collaborators

8 papers

cs.LG2026

Flexible Routing via Uncertainty Decomposition

Charlotte Peale, Siddartha Devic, Parikshit Gopalan +2

A key strategy for balancing performance and cost in modern machine learning systems is to dynamically route queries to either a low-cost model or a more expensive oracle (such as…

cs.LG2026

Are LLM Decisions Faithful to Verbal Confidence?

Jiawei Wang, Yanfei Zhou, Siddartha Devic +1

Large Language Models (LLMs) can produce surprisingly sophisticated estimates of their own uncertainty. However, it remains unclear to what extent this expressed confidence is tied…

cs.LG2025

Proper Learnability and the Role of Unlabeled Data

Julian Asilis, Siddartha Devic, Shaddin Dughmi +2

Proper learning refers to the setting in which learners must emit predictors in the underlying hypothesis class , and often leads to learners with simple algorithmic forms (e.g.…

cs.CY2025

An External Fairness Evaluation of LinkedIn Talent Search

Tina Behzad, Siddartha Devic, Vatsal Sharan +2

We conduct an independent, third-party audit for bias of LinkedIn's Talent Search ranking system, focusing on potential ranking bias across two attributes: gender and race. To do s…

cs.AI2025

Trace Length is a Simple Uncertainty Signal in Reasoning Models

Siddartha Devic, Charlotte Peale, Arwen Bradley +3

Uncertainty quantification for LLMs is a key research direction towards addressing hallucination and other issues that limit their reliable deployment. In this work, we show that r…

cs.LG2025

Auditability and the Landscape of Distance to Multicalibration

Nathan Derhake, Siddartha Devic, Dutch Hansen +2

Calibration is a critical property for establishing the trustworthiness of predictors that provide uncertainty estimates. Multicalibration is a strengthening of calibration which r…