Research Intern - Training-Time Provenance (Data Dignity)

Research Internships at Microsoft provide a dynamic environment for research careers with a network of world-class research labs led by globally-recognized scientists and engineers, who pursue innovation in a range of scientific and technical disciplines to help solve complex challenges in diverse fields, including computing, healthcare, economics, and the environment.

Training-time provenance is a research effort on estimating the influence of specific training data on outputs of large language models (LLMs). Current neural network architectures are opaque in terms of providing sources for their generations, and there are at least two good reasons to change this:

1. “X-ray” into intent, so that we can detect bad human actors or dangerous AI activity by identifying the most influential source documents related to a given model output. For instance, sneaky prompts might invoke articles about bomb making that could evade guardrails otherwise. This will be a deeper method of countering this type of danger than others currently in use.
2. “Data dignity”, meaning incentives, recognition, and potentially pay for people who contribute certain valuable data to unforeseen kinds of models we will want in the future, assuming the future will surprise us fundamentally. The goal is to foster new classes of creative professionals where possible, instead of relying solely on ideas like Universal Basic Income in the event of a future with very high-functioning large models. 

We are attempting to demonstrate that LLMs can be trained in such a way that influence of specific training data on generated outputs can be efficiently and usefully estimated. You can read more about “Data dignity” in the article: There is no A.I. (The New Yorker).

Research Interns put inquiry and theory into practice. Alongside fellow doctoral candidates and some of the world’s best researchers, Research Interns learn, collaborate, and network for life. Research Interns not only advance their own careers, but they also contribute to exciting research and development strides. During the 12-week internship, Research Interns are paired with mentors and expected to collaborate with other Research Interns and researchers, present findings, and contribute to the vibrant life of the community. Research internships are available in all areas of research, and are offered year-round, though they typically begin in the summer.

For this Research Internship (summer 2025), we are seeking PhD students with a passion for fundamental Deep Learning research, particularly those with experience in training LLMs and other large AI models. The Research Intern's responsibilities will include (1) training small language models with novel schemes preserving provenance of data, (2) experimenting with these models to test their performance and reliability.