The deployment of Large Language Models (LLMs) in diverse applications necessitates an assurance of safety without compromising the contextual integrity of the generated content. Traditional approaches, including safety-specific fine-tuning or adversarial testing, often yield safe outputs at the expense of contextual meaning. This can result in a diminished capacity to handle nuanced aspects of bias and toxicity, such as underrepresentation or negative portrayals across various demographics. To address these challenges, we introduce MBIAS, an LLM framework carefully instruction fine-tuned on a custom dataset designed specifically for safety interventions. MBIAS is designed to significantly reduce biases and toxic elements in LLM outputs while preserving the main information. This work also details our further use of LLMs: as annotator under human supervision and as evaluator of generated content. Empirical analysis reveals that MBIAS achieves a reduction in bias and toxicity by over 30% in standard evaluations, and by more than 90% in diverse demographic tests, highlighting the robustness of our approach. We make the dataset and the fine-tuned MBIAS model available to the research community for further investigation and to ensure reproducibility. The code for this project can be accessed here https://github.com/shainarazavi/MBIAS.

Medical dialogue systems have the potential to assist doctors in expanding access to medical care, improving the quality of patient experiences, and lowering medical expenses. The computational methods are still in their early stages and are not ready for widespread application despite their great potential. Existing transformer-based language models have shown promising results but lack domain-specific knowledge. However, to diagnose like doctors, an automatic medical diagnosis necessitates more stringent requirements for the rationality of the dialogue in the context of relevant knowledge. In this study, we propose a new method that addresses the challenges of medical dialogue generation by incorporating medical knowledge into transformer-based language models. We present a method that leverages an external medical knowledge graph and injects triples as domain knowledge into the utterances. Automatic and human evaluation on a publicly available dataset demonstrates that incorporating medical knowledge outperforms several state-of-the-art baseline methods.

News recommender systems face certain challenges. These challenges arise due to evolving users’ preferences over dynamically created news articles. The diversity is necessary for a news recommender system to expose users to a variety of information. We propose a deep neural network based on a two-tower architecture that learns news representation through a news item tower and users’ representations through a query tower. We customize an augmented vector for each query and news item to introduce information interaction between the two towers. We introduce diversity in the proposed architecture by considering a category loss function that aligns items’ representation of uneven news categories. Experimental results on two news datasets reveal that our proposed architecture is more effective compared to the state-of-the-art methods and achieves a balance between accuracy and diversity.

The dynamics and influence of fake news on Twitter during the 2020 US presidential election remains to be clarified. Here, we use a dataset related to 2020 U.S Election that consists of news articles and tweets on those articles. Therefore, it is extremely important to stop the spread of fake news before it reaches a mass level, which is a big challenge. We propose a novel fake news detection framework that can address this challenge. Our proposed framework exploits the information from news articles and social contexts to detect fake news. The proposed model is based on a Transformer architecture, which can learn useful representations from fake news data and predicts the probability of a news as being fake or real. Experimental results on real-world data show that our model can detect fake news with higher accuracy and much earlier, compared to the baselines.