Explanipedia

RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning Evaluation Open

Xinnuo Xu, Rebekah L. Lawrence, Kanak Dubey, A. K. Pandey, Risa Ueno , et al. · 2025

Recent Large Language Models (LLMs) have reported high accuracy on reasoning benchmarks. However, it is still unclear whether the observed results arise from true reasoning or from statistical recall of the training set. Inspired by the la…

Reasoning Elicitation in Language Models via Counterfactual Feedback Open

Alihan Hüyük, Xinnuo Xu, Jacqueline Maasch, Aditya V. Nori, Javier González · 2024

Despite the increasing effectiveness of language models, their reasoning capabilities remain underdeveloped. In particular, causal reasoning through counterfactual question answering is lacking. This work aims to bridge this gap. We first …

Does Reasoning Emerge? Examining the Probabilities of Causation in Large Language Models Open

Javier González, Aditya V. Nori · 2024

Recent advances in AI have been significantly driven by the capabilities of large language models (LLMs) to solve complex problems in ways that resemble human thinking. However, there is an ongoing debate about the extent to which LLMs are…

Cautionary Tales on Synthetic Controls in Survival Analyses Open

Alicia Curth, Hoifung Poon, Aditya V. Nori, Javier González · 2023

Synthetic control (SC) methods have gained rapid popularity in economics recently, where they have been applied in the context of inferring the effects of treatments on standard continuous outcomes assuming linear input-output relations. I…

Beyond Words: A Mathematical Framework for Interpreting Large Language Models Open

Javier González, Aditya V. Nori · 2023

Large language models (LLMs) are powerful AI tools that can generate and comprehend natural language text and other complex information. However, the field lacks a mathematical framework to systematically describe, compare and improve LLMs…

Exploring the Boundaries of GPT-4 in Radiology Open

Qianchu Liu, Stephanie L. Hyland, Shruthi Bannur, Kenza Bouzid, Daniel C. Castro , et al. · 2023

The recent success of general-domain large language models (LLMs) has significantly changed the natural language processing paradigm towards a unified foundation model across domains and applications. In this paper, we focus on assessing t…

Active label cleaning: Improving dataset quality under resource constraints. Open

Mélanie Bernhardt, Daniel C. Castro, Ryutaro Tanno, Anton Schwaighofer, Kerem Can Tezcan , et al. · 2021

Imperfections in data annotation, known as label noise, are detrimental to the training of machine learning models and have an often-overlooked confounding effect on the assessment of model performance. Nevertheless, employing experts to r…

Hierarchical Analysis of Visual COVID-19 Features from Chest Radiographs Open

Shruthi Bannur, Ozan Oktay, Mélanie Bernhardt, Anton Schwaighofer, R. Jena , et al. · 2021

Chest radiography has been a recommended procedure for patient triaging and resource management in intensive care units (ICUs) throughout the COVID-19 pandemic. The machine learning efforts to augment this workflow have been long challenge…

Secure Medical Image Analysis with CrypTFlow Open

Javier Alvarez-Valle, Pratik Bhatu, Nishanth Chandran, Divya Gupta, Aditya V. Nori , et al. · 2020

We present CRYPTFLOW, a system that converts TensorFlow inference code into Secure Multi-party Computation (MPC) protocols at the push of a button. To do this, we build two components. Our first component is an end-to-end compiler from Ten…

Overfitting in Synthesis: Theory and Practice (Extended Version) Open

Saswat Padhi, Todd Millstein, Aditya V. Nori, Rahul Sharma · 2019

In syntax-guided synthesis (SyGuS), a synthesizer's goal is to automatically generate a program belonging to a grammar of possible implementations that meets a logical specification. We investigate a common limitation across state-of-the-a…

Robustness of Neural Networks: A Probabilistic and Practical Approach Open

Ravi Mangal, Aditya V. Nori, Alessandro Orso · 2019

Neural networks are becoming increasingly prevalent in software, and it is therefore important to be able to verify their behavior. Because verifying the correctness of neural networks is extremely challenging, it is common to focus on the…

Adaptive Neural Trees Open

Ryutaro Tanno, Kai Arulkumaran, Daniel C. Alexander, Antonio Criminisi, Aditya V. Nori · 2018

Deep neural networks and decision trees operate on largely separate paradigms; typically, the former performs representation learning with pre-specified architectures, while the latter is characterised by learning hierarchies over pre-spec…

Specification Inference and Invariant Generation: A Machine Learning Perspective Open

Aditya V. Nori · 2018

Computing good specification and invariants is key to effective and efficient program verification. In this talk, I will describe our experiences in using machine learning techniques (Bayesian inference, SVMs) for computing specifications …

FairSquare: probabilistic verification of program fairness Open

Aws Albarghouthi, Loris D’Antoni, Samuel Drews, Aditya V. Nori · 2017

With the range and sensitivity of algorithmic decisions expanding at a break-neck speed, it is imperative that we aggressively investigate fairness and bias in decision-making programs. First, we show that a number of recently proposed for…

Quantifying Program Bias Open

Aws Albarghouthi, Loris D’Antoni, Samuel Drews, Aditya V. Nori · 2017

With the range and sensitivity of algorithmic decisions expanding at a break-neck speed, it is imperative that we aggressively investigate whether programs are biased. We propose a novel probabilistic program analysis technique and apply i…

Fairness as a Program Property Open

Aws Albarghouthi, Loris D’Antoni, Samuel Drews, Aditya V. Nori · 2016

We explore the following question: Is a decision-making program fair, for some useful definition of fairness? First, we describe how several algorithmic fairness questions can be phrased as program verification problems. Second, we discuss…

Debugging Machine Learning Tasks Open

Aleksandar Chakarov, Aditya V. Nori, Sriram K. Rajamani, Shayak Sen, Deepak Vijaykeerthy · 2016

Unlike traditional programs (such as operating systems or word processors) which have large amounts of code, machine learning tasks use programs with relatively small amounts of code (written in machine learning libraries), but voluminous …

Query-guided maximum satisfiability Open

Xin Zhang, Ravi Mangal, Aditya V. Nori, Mayur Naik · 2016

We propose a new optimization problem "Q-MaxSAT", an extension of the well-known Maximum Satisfiability or MaxSAT problem. In contrast to MaxSAT, which aims to find an assignment to all variables in the formula, Q-MaxSAT computes an assign…

A Provably Correct Sampler for Probabilistic Programs Open

Chung-Kil Hur, Aditya V. Nori, Sriram K. Rajamani, Selva Samuel · 2015

We consider the problem of inferring the implicit distribution specified by a probabilistic program. A popular inference technique for probabilistic programs called Markov Chain Monte Carlo or MCMC sampling involves running the program rep…

Aditya V. Nori YOU? Author Swipe