My lab will move to

and

this Fall! I’m excited to connect with amazing researchers at

and larger ML/NLP community in NYC. I will be recruiting students this cycle at NYU. Happy to be back to the city 🗽on the east coast as well. I had a

We study sampling diverse output from a suite of LLMs. One key surprise for me was that it's better to carefully pick a single model to sample many times, rather than naively mixing outputs from multiple models.

Do LLMs suffer from human-like cognitive biases? 🤔 Check out

's new paper on how models navigate hypothesis spaces. We found that confirmation bias degrades LLM performance, and we explore strategies to mitigate it.

Excited to introduce our new work on improving information coverage for search systems (LLMs + retriever). Key idea: train retrievers to search for answers that are missing from earlier retrieval rounds.

Reasoning models are more uncertain when generating reasoning traces for easy questions compared to generating traces for medium-difficulty questions. We use this insight to build a light-weight, adaptive inference strategy for reasoning models. Was fun exploring this with my