Gintare Karolina Dziugaite

Unlearning in- vs. out-of-distribution data in LLMs under gradient-based method

Teodora Baluta

Pascal Lamblin

Daniel Tarlow

Fabian Pedregosa

Machine unlearning aims to solve the problem of removing the influence of selected training examples from a learned model. Despite the incre… (voir plus)asing attention to this problem, it remains an open research question how to evaluate unlearning in large language models (LLMs), and what are the critical properties of the data to be unlearned that affect the quality and efficiency of unlearning. This work formalizes a metric to evaluate unlearning quality in generative models, and uses it to assess the trade-offs between unlearning quality and performance. We demonstrate that unlearning out-of-distribution examples requires more unlearning steps but overall presents a better trade-off overall. For in-distribution examples, however, we observe a rapid decay in performance as unlearning progresses. We further evaluate how example's memorization and difficulty affect unlearning under a classical gradient ascent-based approach.

2024-11-07

ArXiv (prépublication)

Unlearning in- vs. out-of-distribution data in LLMs under gradient-based method

Teodora Baluta

Pascal Lamblin

Daniel Tarlow

Fabian Pedregosa

Machine unlearning aims to solve the problem of removing the influence of selected training examples from a learned model. Despite the incre… (voir plus)asing attention to this problem, it remains an open research question how to evaluate unlearning in large language models (LLMs), and what are the critical properties of the data to be unlearned that affect the quality and efficiency of unlearning. This work formalizes a metric to evaluate unlearning quality in generative models, and uses it to assess the trade-offs between unlearning quality and performance. We demonstrate that unlearning out-of-distribution examples requires more unlearning steps but overall presents a better trade-off overall. For in-distribution examples, however, we observe a rapid decay in performance as unlearning progresses. We further evaluate how example's memorization and difficulty affect unlearning under a classical gradient ascent-based approach.

2024-11-07

ArXiv (prépublication)

The Non-Local Model Merging Problem: Permutation Symmetries and Variance Collapse

Ekansh Sharma

Daniel M. Roy

2024-10-16

ArXiv (prépublication)

The Non-Local Model Merging Problem: Permutation Symmetries and Variance Collapse

Ekansh Sharma

Daniel M. Roy

Model merging aims to efficiently combine the weights of multiple expert models, each trained on a specific task, into a single multi-task m… (voir plus)odel, with strong performance across all tasks. When applied to all but the last layer of weights, existing methods -- such as Task Arithmetic, TIES-merging, and TALL mask merging -- work well to combine expert models obtained by fine-tuning a common foundation model, operating within a"local"neighborhood of the foundation model. This work explores the more challenging scenario of"non-local"merging, which we find arises when an expert model changes significantly during pretraining or where the expert models do not even share a common foundation model. We observe that standard merging techniques often fail to generalize effectively in this non-local setting, even when accounting for permutation symmetries using standard techniques. We identify that this failure is, in part, due to"variance collapse", a phenomenon identified also in the setting of linear mode connectivity by Jordan et al. (2023). To address this, we propose a multi-task technique to re-scale and shift the output activations of the merged model for each task, aligning its output statistics with those of the corresponding task-specific expert models. Our experiments demonstrate that this correction significantly improves the performance of various model merging approaches in non-local settings, providing a strong baseline for future research on this problem.

2024-10-16

ArXiv (prépublication)

Unlearning in- vs. out-of-distribution data in LLMs under gradient-based methods

Teodora Baluta

Pascal Lamblin

Daniel Tarlow

Fabian Pedregosa

Machine unlearning aims to solve the problem of removing the influence of selected training examples from a learned model. Despite the incre… (voir plus)asing attention to this problem, it remains an open research question how to evaluate unlearning in large language models (LLMs), and what are the critical properties of the data to be unlearned that affect the quality and efficiency of unlearning. This work formalizes a metric to evaluate unlearning quality in generative models, and uses it to assess the trade-offs between unlearning quality and performance. We demonstrate that unlearning out-of-distribution examples requires more unlearning steps but overall presents a better trade-off overall. For in-distribution examples, however, we observe a rapid decay in performance as unlearning progresses. We further evaluate how example's memorization and difficulty affect unlearning under a classical gradient ascent-based approach.

2024-10-12

NeurIPS.cc/2024/Workshop/SafeGenAi (poster)

Evaluating Interventional Reasoning Capabilities of Large Language Models

Tejas Kasetty

Divyat Mahajan

Alexandre Drouin

Dhanya Sridhar

Numerous decision-making tasks require estimating causal effects under interventions on different parts of a system. As practitioners consid… (voir plus)er using large language models (LLMs) to automate decisions, studying their causal reasoning capabilities becomes crucial. A recent line of work evaluates LLMs ability to retrieve commonsense causal facts, but these evaluations do not sufficiently assess how LLMs reason about interventions. Motivated by the role that interventions play in causal inference, in this paper, we conduct empirical analyses to evaluate whether LLMs can accurately update their knowledge of a data-generating process in response to an intervention. We create benchmarks that span diverse causal graphs (e.g., confounding, mediation) and variable types, and enable a study of intervention-based reasoning. These benchmarks allow us to isolate the ability of LLMs to accurately predict changes resulting from their ability to memorize facts or find other shortcuts. Our analysis on four LLMs highlights that while GPT- 4 models show promising accuracy at predicting the intervention effects, they remain sensitive to distracting factors in the prompts.

2024-10-10

NeurIPS.cc/2024/Workshop/CALM (poster)

Robust Knowledge Unlearning via Mechanistic Localizations

Phillip Huang Guo

Aaquib Syed

Abhay Sheshadri

Aidan Ewart

2024-06-28

ICML.cc/2024/Workshop/NextGenAISafety (poster)

Mixture of Experts in a Mixture of RL settings

Timon Willi

Johan Samir Obando Ceron

Jakob Nicolaus Foerster

Pablo Samuel Castro

Mixtures of Experts (MoEs) have gained prominence in (self-)supervised learning due to their enhanced inference efficiency, adaptability to … (voir plus)distributed training, and modularity. Previous research has illustrated that MoEs can significantly boost Deep Reinforcement Learning (DRL) performance by expanding the network's parameter count while reducing dormant neurons, thereby enhancing the model's learning capacity and ability to deal with non-stationarity. In this work, we shed more light on MoEs' ability to deal with non-stationarity and investigate MoEs in DRL settings with"amplified"non-stationarity via multi-task training, providing further evidence that MoEs improve learning capacity. In contrast to previous work, our multi-task results allow us to better understand the underlying causes for the beneficial effect of MoE in DRL training, the impact of the various MoE components, and insights into how best to incorporate them in actor-critic-based DRL networks. Finally, we also confirm results from previous work.

2024-06-26

ArXiv (prépublication)

Robust Unlearning via Mechanistic Localizations

Phillip Huang Guo

Aaquib Syed

Abhay Sheshadri

Aidan Ewart

Methods for machine unlearning in large language models seek to remove undesirable knowledge or capabilities without compromising general la… (voir plus)nguage modeling performance. This work investigates the use of mechanistic interpretability to improve the precision and effectiveness of unlearning. We demonstrate that localizing unlearning to components with particular mechanisms in factual recall leads to more robust unlearning across different input/output formats, relearning, and latent knowledge, and reduces unintended side effects compared to nonlocalized unlearning. Additionally, we analyze the strengths and weaknesses of different automated (rather than manual) interpretability methods for guiding unlearning, finding that their corresponding unlearned models require smaller edit sizes to achieve unlearning but are much less robust.

2024-06-24

ICML.cc/2024/Workshop/MI (spotlight)

Robust Unlearning via Mechanistic Localizations

Phillip Huang Guo

Aaquib Syed

Abhay Sheshadri

Aidan Ewart

Methods for machine unlearning in large language models seek to remove undesirable knowledge or capabilities without compromising general la… (voir plus)nguage modeling performance. This work investigates the use of mechanistic interpretability to improve the precision and effectiveness of unlearning. We demonstrate that localizing unlearning to components with particular mechanisms in factual recall leads to more robust unlearning across different input/output formats, relearning, and latent knowledge, and reduces unintended side effects compared to nonlocalized unlearning. Additionally, we analyze the strengths and weaknesses of different automated (rather than manual) interpretability methods for guiding unlearning, finding that their corresponding unlearned models require smaller edit sizes to achieve unlearning but are much less robust.

2024-06-24

ICML.cc/2024/Workshop/MI (spotlight)

Linear Weight Interpolation Leads to Transient Performance Gains

Gaurav Iyer

David Rolnick

2024-06-16

ICML.cc/2024/Workshop/HiLD (poster)