English
Related papers

Related papers: Understanding Transformer Memorization Recall Thro…

200 papers

Large language models (LLMs) have been proven capable of memorizing their training data, which can be extracted through specifically designed prompts. As the scale of datasets continues to grow, privacy risks arising from memorization have…

Computation and Language · Computer Science 2023-11-07 Zhenhong Zhou , Jiuyang Xiang , Chaomeng Chen , Sen Su

Large Language Models (LLMs) are increasingly deployed to automatically label and analyze educational dialogue at scale, yet current pipelines lack reliable ways to detect when models are wrong. We investigate whether reasoning generated by…

Computation and Language · Computer Science 2026-02-11 Bakhtawar Ahtisham , Kirk Vanacore , Zhuqian Zhou , Jinsook Lee , Rene F. Kizilcec

Transformer-based Large Language Models (LLMs) have revolutionized Natural Language Processing by demonstrating exceptional performance across diverse tasks. This study investigates the impact of the parameter initialization scale on the…

Computation and Language · Computer Science 2025-05-22 Junjie Yao , Zhongwang Zhang , Zhi-Qin John Xu

Despite their wide adoption, the underlying training and memorization dynamics of very large language models is not well understood. We empirically study exact memorization in causal and masked language modeling, across model sizes and…

Computation and Language · Computer Science 2022-11-04 Kushal Tirumala , Aram H. Markosyan , Luke Zettlemoyer , Armen Aghajanyan

Training data leakage from Large Language Models (LLMs) raises serious concerns related to privacy, security, and copyright compliance. A central challenge in assessing this risk is distinguishing genuine memorization of training data from…

Machine Learning · Computer Science 2026-02-24 Trishita Tiwari , Ari Trachtenberg , G. Edward Suh

Autoregressive language models (LMs) generate one token at a time, yet human reasoning operates over higher-level abstractions - sentences, propositions, and concepts. This contrast raises a central question- Can LMs likewise learn to…

Computation and Language · Computer Science 2025-10-14 Hyeonbin Hwang , Byeongguk Jeon , Seungone Kim , Jiyeon Kim , Hoyeon Chang , Sohee Yang , Seungpil Won , Dohaeng Lee , Youbin Ahn , Minjoon Seo

Although it is known that transformer language models (LMs) pass features from early layers to later layers, it is not well understood how this information is represented and routed by the model. We analyze a mechanism used in two LMs to…

Computation and Language · Computer Science 2025-05-12 Jack Merullo , Carsten Eickhoff , Ellie Pavlick

Neural language models are black-boxes--both linguistic patterns and factual knowledge are distributed across billions of opaque parameters. This entangled encoding makes it difficult to reliably inspect, verify, or update specific facts.…

Large language models (LLMs) sometimes fail to respond appropriately to deterministic tasks -- such as counting or forming acronyms -- because the implicit prior distribution they have learned over sequences of tokens influences their…

Computation and Language · Computer Science 2025-04-18 Liyi Zhang , Veniamin Veselovsky , R. Thomas McCoy , Thomas L. Griffiths

Using translation memories (TMs) as prompts is a promising approach to in-context learning of machine translation models. In this work, we take a step towards prompting large language models (LLMs) with TMs and making them better…

Computation and Language · Computer Science 2023-05-30 Yongyu Mu , Abudurexiti Reheman , Zhiquan Cao , Yuchun Fan , Bei Li , Yinqiao Li , Tong Xiao , Chunliang Zhang , Jingbo Zhu

Multiple studies have probed representations emerging in neural networks trained for end-to-end NLP tasks and examined what word-level linguistic information may be encoded in the representations. In classical probing, a classifier is…

Computation and Language · Computer Science 2021-10-26 Rudolf Rosa , Tomáš Musil , David Mareček

Language model (LM) pre-training is useful in many language processing tasks. But can pre-trained LMs be further leveraged for more general machine learning problems? We propose an approach for using LMs to scaffold learning and…

We investigate the extent to which modern, neural language models are susceptible to structural priming, the phenomenon whereby the structure of a sentence makes the same structure more probable in a follow-up sentence. We explore how…

Computation and Language · Computer Science 2022-06-30 Arabella Sinclair , Jaap Jumelet , Willem Zuidema , Raquel Fernández

Intelligent systems must maintain and manipulate task-relevant information online to adapt to dynamic environments and changing goals. This capacity, known as working memory, is fundamental to human reasoning and intelligence. Despite…

Machine Learning · Computer Science 2026-04-14 Hua-Dong Xiong , Li Ji-An , Jiaqi Huang , Robert C. Wilson , Kwonjoon Lee , Xue-Xin Wei

In language models (LMs), intra-memory knowledge conflict largely arises when inconsistent information about the same event is encoded within the model's parametric knowledge. While prior work has primarily focused on resolving conflicts…

Computation and Language · Computer Science 2026-01-15 Minh Vu Pham , Hsuvas Borkakoty , Yufang Hou

Transformer-based language models (LMs) are known to capture factual knowledge in their parameters. While previous work looked into where factual associations are stored, only little is known about how they are retrieved internally during…

Computation and Language · Computer Science 2023-10-17 Mor Geva , Jasmijn Bastings , Katja Filippova , Amir Globerson

While Pre-trained Language Models (PLMs) internalize a great amount of world knowledge, they have been shown incapable of recalling these knowledge to solve tasks requiring complex & multi-step reasoning. Similar to how humans develop a…

Computation and Language · Computer Science 2022-10-25 Boshi Wang , Xiang Deng , Huan Sun

Language models retain a significant amount of world knowledge from their pre-training stage. This allows knowledgeable models to be applied to knowledge-intensive tasks prevalent in information retrieval, such as ranking or question…

Computation and Language · Computer Science 2023-06-13 Jonas Wallat , Tianyi Zhang , Avishek Anand

Unlike literal expressions, idioms' meanings do not directly follow from their parts, posing a challenge for neural machine translation (NMT). NMT models are often unable to translate idioms accurately and over-generate compositional,…

Computation and Language · Computer Science 2022-05-31 Verna Dankers , Christopher G. Lucas , Ivan Titov

As Large Language Models (LLMs) become widely adopted, understanding how they learn from, and memorize, training data becomes crucial. Memorization in LLMs is widely assumed to only occur as a result of sequences being repeated in the…

Computation and Language · Computer Science 2025-05-16 Igor Shilov , Matthieu Meeus , Yves-Alexandre de Montjoye