Large language models (LLMs) typically generate identical or similar responses for all users given the same prompt, posing serious safety risks in high-stakes applications where user vulnerabilities differ widely. Existing safety evaluations primarily rely on context-independent metrics--such as factuality, bias, or toxicity--overlooking the fact that the same response may carry divergent risks depending on the user's background or condition. We introduce "personalized safety" to fill this gap and present PENGUIN--a benchmark comprising 14,000scenarios across seven sensitive domains with both context-rich and context-free variants. Evaluating six leading LLMs, we demonstrate that personalized user information significantly improves safety scores by 43.2%, confirming the effectiveness of personalization in safety alignment. However, not all context attributes contribute equally to safety enhancement. To address this, we develop RAISE--a training-free, two-stage agent framework that strategically acquires user-specific background. RAISE improves safety scores by up to 31.6%over six vanilla LLMs, while maintaining a low interaction cost of just 2.7 user queries on average. Our findings highlight the importance of selective information gathering in safety-critical domains and offer a practical solution for personalizing LLM responses without model retraining. This work establishes a foundation for safety research that adapts to individual user contexts rather than assuming a universal harm standard.

The meteoric rise in text generation capability has been accompanied by parallel growth in interest in machine-generated text detection: the capability to identify whether a given text was generated using a model or written by a person. While detection models show strong performance, they have the capacity to cause significant negative impacts. We explore potential biases in English machine-generated text detection systems. We curate a dataset of student essays and assess 16 different detection systems for bias across four attributes: gender, race/ethnicity, English-language learner (ELL) status, and economic status. We evaluate these attributes using regression-based models to determine the significance and power of the effects, as well as performing subgroup analysis. We find that while biases are generally inconsistent across systems, there are several key issues: several models tend to classify disadvantaged groups as machine-generated, ELL essays are more likely to be classified as machine-generated, economically disadvantaged students' essays are less likely to be classified as machine-generated, and non-White ELL essays are disproportionately classified as machine-generated relative to their White counterparts. Finally, we perform human annotation and find that while humans perform generally poorly at the detection task, they show no significant biases on the studied attributes.

Pandemics involve the high transmission of a disease that impacts global and local health and economic patterns. The impact of a pandemic can be minimized by enforcing certain restrictions on a community. However, while minimizing infection and death rates, these restrictions can also lead to economic crises. Epidemiological models help propose pandemic control strategies based on non-pharmaceutical interventions such as social distancing, curfews, and lockdowns, reducing the economic impact of these restrictions. However, designing manual control strategies while considering disease spread and economic status is non-trivial. Optimal strategies can be designed through multi-objective reinforcement learning (MORL) models, which demonstrate how restrictions can be used to optimize the outcome of a pandemic. In this research, we utilized an epidemiological Susceptible, Exposed, Infected, Recovered, Deceased (SEIRD) model: a compartmental model for virtually simulating a pandemic day by day. We combined the SEIRD model with a deep double recurrent Q-network to train a reinforcement learning agent to enforce the optimal restriction on the SEIRD simulation based on a reward function. We tested two agents with unique reward functions and pandemic goals to obtain two strategies. The first agent placed long lockdowns to reduce the initial spread of the disease, followed by cyclical and shorter lockdowns to mitigate the resurgence of the disease. The second agent provided similar infection rates but an improved economy by implementing a 10-day lockdown and 20-day no-restriction cycle. This use of reinforcement learning and epidemiological modeling allowed for both economic and infection mitigation in multiple pandemic scenarios.

Little attention is placed on analyzing nationality bias in language models, especially when nationality is highly used as a factor in increasing the performance of social NLP models. This paper examines how a text generation model, GPT-2, accentuates pre-existing societal biases about country-based demonyms. We generate stories using GPT-2 for various nationalities and use sensitivity analysis to explore how the number of internet users and the country's economic status impacts the sentiment of the stories. To reduce the propagation of biases through large language models (LLM), we explore the debiasing method of adversarial triggering. Our results show that GPT-2 demonstrates significant bias against countries with lower internet users, and adversarial triggering effectively reduces the same.

Increased deployment of Artificial Intelligence around the world has torn open a very public and heated debate. While AI is being used to do things like sentence criminals, determine who should be hired and fired, and assess what loan rate you should be offered, it's also being leveraged to protect against poaching, detect illnesses sooner and more accurately, and shed new insights into fighting climate change. As we continue to develop AmandaAI here at TTT, we increasingly involve ourselves in the field. And as the technology continues to advance, we will continue to take on more and more clients who want to incorporate AI into their software. Since we're helping to create an AI-enabled future, we have a responsibility to explore what exactly that means.