Related papers: Efficiently Verifiable Proofs of Data Attribution
Trustworthy machine learning is driving a large number of ML community works in order to improve ML acceptance and adoption. The main aspect of trustworthy machine learning are the followings: fairness, uncertainty, robustness,…
Trustworthy verifiers are essential for the success of reinforcement learning with verifiable reward (RLVR), which is the core methodology behind various large reasoning models such as DeepSeek-R1. In complex domains like mathematical…
Building recommendation algorithms is one of the most challenging tasks in Machine Learning. Although most of the recommendation systems are built on explicit feedback available from the users in terms of rating or text, a majority of the…
Large-scale AI models such as GPT-4 have accelerated the deployment of artificial intelligence across critical domains including law, healthcare, and finance, raising urgent questions about trust and transparency. This study investigates…
We present a novel interactive learning protocol that enables training request-fulfilling agents by verbally describing their activities. Unlike imitation learning (IL), our protocol allows the teaching agent to provide feedback in a…
We present a new method for statistical verification of quantitative properties over a partially unknown system with actions, utilising a parameterised model (in this work, a parametric Markov decision process) and data collected from…
Safe artificial intelligence for perception tasks remains a major challenge, partly due to the lack of data with high-quality labels. Annotations themselves are subject to aleatoric and epistemic uncertainty, which is typically ignored…
Active learning aims to identify the most informative data from an unlabeled data pool that enables a model to reach the desired accuracy rapidly. This benefits especially deep neural networks which generally require a huge number of…
Machine learning models that first learn a representation of a domain in terms of human-understandable concepts, then use it to make predictions, have been proposed to facilitate interpretation and interaction with models trained on…
Training data attribution (TDA) methods aim to measure how training data impacts a model's predictions. While gradient-based attribution methods, such as influence functions, offer theoretical grounding, their computational costs make them…
Prediction credibility measures, in the form of confidence intervals or probability distributions, are fundamental in statistics and machine learning to characterize model robustness, detect out-of-distribution samples (outliers), and…
How can we trust the correctness of a learned model on a particular input of interest? Model accuracy is typically measured on average over a distribution of inputs, giving no guarantee for any fixed input. This paper proposes a…
We study the problem of learning from multiple untrusted data sources, a scenario of increasing practical relevance given the recent emergence of crowdsourcing and collaborative learning paradigms. Specifically, we analyze the situation in…
Mutual information (MI) is a fundamental measure of statistical dependence between two variables, yet accurate estimation from finite data remains notoriously difficult. No estimator is universally reliable, and common approaches fail in…
Increasingly, artificial intelligence (AI) and machine learning (ML) are used in eScience applications [9]. While these approaches have great potential, the literature has shown that ML-based approaches frequently suffer from results that…
Distributed in-network programs are increasingly deployed in data centers for their performance benefits, but shifting application logic to switches also enlarges the failure domain. Ensuring their correctness before deployment is thus…
Explainable models in Artificial Intelligence are often employed to ensure transparency and accountability of AI systems. The fidelity of the explanations are dependent upon the algorithms used as well as on the fidelity of the data. Many…
Test-time compute scaling allocates inference computation uniformly, uses fixed sampling strategies, and applies verification only for reranking. In contrast, we propose a verifier-guided adaptive framework treating reasoning as iterative…
Technology advances in areas such as sensors, IoT, and robotics, enable new collaborative applications (e.g., autonomous devices). A primary requirement for such collaborations is to have a secure system which enables information sharing…
With recent progress on experimental quantum information processing, an important question has arisen as to whether it is possible to verify arbitrary computation performed on a quantum processor. A number of protocols have been proposed to…