Search for: All records

As large language models (LLMs) are increasingly deployed in the real world, the ability to ``unlearn'', or remove specific pieces of knowledge post hoc, has become essential for a variety of reasons ranging from privacy regulations to correcting outdated or harmful content. Prior work has proposed unlearning benchmarks and algorithms, and has typically assumed that the training process and the target model are fixed. In this work, we empirically investigate how learning-time choices in knowledge encoding impact the effectiveness of unlearning factual knowledge. Our experiments reveal two key findings: (1) learning with paraphrased descriptions improves unlearning performance and (2) unlearning individual piece of knowledge from a chunk of text is challenging. Our results suggest that learning-time knowledge encoding may play a central role in enabling reliable post-hoc unlearning. 

Machine unlearning techniques aim to mitigate unintended memorization in large language models (LLMs). However, existing approaches predominantly focus on the explicit removal of isolated facts, often overlooking latent inferential dependencies and the non-deterministic nature of knowledge within LLMs. Consequently, facts presumed forgotten may persist implicitly through correlated information. To address these challenges, we propose a knowledge unlearning evaluation framework that more accurately captures the implicit structure of real-world knowledge by representing relevant factual contexts as knowledge graphs with associated confidence scores. We further develop an inference-based evaluation protocol leveraging powerful LLMs as judges; these judges reason over the extracted knowledge subgraph to determine unlearning success. Our LLM judges utilize carefully designed prompts and are calibrated against human evaluations to ensure their trustworthiness and stability. Extensive experiments on our newly constructed benchmark demonstrate that our framework provides a more realistic and rigorous assessment of unlearning performance. Moreover, our findings reveal that current evaluation strategies tend to overestimate unlearning effectiveness. Our code is publicly available at https://github.com/Graph-COM/Knowledge_Unlearning.git. 

We study the problem of online multi-task learning where the tasks are performed within similar but not necessarily identical multi-armed bandit environments. In particular, we study how a learner can improve its overall performance across multiple related tasks through robust transfer of knowledge. While an upper confidence bound (UCB)-based algorithm has recently been shown to achieve nearly-optimal performance guarantees in a setting where all tasks are solved concurrently, it remains unclear whether Thompson sampling (TS) algorithms, which have superior empirical performance in general, share similar theoretical properties. In this work, we present a TS-type algorithm for a more general online multi-task learning protocol, which extends the concurrent setting. We provide its frequentist analysis and prove that it is also nearly-optimal using a novel concentration inequality for multi-task data aggregation at random stopping times. Finally, we evaluate the algorithm on synthetic data and show that the TS-type algorithm enjoys superior empirical performance in comparison with the UCB-based algorithm and a baseline algorithm that performs TS for each individual task without transfer. 

In many real-world applications, multiple agents seek to learn how to perform highly related yet slightly different tasks in an online bandit learning protocol. We formulate this problem as the ϵ-multi-player multi-armed bandit problem, in which a set of players concurrently interact with a set of arms, and for each arm, the reward distributions for all players are similar but not necessarily identical. We develop an upper confidence bound-based algorithm, RobustAgg(ϵ), that adaptively aggregates rewards collected by different players. In the setting where an upper bound on the pairwise dissimilarities of reward distributions between players is known, we achieve instance-dependent regret guarantees that depend on the amenability of information sharing across players. We complement these upper bounds with nearly matching lower bounds. In the setting where pairwise dissimilarities are unknown, we provide a lower bound, as well as an algorithm that trades off minimax regret guarantees for adaptivity to unknown similarity structure. 

Detecting overfitting in generative models is an important challenge in machine learning. In this work, we formalize a form of overfitting that we call data-copying – where the gener- ative model memorizes and outputs training samples or small variations thereof. We pro- vide a three sample non-parametric test for detecting data-copying that uses the training set, a separate sample from the target dis- tribution, and a generated sample from the model, and study the performance of our test on several canonical models and datasets. 

Normalizing flows have received a great deal of recent attention as they allow flexible gen- erative modeling as well as easy likelihood computation. While a wide variety of flow models have been proposed, there is little formal understanding of the representation power of these models. In this work, we study some basic normalizing flows and rigorously establish bounds on their expressive power. Our results indicate that while these flows are highly expressive in one dimension, in higher dimensions their representation power may be limited, especially when the flows have moderate depth. 

A growing body of research has shown that many classifiers are susceptible to adversarial exam- ples – small strategic modifications to test inputs that lead to misclassification. In this work, we study general non-parametric methods, with a view towards understanding when they are ro- bust to these modifications. We establish general conditions under which non-parametric methods are r-consistent – in the sense that they converge to optimally robust and accurate classifiers in the large sample limit. Concretely, our results show that when data is well-separated, nearest neighbors and kernel clas- sifiers are r-consistent, while histograms are not. For general data distributions, we prove that pre- processing by Adversarial Pruning (Yang et al., 2019) – that makes data well-separated – followed by nearest neighbors or kernel classifiers also leads to r-consistency. 

Detecting overfitting in generative models is an important challenge in machine learning. In this work, we formalize a form of overfitting that we call data-copying – where the gener- ative model memorizes and outputs training samples or small variations thereof. We pro- vide a three sample test for detecting data- copying that uses the training set, a separate sample from the target distribution, and a generated sample from the model, and study the performance of our test on several canon- ical models and datasets.