影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
33.3/100
前 20.8%
全站排名 #13,383
发表论文7 篇
平均评分
年均产出3.5 篇/年
Sonali Parbhoo
研究方向
Causal Inference · Reinforcement Learning/Decision Making in Uncertainty · Interpretable ML · Uncertainty Estimation
19
The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM Objectives
ICLR 2026Poster
通讯15
Reward Shaping Control Variates for Off-Policy Evaluation Under Sparse Rewards
ICLR 2026Desk Rejected
一作10
Learning from Failures: Understanding LLM Alignment through Failure-Aware Inverse RL
ICLR 2026Desk Rejected
通讯18
Causal Bayesian Optimization with Unknown Causal Graphs
ICLR 2025Rejected
通讯16
Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse Reinforcement Learning
COLM 2025Poster
通讯26
Concept-driven Off Policy Evaluation
ICLR 2025Rejected
三作21
Controlling Information Leakage in Concept Bottleneck Models with Trees
ICLR 2025Withdrawn
二作