Chandan Singh | chandan singh

Research

Some areas I'm currently excited about. If you want to chat about research or are interested in interning at MSR, feel free to reach out over email :)

🔎 Interpretability methods, especially LLM interpretability.

augmented imodels - build a transparent model using LLMs
attention steering - mechanistically guide LLMs by emphasizing specific input spans
explanation penalization - regularize explanations to align models with prior knowledge
adaptive wavelet distillation - replace neural nets with transparent wavelet models

💊 Clinical decision rules, can we improve them with data?

human-ai co-design of clinical models - build clinical rules by using LLMs to analyze EHR, vetted by clinicians
greedy tree sums - build accurate, compact tree-based clinical models
clinical self-verification - improve LLM-based clinical information extraction with self-verirication
clinical rule vetting - test a clinical decision instrument for evaluating intra-abdominal injury
clinical rule bias assessment - evaluate biases in the development of popular clinical decision instruments

🧠 Semantic brain mapping, mostly using fMRI responses to language.

generative causal testing - causally test fMRI explanations with LLM-generated stimuli
qa encoding models - model fMRI language responses to verbal theories using LLM annotations
summarize & score explanations - generate natural-language explanations of fMRI encoding models

Note: I put a lot of my code into the imodels and imodelsX packages.

year	title	authors	tags	paper
'26	Test-time Recursive Thinking: Self-Improvement without External Feedback	zhuang, singh, liu, shen, zhang, shang, gao, & chen	🌀	arXiv
'26	Human-AI Co-design for Clinical Prediction Models	feng, kothari, vossler, bishara, zier, addo, kornblith, tan, & singh	💊🌀	arXiv
'26	Do explanations generalize across large reasoning models?	pal, bau, & singh	💊🌀	arXiv
'25	Evaluating scientific theories as predictive models in language neuroscience	singh, antonello, guo, mischler, gao, mesgarani, & huth	🧠🔎🌀	bioRxiv
'25	Mixture of Inputs	zhuang et al.	🌀	NeurIPS
'25	Interpretable Language Modeling via Induction-head Ngram Models	kim, mantena, et al.	🧠🔎🌀	NeurIPS
'25	Bayesian Concept Bottleneck Models with LLM Priors	feng, kothari, zier, singh, & tan	🔎🌀	NeurIPS
'25	OmniGuard	verma, hines, bilmes, siska, zettlemoyer, gonen, & singh	🌀	EMNLP
'25	Systematic Bias in Clinical Decision Instrument Development	obra, singh, et al.	🔎💊	npj Digital Medicine
'25	Analyzing patient perspectives with llms	kornblith, singh et al.	💊🌀	nature scientific reports
'25	SimDINO	wu et al.	🌀	icml
'25	Vector-ICL: In-context Learning with Continuous Vector Representations	zhuang et al.	🔎🌀	iclr
'24	Crafting Interpretable Embeddings by Asking LLMs Questions	benara, singh, morris, antonello, stoica, huth, & gao	🧠🔎🌀	neurips
'25	Generative causal testing to bridge data-driven models and scientific theories in language neuroscience	antonello, singh, jain, hsu, gao, yu, & huth	🧠🔎🌀	arxiv
'25	Towards Understanding Graphical Perception in Large Multimodal Models	zhang et al.	🌀	arxiv
'24	Rethinking Interpretability in the Era of Large Language Models	singh, inala, galley, caruana, & gao	🔎🌀	arxiv
'24	Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning	chen et al.	🔎🌀	COLING
'24	Learning a Decision Tree Algorithm with Transformers	zhuang et al.	🔎🌀🌳	tmlr
'24	Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering	zhang, yu, et al.	🔎🌀	arxiv
'24	Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs	zhang et al.	🔎🌀	iclr
'24	Attribute Structuring Improves LLM-Based Evaluation of Clinical Text Summaries	gero et al.	🔎🌀	ml4h findings
'23	Tree Prompting	morris, singh, rush, gao, & deng	🔎🌀🌳	emnlp
'23	Augmenting Interpretable Models with LLMs during Training	singh, askari, caruana, & gao	🔎🌀🌳	nature communications
'23	Explaining black box text modules in natural language with language models	singh, hsu, antonello, jain, huth, yu & gao	🔎🌀	neurips workshop
'23	Self-Verification Improves Few-Shot Clinical Information Extraction	gero, singh, cheng, naumann, galley, gao, & poon	🔎🌀💊	icml workshop
'22	Explaining patterns in data with language models via interpretable autoprompting	singh, morris, aneja, rush, & gao	🔎🌀	emnlp workshop
'22	Stress testing a clinical decision instrument performance for intra-abdominal injury	kornblith, singh et al.	🔎🌳💊	PLOS digital health
'22	Fast interpretable greedy-tree sums (FIGS)	tan, singh, nasseri, agarwal, & yu	🔎🌳	pnas
'22	Hierarchical shrinkage for trees	agarwal, tan, ronen, singh, & yu	🔎🌳	icml (spotlight)
'22	VeridicalFlow: a python package for building trustworthy data science pipelines with PCS	duncan, kapoor, agarwal, singh, & yu	💻🔍	joss
'21	imodels: a python package for fitting interpretable models	singh, nasseri, et al.	💻🔍🌳	joss
'21	Adaptive wavelet distillation from neural networks through interpretations	ha, singh, et al.	🔍🌀🌳	neurips
'21	Matched sample selection with GANs for mitigating attribute confounding	singh, balakrishnan, & perona	🌀	cvpr workshop
'21	Revisiting complexity and the bias-variance tradeoff	dwivedi, singh, yu & wainwright	🌀	jmlr
'20	Curating a COVID-19 data repository and forecasting county-level death counts in the United States	altieri et al.	🔎🦠	hdsr
'20	Transformation importance with applications to cosmology	singh, ha, lanusse, boehm, liu & yu	🔎🌀🌌	iclr workshop (spotlight)
'20	Interpretations are useful: penalizing explanations to align neural networks with prior knowledge	rieger, singh, murdoch & yu	🔎🌀	icml
'19	Hierarchical interpretations for neural network predictions	Singh, Murdoch, & Yu	🔍🌀	ICLR
'19	interpretable machine learning: definitions, methods, and applications	Murdoch, Singh, et al.	🔍🌳🌀	pnas
'19	disentangled attribution curves for interpreting random forests and boosted trees	devlin, singh, murdoch & yu	🔍🌳	arxiv
'18	large scale image segmentation with structured loss based deep learning for connectome reconstruction	Funke, Tschopp, et al.	🧠🌀	TPAMI
'18	linearization of excitatory synaptic integration at no extra cost	Morel, Singh, & Levy	🧠	J Comp Neuro
'17	a consensus layer V pyramidal neuron can sustain interpulse-interval coding	Singh & Levy	🧠	Plos One
'17	a constrained, weighted-l1 minimization approach for joint discovery of heterogeneous neural connectivity graphs	Singh, Wang, & Qi	🧠	neurips Workshop

Research

resources + posts

paper overviews

research posts

slides

ai

cs

math

ml

neuro

stat

ml projects

misc

experience