Large language models (LLMs) support data analysis through conversational user
interfaces, as exemplified in OpenAI's ChatGPT (formally known as Advanced Data Analysis …

Many neural nets appear to represent data as linear combinations of" feature vectors."
Algorithms for discovering these vectors have seen impressive recent success. However, we …

We demonstrate that when people use large language models (LLMs) to generate
recommendations, the LLMs produce responses that reflect both what the user wants and …

Large Language Models (LLMs) are increasingly utilized for domain-specific tasks, yet
integrating domain expertise into evaluating their outputs remains challenging. A common …

Interpretability methods seek to understand language model representations, yet the outputs
of most such methods--circuits, vectors, scalars--are not immediately human-interpretable. In …

While the biases of language models in production are extensively documented, the biases
of their guardrails have been neglected. This paper studies how contextual information …

User prompts for generative AI models are often underspecified, leading to sub-optimal
responses. This problem is particularly evident in text-to-image (T2I) generation, where …

Traditional POI recommendation systems often lack transparency, interpretability, and
scrutability due to their reliance on dense vector-based user embeddings. Furthermore, the …

The telecommunications industry is increasingly reliant on human agents to handle complex
customer support inquiries. With the rapid evolution of technologies like 5G and IoT …

There is an urgent need to identify both short and long-term risks from newly emerging types
of Artificial Intelligence (AI), as well as available risk management measures. In response …