Related papers: Demystifying Language Model Forgetting with Low-ra…

Fine-tuning a language model often results in a degradation of its existing performance on other tasks, due to a shift in the model parameters; this phenomenon is often referred to as (catastrophic) forgetting. We are interested in…

Large Language Models (LLMs) deployed in real-world settings increasingly face the need to unlearn sensitive, outdated, or proprietary information. Existing unlearning methods typically formulate forgetting and retention as a regularized…

Unlearning methods have the potential to improve the privacy and safety of large language models (LLMs) by removing sensitive or harmful information post hoc. The LLM unlearning research community has increasingly turned toward empirical…

While there has been much recent work studying how linguistic information is encoded in pre-trained sentence representations, comparatively little is understood about how these models change when adapted to solve downstream tasks. Using a…

Large language models (LLM) trained using the next-token-prediction objective, such as GPT3 and PaLM, have revolutionized natural language processing in recent years by showing impressive zero-shot and few-shot capabilities across a wide…

Catastrophic forgetting is a pervasive issue for pre-trained language models (PLMs) during continual learning, where models lose previously acquired knowledge when sequentially trained on a series of tasks. The model's ability to retain old…

The leakage of benchmark data into the training data has emerged as a significant challenge for evaluating the capabilities of large language models (LLMs). In this work, we challenge the common assumption that small-scale contamination…

A widespread strategy to obtain a language model that performs well on a target domain is to finetune a pretrained model to perform unsupervised next-token prediction on data from that target domain. Finetuning presents two challenges: (i)…

Training data plays a pivotal role in AI models. Large language models (LLMs) are trained with massive amounts of documents, and their parameters hold document-related contents. Recently, several studies identified content-specific…

Scientific reasoning rarely stops at what is directly observable; it often requires uncovering hidden structure from data. From estimating reaction constants in chemistry to inferring demand elasticities in economics, this latent structure…

Large language models (LLMs) have demonstrated remarkable potential across numerous applications and have shown an emergent ability to tackle complex reasoning tasks, such as mathematical computations. However, even for the simplest…

Training and fine-tuning large language models (LLMs) come with challenges related to memory and computational requirements due to the increasing size of the model weights and the optimizer states. Various techniques have been developed to…

Unlearning in large language models (LLMs) aims to remove specified data, but its efficacy is typically assessed with task-level metrics like accuracy and perplexity. We show that these metrics can be misleading, as models can appear to…

Recently, decomposing complex problems into simple subtasks--a crucial part of human-like natural planning--to solve the given problem has significantly boosted the performance of large language models (LLMs). However, leveraging such…

Over recent years, an increasing amount of compute and data has been poured into training large language models (LLMs), usually by doing one-pass learning on as many tokens as possible randomly selected from large-scale web corpora. While…

Machine unlearning, the study of efficiently removing the impact of specific training instances on a model, has garnered increased attention in recent years due to regulatory guidelines such as the \emph{Right to be Forgotten}. Achieving…

Driven by privacy protection laws and regulations, unlearning in Large Language Models (LLMs) is gaining increasing attention. However, current research often neglects the interpretability of the unlearning process, particularly concerning…

Pretrained Language Models (LMs) memorize a vast amount of knowledge during initial pretraining, including information that may violate the privacy of personal lives and identities. Previous work addressing privacy issues for language…

Recent Active Learning (AL) approaches in Natural Language Processing (NLP) proposed using off-the-shelf pretrained language models (LMs). In this paper, we argue that these LMs are not adapted effectively to the downstream task during AL…

Large language model (LLM) unlearning has demonstrated effectiveness in removing the influence of undesirable data (also known as forget data). Existing approaches typically assume full access to the forget dataset, overlooking two key…