相关论文: OpenAI's GPT-OSS-20B Model and Safety Alignment Is…

This work explores fine-tuning OpenAI's Whisper automatic speech recognition (ASR) model for Amharic, a low-resource language, to improve transcription accuracy. While the foundational Whisper model struggles with Amharic due to limited…

Hate speech detection relies heavily on linguistic resources, which are primarily available in high-resource languages such as English and Chinese, creating barriers for researchers and platforms developing tools for low-resource languages…

Large language models exhibit safety degradation in non-English languages. Standard evaluation relies on Jailbreak Success Rate (JSR), which confounds several safety-driving factors into one, obscuring the specific cause(s) of safety…

As Large Language Models (LLMs) become integrated into daily life, they are increasingly used for personal queries, including Sexual and Reproductive Health (SRH), allowing users to chat anonymously without fear of judgment. However,…

In light of the mounting imperative for public security, the necessity for automated threat detection in high-risk scenarios is becoming increasingly pressing. However, existing methods generally suffer from the problems of uninterpretable…

Social media platforms allow users to freely share their opinions about issues or anything they feel like. However, they also make it easier to spread hate and abusive content. The Fulani ethnic group has been the victim of this unfortunate…

In recent years, neural models trained on large multilingual text and speech datasets have shown great potential for supporting low-resource languages. This study investigates the performances of two state-of-the-art Automatic Speech…

Social media platforms serve as accessible outlets for individuals to express their thoughts and experiences, resulting in an influx of user-generated data spanning all age groups. While these platforms enable free expression, they also…

This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We…

Progress in natural language generation research has been shaped by the ever-growing size of language models. While large language models pre-trained on web data can generate human-sounding text, they also reproduce social biases and…

Large language models (LLMs) have become mainstream technology with their versatile use cases and impressive performance. Despite the countless out-of-the-box applications, LLMs are still not reliable. A lot of work is being done to improve…

The capabilities of natural language models trained on large-scale data have increased immensely over the past few years. Open source libraries such as HuggingFace have made these models easily available and accessible. While prior research…

The rise of digital technology has dramatically increased the potential for cyberbullying and online abuse, necessitating enhanced measures for detection and prevention, especially among children. This study focuses on detecting abusive…

In this paper, we test the hypothesis that although OpenAI's GPT-4 performs well generally, we can fine-tune open-source models to outperform GPT-4 in smart contract vulnerability detection. We fine-tune two models from Meta's Code Llama…

The integration of large language models (LLMs) on low-power edge devices such as Raspberry Pi, known as edge language models (ELMs), has introduced opportunities for more personalized, secure, and low-latency language intelligence that is…

When encountering increasingly frequent performance improvements or cost reductions from a new large language model (LLM), developers of applications leveraging LLMs must decide whether to take advantage of these improvements or stay with…

While most AI alignment research focuses on preventing models from generating explicitly harmful content, a more subtle risk is emerging: capability-oriented training induced exploitation. We investigate whether language models, when…

Recent advances in aligning Large Language Models with human preferences have benefited from larger reward models and better preference data. However, most of these methodologies rely on the accuracy of the reward model. The reward models…

Sociotechnical systems, such as language technologies, frequently exhibit identity-based biases. These biases exacerbate the experiences of historically marginalized communities and remain understudied in low-resource contexts. While models…

Large Language Models (LLMs), such as ChatGPT, are widely used to generate content for various purposes and audiences. However, these models may not reflect the cultural and emotional diversity of their users, especially for low-resource…