Related papers: Tool Unlearning for Tool-Augmented LLMs

Generative models such as Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) trained on massive datasets can lead them to memorize and inadvertently reveal sensitive information, raising ethical and privacy concerns.…

Machine unlearning is an emerging technology that has come to attract widespread attention. A number of factors, including regulations and laws, privacy, and usability concerns, have resulted in this need to allow a trained model to forget…

Large language models (LLMs) have demonstrated exceptional reasoning capabilities, enabling them to solve various complex problems. Recently, this ability has been applied to the paradigm of tool learning. Tool learning involves providing…

Multi-Task Learning (MTL) is widely-accepted in Natural Language Processing as a standard technique for learning multiple related tasks in one model. Training an MTL model requires having the training data for all tasks available at the…

Large Language Models (LLMs) are known to be vulnerable to jailbreak attacks. An important observation is that, while different types of jailbreak attacks can generate significantly different queries, they mostly result in similar responses…

Instruction-tuned large language models (LLMs) excel at many tasks but often fail to use external tools due to complicated and unfamiliar syntax constraints. While extensive fine-tuning and prompting can mitigate the issue, these approaches…

Pretrained knowledge memorized in LLMs raises critical concerns over safety and privacy, which has motivated LLM Unlearning as a technique for selectively removing the influences of undesirable knowledge. Existing approaches, rooted in…

Fine-tuning-based unlearning methods prevail for preventing targeted harmful, sensitive, or copyrighted information within large language models while preserving overall capabilities. However, the true effectiveness of these methods is…

Tool learning is widely acknowledged as a foundational approach or deploying large language models (LLMs) in real-world scenarios. While current research primarily emphasizes leveraging tools to augment LLMs, it frequently neglects emerging…

While many have shown how Large Language Models (LLMs) can be applied to a diverse set of tasks, the critical issues of data contamination and memorization are often glossed over. In this work, we address this concern for tabular data.…

The right to be forgotten requires the removal or "unlearning" of a user's data from machine learning models. However, in the context of Machine Learning as a Service (MLaaS), retraining a model from scratch to fulfill the unlearning…

While current large language models (LLMs) perform well on many knowledge-related tasks, they are limited by relying on their parameters as an implicit storage mechanism. As a result, they struggle with memorizing rare events and with…

The inability to filter out in advance all potentially problematic data from the pre-training of large language models has given rise to the need for methods for unlearning specific pieces of knowledge after training. Existing techniques…

Machine Unlearning (MU) aims to remove target training data from a trained model so that the removed data no longer influences the model's behavior, fulfilling "right to be forgotten" obligations under data privacy laws. Yet, we observe…

Machine unlearning aims to solve the problem of removing the influence of selected training examples from a learned model. Despite the increasing attention to this problem, it remains an open research question how to evaluate unlearning in…

Machine learning models are vulnerable to adversarial attacks, including attacks that leak information about the model's training data. There has recently been an increase in interest about how to best address privacy concerns, especially…

Machine unlearning has garnered significant attention due to its ability to selectively erase knowledge obtained from specific training data samples in an already trained machine learning model. This capability enables data holders to…

The recent trend of using Large Language Models (LLMs) as tool agents in real-world applications underscores the necessity for comprehensive evaluations of their capabilities, particularly in complex scenarios involving planning, creating,…

Despite advances in Preference Alignment (PA) for Large Language Models (LLMs), mainstream methods like Reinforcement Learning with Human Feedback (RLHF) face notable challenges. These approaches require high-quality datasets of positive…

High-quality, error-free datasets are a key ingredient in building reliable, accurate, and unbiased machine learning (ML) models. However, real world datasets often suffer from errors due to sensor malfunctions, data entry mistakes, or…