1 citations · 1 across the 5 of their papers we have counts for
6 papers
Retrieval Sensitivity to Identity Signals in Queries
Andrew Tang, Nicholas Deas, Kathleen McKeown +1
Dense retrievers decide which documents reach users and the language models that use them, yet they are typically evaluated with neutral queries. We ask whether the identity signal…
Bayesian Wind Tunnels for Model Selection
Siddhartha R Dalal, Vishal Misra, Abhay Parekh
Prior work has shown that transformers can perform exact Bayesian filtering within a fixed hypothesis class. Can they also perform Bayesian model selection -- identifying the corre…
Geometric Scaling of Bayesian Inference in LLMs
Naman Agarwal, Siddhartha R. Dalal, Vishal Misra
Recent work has shown that small transformers trained in controlled "wind-tunnel'' settings can implement exact Bayesian inference, and that their training dynamics produce a geome…
Gradient Dynamics of Attention: How Cross-Entropy Sculpts Bayesian Manifolds
Naman Agarwal, Siddhartha R. Dalal, Vishal Misra
Transformers empirically perform precise probabilistic reasoning in carefully constructed ``Bayesian wind tunnels'' and in large-scale language models, yet the mechanisms by which…
The Bayesian Geometry of Transformer Attention
Naman Agarwal, Siddhartha R. Dalal, Vishal Misra
Transformers often appear to perform Bayesian reasoning in context, but verifying this rigorously has been impossible: natural data lack analytic posteriors, and large models confl…
Beyond the Black Box: A Statistical Model for LLM Reasoning and Inference
Siddhartha Dalal, Vishal Misra
This paper introduces a novel Bayesian learning model to explain the behavior of Large Language Models (LLMs), focusing on their core optimization metric of next token prediction.…