English
Related papers

Related papers: Understanding Verbatim Memorization in LLMs Throug…

200 papers

In this paper we address the question of how to render sequence-level networks better at handling structured input. We propose a machine reading simulator which processes text incrementally from left to right and performs shallow reasoning…

Computation and Language · Computer Science 2016-09-22 Jianpeng Cheng , Li Dong , Mirella Lapata

Due to the size and complexity of modern large language models (LLMs), it has proven challenging to uncover the underlying mechanisms that models use to solve reasoning problems. For instance, is their reasoning for a specific problem…

Machine Learning · Computer Science 2025-06-23 Guan Zhe Hong , Nishanth Dikkala , Enming Luo , Cyrus Rashtchian , Xin Wang , Rina Panigrahy

Large language models can memorize and repeat their training data, causing privacy and copyright risks. To mitigate memorization, we introduce a subtle modification to the next-token training objective that we call the goldfish loss. During…

Large Language Models (LLMs) exhibit positional bias, struggling to utilize information from the middle or end of long contexts. Our study explores LLMs' long-context reasoning by probing their hidden representations. We find that while…

Computation and Language · Computer Science 2024-10-08 Taiming Lu , Muhan Gao , Kuai Yu , Adam Byerly , Daniel Khashabi

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

Existing memory systems enable Large Language Models (LLMs) to support long-horizon human-LLM interactions by persisting historical interactions beyond limited context windows. However, while recent approaches have succeeded in constructing…

Computation and Language · Computer Science 2026-04-21 Haidong Xin , Xinze Li , Zhenghao Liu , Yukun Yan , Shuo Wang , Cheng Yang , Yu Gu , Ge Yu , Maosong Sun

Recent studies show that neural retrievers often display source bias, favoring passages generated by LLMs over human-written ones, even when both are semantically similar. This bias has been considered an inherent flaw of retrievers,…

Information Retrieval · Computer Science 2026-04-08 Wei Huang , Keping Bi , Yinqiong Cai , Wei Chen , Jiafeng Guo , Xueqi Cheng

Steering large language models (LLMs) is usually done by either instruction prompting or activation steering. Prompting often gives strong control, but caches guidance tokens at every layer and can clutter long interactions; activation…

Machine Learning · Computer Science 2026-05-12 Andy Zeyi Liu , Michael Zhang , Ilana Greenberg , Adam Alnasser , Lucas Baker , John Sous

Long Short-Term Memory (LSTM) is one of the most widely used recurrent structures in sequence modeling. It aims to use gates to control information flow (e.g., whether to skip some information or not) in the recurrent computations, although…

Machine Learning · Computer Science 2018-06-11 Zhuohan Li , Di He , Fei Tian , Wei Chen , Tao Qin , Liwei Wang , Tie-Yan Liu

The mechanisms by which reasoning training reshapes LLMs' internal computations remain unclear. We study lightweight steering vectors inserted into the base model's residual stream and trained with a reinforcement-learning objective. These…

Transformers have become the go-to architecture for language and vision tasks, yet their theoretical properties, especially memorization capacity, remain elusive. This paper investigates the memorization abilities of multi-head attention…

Machine Learning · Computer Science 2024-03-05 Sadegh Mahdavi , Renjie Liao , Christos Thrampoulidis

Transformer-based language models (LMs) track contextual information through large, hard-coded input windows. We introduce MemoryPrompt, a leaner approach in which the LM is complemented by a small auxiliary recurrent network that passes…

Computation and Language · Computer Science 2024-02-26 Nathanaël Carraz Rakotonirina , Marco Baroni

Memristors are nonlinear two-terminal circuit elements whose resistance at a given time depends on past electrical stimuli. Recently, networks of memristors have received attention in neuromorphic computing since they can be used as a tool…

Optimization and Control · Mathematics 2024-09-24 Marieke Heidema , Henk van Waarde , Bart Besselink

Large language models (LLMs) can detect software vulnerabilities, but how do they actually identify vulnerable code? We address this question using mechanistic interpretability; analyzing the internal computations of a neural network to…

Cryptography and Security · Computer Science 2026-05-29 Syafiq Al Atiiq , Chun Zhou , Christian Gehrmann

Transformer-based large language models (LLM) have been widely used in language processing applications. However, due to the memory constraints of the devices, most of them restrict the context window. Even though recurrent models in…

Computation and Language · Computer Science 2025-02-07 Zifan He , Yingqi Cao , Zongyue Qin , Neha Prakriya , Yizhou Sun , Jason Cong

While Large Language Models (LLMs) demonstrate impressive reasoning capabilities, growing evidence suggests much of their success stems from memorized answer-reasoning patterns rather than genuine inference. In this work, we investigate a…

Computation and Language · Computer Science 2025-06-24 Yang Wu , Yifan Zhang , Yiwei Wang , Yujun Cai , Yurong Wu , Yuran Wang , Ning Xu , Jian Cheng

Two of the many trends in neural network research of the past few years have been (i) the learning of dynamical systems, especially with recurrent neural networks such as long short-term memory networks (LSTMs) and (ii) the introduction of…

Numerical Analysis · Mathematics 2024-11-15 Benedikt Brantner , Guillaume de Romemont , Michael Kraus , Zeyuan Li

Large language models based on transformers have achieved great empirical successes. However, as they are deployed more widely, there is a growing need to better understand their internal mechanisms in order to make them more reliable.…

Machine Learning · Statistics 2023-11-08 Alberto Bietti , Vivien Cabannes , Diane Bouchacourt , Herve Jegou , Leon Bottou

Idioms have long posed a challenge due to their unique linguistic properties, which set them apart from other common expressions. While recent studies have leveraged large language models (LLMs) to handle idioms across various tasks, e.g.,…

Computation and Language · Computer Science 2025-09-24 Jisu Kim , Youngwoo Shin , Uiji Hwang , Jihun Choi , Richeng Xuan , Taeuk Kim

Large language models (LLMs) are known to memorize and recall English text from their pretraining data. However, the extent to which this ability generalizes to non-English languages or transfers across languages remains unclear. This paper…

Computation and Language · Computer Science 2025-10-08 Alisha Srivastava , Emir Korukluoglu , Minh Nhat Le , Duyen Tran , Chau Minh Pham , Marzena Karpinska , Mohit Iyyer