English
Related papers

Related papers: Causal Estimation of Memorisation Profiles

200 papers

In this paper, we investigate knowledge forgetting in large language models with a focus on its generalisation, ensuring that models forget not only specific training samples but also related implicit knowledge. To this end, we begin by…

Computation and Language · Computer Science 2025-10-10 Huazheng Wang , Yongcheng Jing , Haifeng Sun , Yingjie Wang , Jingyu Wang , Jianxin Liao , Dacheng Tao

In this work, we investigate how a model's tendency to broadly integrate its parametric knowledge evolves throughout pretraining, and how this behavior affects overall performance, particularly in terms of knowledge acquisition and…

Computation and Language · Computer Science 2025-03-13 Jiyeon Kim , Hyunji Lee , Hyowon Cho , Joel Jang , Hyeonbin Hwang , Seungpil Won , Youbin Ahn , Dohaeng Lee , Minjoon Seo

Large language models (LLMs) suffer from forgetting of upstream knowledge when fine-tuned. Despite efforts on mitigating forgetting, few have investigated how forgotten upstream examples are dependent on newly learned tasks. Insights on…

Machine Learning · Computer Science 2025-12-09 Xisen Jin , Xiang Ren

The widespread use of diffusion models has led to an abundance of AI-generated data, raising concerns about model collapse -- a phenomenon in which recursive iterations of training on synthetic data lead to performance degradation. Prior…

Machine Learning · Computer Science 2025-12-29 Lianghe Shi , Meng Wu , Huijie Zhang , Zekai Zhang , Molei Tao , Qing Qu

Machine unlearning (MUL) focuses on removing the influence of specific subsets of data (such as noisy, poisoned, or privacy-sensitive data) from pretrained models. MUL methods typically rely on specialized forms of fine-tuning. Recent…

Machine Learning · Computer Science 2024-11-05 Kairan Zhao , Peter Triantafillou

The lack of transparency about code datasets used to train large language models (LLMs) makes it difficult to detect, evaluate, and mitigate data leakage. We present a perturbation-based method to quantify memorization advantage in code…

Diffusion models have achieved remarkable success across diverse domains, but they remain vulnerable to memorization -- reproducing training data rather than generating novel outputs. This not only limits their creative potential but also…

Machine Learning · Statistics 2025-11-10 Zeqi Ye , Qijie Zhu , Molei Tao , Minshuo Chen

Evaluating hypothetical statements about how the world would be had a different course of action been taken is arguably one key capability expected from modern AI systems. Counterfactual reasoning underpins discussions in fairness, the…

Machine Learning · Computer Science 2022-10-04 Kevin Xia , Yushu Pan , Elias Bareinboim

This position paper argues that understanding generalization in diffusion models requires fundamentally new theoretical frameworks that go beyond both classical statistical learning theory and the benign overfitting paradigm developed for…

Machine Learning · Computer Science 2026-05-08 Pierre Marion , Yu-Han Wu

Increasing the number of parameters in language models is a common strategy to enhance their performance. However, smaller language models remain valuable due to their lower operational costs. Despite their advantages, smaller models…

Computation and Language · Computer Science 2024-10-16 Richard Diehl Martinez , Pietro Lesci , Paula Buttery

Causal language models acquire vast amount of knowledge from general text corpus during pretraining, but the efficiency of knowledge learning is known to be unsatisfactory, especially when learning from knowledge-dense and small-sized…

Artificial Intelligence · Computer Science 2025-03-13 Jian Gao , Xiao Zhang , Ji Wu , Miao Li

Causal representation learning aims to unveil latent high-level causal representations from observed low-level data. One of its primary tasks is to provide reliable assurance of identifying these latent causal models, known as…

Machine Learning · Computer Science 2024-12-02 Yuhang Liu , Zhen Zhang , Dong Gong , Mingming Gong , Biwei Huang , Anton van den Hengel , Kun Zhang , Javen Qinfeng Shi

Scaling laws have allowed Pre-trained Language Models (PLMs) into the field of causal reasoning. Causal reasoning of PLM relies solely on text-based descriptions, in contrast to causal discovery which aims to determine the causal…

Many real-world applications require machine-learning models to be able to deal with non-stationary data distributions and thus learn autonomously over an extended period of time, often in an online setting. One of the main challenges in…

Machine Learning · Computer Science 2025-07-22 Giuseppe Serra , Ben Werner , Florian Buettner

Causal models communicate our assumptions about causes and effects in real-world phe- nomena. Often the interest lies in the identification of the effect of an action which means deriving an expression from the observed probability…

Machine Learning · Statistics 2018-06-20 Santtu Tikka , Juha Karvanen

In this report we review memory-based meta-learning as a tool for building sample-efficient strategies that learn from past experience to adapt to any task within a target class. Our goal is to equip the reader with the conceptual…

Large language models may encode sensitive information or outdated knowledge that needs to be removed, to ensure responsible and compliant model responses. Unlearning has emerged as an efficient alternative to full retraining, aiming to…

Computation and Language · Computer Science 2026-05-28 Yuefeng Peng , Parnian Afshar , Megan Ganji , Thomas Butler , Amir Houmansadr , Mingxian Wang , Dezhi Hong

As models continue to grow in size, the development of memory optimization methods (MOMs) has emerged as a solution to address the memory bottleneck encountered when training large models. To comprehensively examine the practical value of…

Machine Learning · Computer Science 2023-06-06 Xiaoxuan Liu , Siddharth Jha , Alvin Cheung

Large language model (LLM) post-training enhances latent skills, unlocks value alignment, improves performance, and enables domain adaptation. Unfortunately, post-training is known to induce forgetting, especially in the ubiquitous use-case…

Machine Learning · Computer Science 2026-05-25 Lukas Thede , Stefan Winzeck , Zeynep Akata , Jonathan Richard Schwarz

Memory-based learning, keeping full memory of learning material, appears a viable approach to learning NLP tasks, and is often superior in generalisation accuracy to eager learning approaches that abstract from learning material. Here we…

cmp-lg · Computer Science 2007-05-23 Antal van den Bosch , Walter Daelemans