Research

AI can match or even outperform humans in many tasks, but they are also prone to mistakes on unfamiliar inputs. Unfortunately, AI often encounter unfamiliar inputs when deployed in the real world because training data is seldom diverse enough to reflect the diversity of real-world inputs. This not only degrades (AI) reliablity but can also lead to safety violations. For example,

1. polygenic risk scores are many times less accurate on non-European people because most subjects in genome-wide association studies are European [Martin et al];
2. word embeddings perpetuate gender stereotypes: “man is to computer programmer as woman is to homemaker” [Bolukbasi et al];
3. malicious users can circumvent ChatGPT’s safety training with adversarial inputs (“jailbreak” attacks) [Wei et al].

My research leverages statistical science to improve the reliability and safety of AI in the real world. Towards this goal, we work on:

AI alignment and evaluation

Despite transformative advances in AI (experts predict that AI will exceed human capabilities in the near future [Bengio et al]), AI remain prone to unexpected behavior, making them unreliable and potentially dangerous in the hands of malicious actors. We develop new theories and methods for AI alignment and evaluation to help us anticipate and manage AI risks. Some representative papers are:

1. A statistical framework for weak-to-strong generalization
   S Somerstep, F Maia Polo, M Banerjee, Y Ritov, M Yurochkin, Y Sun.
2. Aligners: Decoupling LLMs and Alignment
   L Ngweta, M Agarwal, S Maity, A Gittens, Y Sun, M Yurochkin.
   A short version appeared as an ICLR 2024 TinyPaper.
3. tinyBenchmarks: evaluating LLMs with few examples
   F Maia Polo, L Weber, L Choshen, Y Sun, G Xu, M Yurochkin. ICML 2024.

Algorithmic fairness

My foray into algorithmic fairness began with an effort to develop a suite of algorithms to help practitioners implement individual fairness (IF), an intuitive notion of algorithmic fairness that requires algorithms to “treat similar inputs similarly”. The suite includes algorithms for aligning similarity metrics with user feedback, auditing algorithms for violations of IF, and training individually fair AI. The algorithms are implemented in

/Trusted-AI/AIF360
/IBM/inFairness

Before our work, IF was dismissed as impractical because there were no practical ways of picking similarity metrics for many AI tasks and no practical algorithms to train individually fair AI. The (similarity) metric learning algorithms in the suite address this issue by helping practitioners align similarity metrics with user feedback. Here are some representative papers:

1. Post-processing for Individual Fairness
   F Petersen, D Mukherjee, Y Sun, M Yurochkin. NeurIPS 2021.
2. SenSeI: Sensitive Set Invariance for Enforcing Individual Fairness
   M Yurochkin, Y Sun. ICLR 2021.
3. Two simple ways to learn individual fairness metrics from data
   D Mukherjee, M Yurochkin, M Banerjee, Y Sun. ICML 2020.

Learning under distribution shifts

AI often encounter adversarial and out-of-distribution inputs in the real world, but the pernicious effects of distribution shifts are poorly understood. This is a form of technical debt that hinders us from anticipating AI risks before they arise. We seek to repay this technical debt. A key insight from our work is (contrary to popular belief) aligning AI so that they are fair/safe/transparent may not be at odds with performance. In fact, alignment can improve (out-of-distribution) performance. Some representative papers are:

1. Algorithmic Fairness in Performative Policy Learning: Escaping the Impossibility of Group Fairness
   S Somerstep, Y Ritov, Y Sun. FAccT 2024.
2. An Investigation of Representation and Allocation Harms in Contrastive Learning
   S Maity, M Agarwal, M Yurochkin, Y Sun. ICLR 2024.
3. Domain Adaptation meets Individual Fairness. And they get along.
   D Mukherjee, F Petersen, M Yurochkin, Y Sun. NeurIPS 2022.