English
Related papers

Related papers: Localizing Paragraph Memorization in Language Mode…

200 papers

How do language models learn to make predictions during pre-training? To study this, we extract learning curves from five autoregressive English language model pre-training runs, for 1M unseen tokens in context. We observe that the language…

Computation and Language · Computer Science 2024-08-01 Tyler A. Chang , Zhuowen Tu , Benjamin K. Bergen

Modern neural network based speech recognition models are required to continually absorb new data without re-training the whole system, especially in downstream applications using foundation models, having no access to the original training…

Computation and Language · Computer Science 2025-06-23 Enes Yavuz Ugan , Ngoc-Quan Pham , Alexander Waibel

Large language models (LLMs) have shown great capabilities in various tasks but also exhibited memorization of training data, raising tremendous privacy and copyright concerns. While prior works have studied memorization during…

Artificial Intelligence · Computer Science 2024-02-26 Shenglai Zeng , Yaxin Li , Jie Ren , Yiding Liu , Han Xu , Pengfei He , Yue Xing , Shuaiqiang Wang , Jiliang Tang , Dawei Yin

In this paper, we investigate the principle that `good explanations are hard to vary' in the context of deep learning. We show that averaging gradients across examples -- akin to a logical OR of patterns -- can favor memorization and…

Machine Learning · Computer Science 2020-10-27 Giambattista Parascandolo , Alexander Neitz , Antonio Orvieto , Luigi Gresele , Bernhard Schölkopf

This work investigates how semantics influence localisation performance and robustness in a learned self-supervised, contrastive semantic localisation framework. After training a localisation network on both original and perturbed maps, we…

Machine Learning · Computer Science 2025-10-09 Manshika Charvi Bissessur , Efimia Panagiotaki , Daniele De Martini

Rote learning is a memorization technique based on repetition. Many researchers argue that rote learning hinders generalization because it encourages verbatim memorization rather than deeper understanding. This concern extends even to…

Computation and Language · Computer Science 2026-03-03 Qinyuan Wu , Soumi Das , Mahsa Amani , Bishwamittra Ghosh , Mohammad Aflah Khan , Krishna P. Gummadi , Muhammad Bilal Zafar

Language models learn a great quantity of factual information during pretraining, and recent work localizes this information to specific model weights like mid-layer MLP weights. In this paper, we find that we can change how a fact is…

Machine Learning · Computer Science 2023-10-17 Peter Hase , Mohit Bansal , Been Kim , Asma Ghandeharioun

The impressive capabilities of large language models (LLMs) have sparked debate over whether these models genuinely generalize to unseen tasks or predominantly rely on memorizing vast amounts of pretraining data. To explore this issue, we…

Computation and Language · Computer Science 2025-03-04 Xinyi Wang , Antonis Antoniades , Yanai Elazar , Alfonso Amayuelas , Alon Albalak , Kexun Zhang , William Yang Wang

Overparameterized deep networks that generalize well have been key to the dramatic success of deep learning in recent years. The reasons for their remarkable ability to generalize are not well understood yet. When class labels in the…

Machine Learning · Computer Science 2026-02-03 Simran Ketha , Venkatakrishnan Ramaswamy

We present the first comprehensive study of Memorization in Multilingual Large Language Models (MLLMs), analyzing 95 languages using models across diverse model scales, architectures, and memorization definitions. As MLLMs are increasingly…

Computation and Language · Computer Science 2026-01-08 Xiaoyu Luo , Yiyi Chen , Johannes Bjerva , Qiongxiu Li

Language Models (LMs) are prone to memorizing parts of their data during training and unintentionally emitting them at generation time, raising concerns about privacy leakage and disclosure of intellectual property. While previous research…

Computation and Language · Computer Science 2025-06-12 Stefan Arnold

Methods for knowledge editing and unlearning in large language models seek to edit or remove undesirable knowledge or capabilities without compromising general language modeling performance. This work investigates how mechanistic…

Machine Learning · Computer Science 2024-12-06 Phillip Guo , Aaquib Syed , Abhay Sheshadri , Aidan Ewart , Gintare Karolina Dziugaite

Modern tokenizers employ deterministic algorithms to map text into a single "canonical" token sequence, yet the same string can be encoded as many non-canonical tokenizations using the tokenizer vocabulary. In this work, we investigate the…

Computation and Language · Computer Science 2026-02-04 Brian Siyuan Zheng , Alisa Liu , Orevaoghene Ahia , Jonathan Hayase , Yejin Choi , Noah A. Smith

The concept of localization in LLMs is often mentioned in prior work; however, methods for localization have never been systematically and directly evaluated. We propose two complementary benchmarks that evaluate the ability of localization…

Computation and Language · Computer Science 2024-04-03 Ting-Yun Chang , Jesse Thomason , Robin Jia

Modern large language model (LLM) applications increasingly rely on long conditioning prefixes to control model behavior at inference time. While prefix-augmented inference is effective, it incurs two structural limitations: i) the prefix's…

Computation and Language · Computer Science 2026-05-19 Yasuyuki Okoshi , Hao Mark Chen , Guanxi Lu , Hongxiang Fan , Masato Motomura , Daichi Fujiki

This paper investigates token homogenization - the convergence of token representations toward uniformity across transformer layers and its relationship to positional bias in large language models. We empirically examine whether…

When automatically generating a sentence description for an image or video, it often remains unclear how well the generated caption is grounded, that is whether the model uses the correct image regions to output particular words, or if the…

Computer Vision and Pattern Recognition · Computer Science 2020-07-21 Chih-Yao Ma , Yannis Kalantidis , Ghassan AlRegib , Peter Vajda , Marcus Rohrbach , Zsolt Kira

Language models perform well on grammatical agreement, but it is unclear whether this reflects rule-based generalization or memorization. We study this question for German definite singular articles, whose forms depend on gender and case.…

Computation and Language · Computer Science 2026-04-15 Jonathan Drechsel , Erisa Bytyqi , Steffen Herbold

LLMs have been found to memorize training textual sequences and regurgitate verbatim said sequences during text generation time. This fact is known to be the cause of privacy and related (e.g., copyright) problems. Unlearning in LLMs then…

Machine Learning · Computer Science 2024-05-07 George-Octavian Barbulescu , Peter Triantafillou

Grounding (i.e. localizing) arbitrary, free-form textual phrases in visual content is a challenging problem with many applications for human-computer interaction and image-text reference resolution. Few datasets provide the ground truth…

Computer Vision and Pattern Recognition · Computer Science 2017-02-21 Anna Rohrbach , Marcus Rohrbach , Ronghang Hu , Trevor Darrell , Bernt Schiele