Chandan Singh

Senior Researcher

À propos

👋Hello👋! I work in the deep learning group on interpretable machine learning with the broad goal of improving science & medicine with data. For details, see my personal website or my google scholar. Here’s what I’m excited about these days:

🔎 Interpretability. I’m interested in rethinking interpretability in the context of LLMs

augmented imodels (opens in new tab) – use LLMs to build a transparent model
tree prompting (opens in new tab) – improve few-shot text classification with decision trees
attention steering (opens in new tab) – guide LLMs by emphasizing specific input spans
interpretable autoprompting (opens in new tab) – automatically find fluent natural-language prompts

🧠 Neuroscience. I also study leveraging LLMs to understand how the human brain represents language (using fMRI in collaboration with the Huth lab (opens in new tab) at UT Austin).

explanation-mediated validation (opens in new tab) – build and test fMRI explanations using LLM-generated stimuli
qa embeddings (opens in new tab) – build interpretable fMRI encoding models by asking yes/no questions to LLMs
summarize & score explanations (opens in new tab) – generate natural-language explanations of fMRI encoding models

My PhD at UC Berkeley (advised by Bin Yu (opens in new tab)) focused on working with scientists and doctors to develop interpretations for scientific domains.

Internships / collaborations

If you want to chat about research (or are interested in interning at MSR), feel free to reach out over email! Previously, I’ve been lucky to help mentor some wonderful students:

Recent publications

Crafting Interpretable Embeddings by Asking LLMs Questions

Large language models (LLMs) have rapidly improved text embeddings for a growing array of natural-language processing tasks. However, their opaqueness and proliferation into scientific domains such as neuroscience have created a growing need for interpretability. Here, we ask whether we…

Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs

In human-written articles, we often leverage the subtleties of text style, such as bold and italics, to guide the attention of readers. These textual emphases are vital for the readers to grasp the conveyed information. When interacting with large language…

Tree Prompting: Efficient Task Adaptation without Fine-Tuning

Prompting language models (LMs) is the main interface for applying them to new tasks. However, for smaller LMs, prompting provides low accuracy compared to gradient-based finetuning. Tree Prompting is an approach to prompting which builds a decision tree of prompts,…