15 papers
When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs
Omatharv Bharat Vaidya, Connor Thomas Jerzak, Zayne Rea Sprague +2
Self-consistency assumes the most frequent answer among sampled reasoning traces is the most reliable, but this can fail in causal reasoning: samples often repeat the same confound…
Platonic Representations for Poverty Mapping: Unified Vision-Language Codes or Agent-Induced Novelty?
Satiyabooshan Murugaboopathy, Connor T. Jerzak, Adel Daoud
We investigate whether socioeconomic indicators, like household wealth, leave recoverable informational imprints in both satellite imagery (capturing features like buildings and ro…
Temporal Dynamics of Development Aid in Africa: Evidence from a Staggered Difference-in-Differences Study of China and World Bank Projects
Mattias Antar, Adel Daoud, Connor T. Jerzak
Subnational studies of aid effectiveness often rely on repeated cross-sections or nighttime lights, making it difficult to separate local treatment effects from baseline difference…
MiniMax Learning of Interpretable Factored Stochastic Policies from Conjoint Data, with Uncertainty Quantification
Connor T. Jerzak, Priyanshi Chandra, Rishi Hazra
We study offline policy optimization over exponentially large factorial action spaces from randomized preference data, showing how conjoint experiments can estimate interpretable s…
Queryable LoRA: Instruction-Regularized Routing Over Shared Low-Rank Update Atoms
Omatharv Bharat Vaidya, Connor T. Jerzak, Nhat Ho +1
We present a data-adaptive method for parameter-efficient fine-tuning of large neural networks. Standard low-rank adaptation methods improve efficiency by restricting each layer up…
Multiplication in Multimodal LLMs: Computation with Text, Image, and Audio Inputs
Samuel G. Balter, Ethan Jerzak, Connor T. Jerzak
Multimodal LLMs can accurately perceive numerical content across modalities yet fail to perform exact multi-digit multiplication when the identical underlying arithmetic problem is…