English
Related papers

Related papers: Locating and Editing Factual Associations in Mamba

200 papers

Understanding how Transformer-based language models store and retrieve factual associations is critical for improving interpretability and enabling targeted model editing. Prior work, primarily on GPT-style models, has identified MLP…

Computation and Language · Computer Science 2025-09-11 Minyeong Choe , Haehyun Cho , Changho Seo , Hyunil Kim

This paper investigates the flow of factual information in Mamba State-Space Model (SSM)-based language models. We rely on theoretical and empirical connections to Transformer-based architectures and their attention mechanisms. Exploiting…

Computation and Language · Computer Science 2025-06-02 Nir Endy , Idan Daniel Grosbard , Yuval Ran-Milo , Yonatan Slutzky , Itay Tshuva , Raja Giryes

The storage and recall of factual associations in auto-regressive transformer language models (LMs) have drawn a great deal of attention, inspiring knowledge editing by directly modifying the located model weights. Most editing works…

Computation and Language · Computer Science 2025-02-28 Xiyu Liu , Zhengxiao Liu , Naibin Gu , Zheng Lin , Wanli Ma , Ji Xiang , Weiping Wang

Transformer structure has achieved great success in multiple applied machine learning communities, such as natural language processing (NLP), computer vision (CV) and information retrieval (IR). Transformer architecture's core mechanism\,…

Information Retrieval · Computer Science 2026-01-06 Zhichao Xu

We study memory in state-space language models using primacy and recency effects as behavioral tools to uncover how information is retained and forgotten over time. Applying structured recall tasks to the Mamba architecture, we observe a…

Computation and Language · Computer Science 2025-06-19 Muhammad Cendekia Airlangga , Hilal AlQuabeh , Munachiso S Nwadike , Kentaro Inui

State-Space Models (SSMs), and particularly Mamba, have recently emerged as a promising alternative to Transformers. Mamba introduces input selectivity to its SSM layer (S6) and incorporates convolution and gating into its block definition.…

Machine Learning · Computer Science 2025-06-16 Ningyuan Huang , Miguel Sarabia , Abhinav Moudgil , Pau Rodriguez , Luca Zappella , Federico Danieli

We analyze the storage and recall of factual associations in autoregressive transformer language models, finding evidence that these associations correspond to localized, directly-editable computations. We first develop a causal…

Computation and Language · Computer Science 2023-01-16 Kevin Meng , David Bau , Alex Andonian , Yonatan Belinkov

As one of the most representative DL techniques, Transformer architecture has empowered numerous advanced models, especially the large language models (LLMs) that comprise billions of parameters, becoming a cornerstone in deep learning.…

Machine Learning · Computer Science 2026-04-07 Haohao Qu , Liangbo Ning , Rui An , Wenqi Fan , Tyler Derr , Hui Liu , Xin Xu , Qing Li

While the Mamba architecture demonstrates superior inference efficiency and competitive performance on short-context natural language processing (NLP) tasks, empirical evidence suggests its capacity to comprehend long contexts is limited…

Computation and Language · Computer Science 2025-01-03 Danlong Yuan , Jiahao Liu , Bei Li , Huishuai Zhang , Jingang Wang , Xunliang Cai , Dongyan Zhao

Large language models (LLMs) have advanced significantly due to the attention mechanism, but their quadratic complexity and linear memory demands limit their performance on long-context tasks. Recently, researchers introduced Mamba, an…

Computation and Language · Computer Science 2024-10-22 Wangjie You , Zecheng Tang , Juntao Li , Lili Yao , Min Zhang

With the explosive growth of data, long-sequence modeling has become increasingly important in tasks such as natural language processing and bioinformatics. However, existing methods face inherent trade-offs between efficiency and memory.…

Machine Learning · Computer Science 2025-10-07 Youjin Wang , Yangjingyi Chen , Jiahao Yan , Jiaxuan Lu , Xiao Sun

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

Transformers are the current architecture of choice for NLP, but their attention layers do not scale well to long contexts. Recent works propose to replace attention with linear recurrent layers -- this is the case for state space models,…

Computation and Language · Computer Science 2024-07-09 Hugo Pitorro , Pavlo Vasylenko , Marcos Treviso , André F. T. Martins

How do transformer-based large language models (LLMs) store and retrieve knowledge? We focus on the most basic form of this task -- factual recall, where the model is tasked with explicitly surfacing stored facts in prompts of form `Fact:…

Machine Learning · Computer Science 2024-02-14 Bilal Chughtai , Alan Cooney , Neel Nanda

Despite the advantageous subquadratic complexity of modern recurrent deep learning models -- such as state-space models (SSMs) -- recent studies have highlighted their potential shortcomings compared to transformers on reasoning and…

Machine Learning · Computer Science 2025-10-13 Destiny Okpekpe , Antonio Orvieto

Decision Transformer, a promising approach that applies Transformer architectures to reinforcement learning, relies on causal self-attention to model sequences of states, actions, and rewards. While this method has shown competitive…

Machine Learning · Computer Science 2024-04-01 Toshihiro Ota

How do language models retrieve entity-specific facts from their parameters? We investigate this question by searching for sparse, entity-selective MLP neurons - which we call entity cells, by analogy to the "grandmother cell" hypothesis in…

Computation and Language · Computer Science 2026-05-19 Itay Yona , Dan Barzilay , Michael Karasik , Mor Geva

Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module. Many subquadratic-time architectures such as linear attention,…

Machine Learning · Computer Science 2024-06-03 Albert Gu , Tri Dao

Recent advancements in recurrent architectures, such as Mamba and RWKV, have showcased strong language capabilities. Unlike transformer-based models, these architectures encode all contextual information into a fixed-size state, leading to…

Computation and Language · Computer Science 2026-01-14 Yingfa Chen , Xinrong Zhang , Shengding Hu , Xu Han , Zhiyuan Liu , Maosong Sun

Recent work has shown that state space models such as Mamba are significantly worse than Transformers on recall-based tasks due to the fact that their state size is constant with respect to their input sequence length. But in practice,…

Machine Learning · Computer Science 2024-10-16 Asher Trockman , Hrayr Harutyunyan , J. Zico Kolter , Sanjiv Kumar , Srinadh Bhojanapalli
‹ Prev 1 2 3 10 Next ›