial impact requires understanding the far-reaching implications of their suggestions. We…

Optimizing large language models (LLMs) for downstream use cases often involves the customization of pre-trained LLMs through further fine-tuning. Meta's open release of Llama models and OpenAI's APIs for fine-tuning GPT-3.5 Turbo on custom…

Pretrained multilingual models exhibit the same social bias as models processing English texts. This systematic review analyzes emerging research that extends bias evaluation and mitigation approaches into multilingual and non-English…

Ensuring the safety of Large Language Models (LLMs) in diverse linguistic settings remains challenging, particularly for low-resource languages. Existing safety alignment methods are English-centric, limiting their effectiveness. We…

Prior research has revealed that certain abstract concepts are linearly represented as directions in the representation space of LLMs, predominantly centered around English. In this paper, we extend this investigation to a multilingual…

Multilingual safety remains significantly imbalanced, leaving non-high-resource (NHR) languages vulnerable compared to robust high-resource (HR) ones. Moreover, the neural mechanisms driving safety alignment remain unclear despite observed…

Subjective well-being is a key metric in economic, medical, and policy decision-making. As artificial intelligence provides scalable tools for modelling human outcomes, it is crucial to evaluate whether large language models (LLMs) can…

Large Language Models (LLMs) have become increasingly popular for their advanced text generation capabilities across various domains. However, like any software, they face security challenges, including the risk of 'jailbreak' attacks that…

Despite their strong performance, large language models (LLMs) face challenges in real-world application of lexical simplification (LS), particularly in privacy-sensitive and resource-constrained environments. Moreover, since vulnerable…

While LLMs appear robustly safety-aligned in English, we uncover a catastrophic, overlooked weakness: attributional collapse under code-mixed perturbations. Our systematic evaluation of open models shows that the linguistic camouflage of…

With the rapid popularity of large language models such as ChatGPT and GPT-4, a growing amount of attention is paid to their safety concerns. These models may generate insulting and discriminatory content, reflect incorrect social values,…

Large Language Models (LLMs) increasingly shape global discourse, making fairness and ideological neutrality essential for responsible AI deployment. Despite growing attention to political bias in LLMs, prior work largely focuses on…

Code-mixing and code-switching (CSW) remain challenging phenomena for large language models (LLMs). Despite recent advances in multilingual modeling, LLMs often struggle in mixed-language settings, exhibiting systematic degradation in…

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…