10 papers
Statistical attribute alignment for black-box generative AI via output post-processing
Kevin Jiang, Morgane Austern, Edgar Dobriban +1
Generative AI systems are increasingly used, but aligning their outputs with user requirements poses a continuing challenge. Here, we aim to ensure that the distribution of an attr…
LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection
Lei Zhao, Abhay Bhaskar, Edgar Dobriban
AI agents such as OpenClaw are increasingly deployed in local workflows with access to external tools. This creates indirect prompt-injection (IPI) risk: an agent may execute harmf…
Where to Spend Rollouts: Hit-Utility Optimal Rollout Allocation for Group-Based RLVR
Tao Wang, Shuo Li, Yan Sun +2
Reinforcement learning with verifiable rewards (RLVR) has emerged as a central paradigm for improving the reasoning capabilities of large language models. Group-based policy optimi…
Risk-Controlled Post-Processing of Decision Policies
Sunay Joshi, Tao Wang, Hamed Hassani +1
Predictive models are often deployed through existing decision policies that stakeholders are reluctant to change unless a risk constraint requires intervention. We study risk-cont…
Synthetic-Powered Multiple Testing with FDR Control
Yonghoon Lee, Meshi Bashari, Edgar Dobriban +1
Multiple hypothesis testing with false discovery rate (FDR) control is a fundamental problem in statistical inference, with broad applications in genomics, drug screening, and outl…
Optimal Decision-Making Based on Prediction Sets
Tao Wang, Edgar Dobriban
Prediction sets can wrap around any ML model to cover unknown test outcomes with a guaranteed probability. Yet, it remains unclear how to use them optimally for downstream decision…
Online Conformal Prediction via Universal Portfolio Algorithms
Tuo Liu, Edgar Dobriban, Francesco Orabona
Online conformal prediction (OCP) seeks prediction intervals that achieve long-run coverage for arbitrary (possibly adversarial) data streams, while remaining as informative…
Statistical Early Stopping for Reasoning Models
Yangxinyu Xie, Tao Wang, Soham Mallick +5
While LLMs have seen substantial improvement in reasoning capabilities, they also sometimes overthink, generating unnecessary reasoning steps, particularly under uncertainty, given…
Solving a Research Problem in Mathematical Statistics with AI Assistance
Edgar Dobriban
Over the last few months, AI models including large language models have improved greatly. There are now several documented examples where they have helped professional mathematica…
Efficiently Learning Branching Networks for Multitask Algorithmic Reasoning
Dongyue Li, Zhenshuo Zhang, Minxuan Duan +2
Algorithmic reasoning -- the ability to perform step-by-step logical inference -- is a synthetic benchmark for evaluating multi-step reasoning abilities, designed for graph neural…