English
Related papers

Related papers: Time Course MechInterp: Analyzing the Evolution of…

200 papers

As the applications of large language models (LLMs) expand across diverse fields, the ability of these models to adapt to ongoing changes in data, tasks, and user preferences becomes crucial. Traditional training methods, relying on static…

Machine Learning · Computer Science 2024-06-11 Junhao Zheng , Shengjie Qiu , Chengming Shi , Qianli Ma

This paper presents a reproducibility study examining how Large Language Models (LLMs) manage competing factual and counterfactual information, focusing on the role of attention heads in this process. We attempt to reproduce and reconcile…

Computation and Language · Computer Science 2025-07-17 Dante Campregher , Yanxu Chen , Sander Hoffman , Maria Heuss

This review synthesizes the nascent but critical field of developmental interpretability for Large Language Models. We chart the field's evolution from static, post-hoc analysis of trained models to a dynamic investigation of the training…

Computation and Language · Computer Science 2025-08-25 Ihor Kendiukhov

Large Language Models (LLMs) are prevalent in modern applications but often memorize training data, leading to privacy breaches and copyright issues. Existing research has mainly focused on posthoc analyses, such as extracting memorized…

Machine Learning · Computer Science 2025-01-10 Tarun Ram Menta , Susmit Agrawal , Chirag Agarwal

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated remarkable progress in visual understanding. This impressive leap raises a compelling question: how can language models, initially trained solely on…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Jing Bi , Junjia Guo , Yunlong Tang , Lianggong Bruce Wen , Zhang Liu , Chenliang Xu

The process by which Large Language Models (LLMs) acquire complex capabilities during training remains a key open question in mechanistic interpretability. This project investigates whether these learning dynamics can be characterized…

Machine Learning · Computer Science 2025-09-22 Elisabetta Rocchetti

Large Language Models (LLMs) store an extensive amount of factual knowledge obtained from vast collections of text. To effectively utilize these models for downstream tasks, it is crucial to have reliable methods for measuring their…

Computation and Language · Computer Science 2023-06-13 Pouya Pezeshkpour

Large Language Models (LLMs) trained on web-scale text corpora have been shown to capture world knowledge in their parameters. However, the mechanism by which language models store different types of knowledge is poorly understood. In this…

Computation and Language · Computer Science 2024-11-08 Jared Fernandez , Yonatan Bisk , Emma Strubell

Large language models (LLMs) acquire knowledge across diverse domains such as science, history, and geography encountered during generative pre-training. However, due to their stochasticity, it is difficult to predict what LLMs have…

Computation and Language · Computer Science 2026-01-27 Kartik Sharma , Yiqiao Jin , Rakshit Trivedi , Srijan Kumar

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

Associative learning--forming links between co-occurring items--is fundamental to human cognition, reshaping internal representations in complex ways. Testing hypotheses on how representational changes occur in biological systems is…

Machine Learning · Computer Science 2025-10-27 Camila Kolling , Vy Ai Vo , Mariya Toneva

The capabilities of large language models (LLMs) have sparked debate over whether such systems just learn an enormous collection of superficial statistics or a set of more coherent and grounded representations that reflect the real world.…

Machine Learning · Computer Science 2024-03-05 Wes Gurnee , Max Tegmark

The rapid advancement of Large Language Models (LLMs) has improved text understanding and generation but poses challenges in computational resources. This study proposes a curriculum learning-inspired, data-centric training strategy that…

Computation and Language · Computer Science 2024-05-14 Jisu Kim , Juhwan Lee

Large language models (LLMs) exhibit remarkable similarity to neural activity in the human language network. However, the key properties of language shaping brain-like representations, and their evolution during training as a function of…

Computation and Language · Computer Science 2025-09-23 Badr AlKhamissi , Greta Tuckute , Yingtian Tang , Taha Binhuraib , Antoine Bosselut , Martin Schrimpf

Large Language Models (LLMs) are increasingly ubiquitous, yet their ability to retain and reason about temporal information remains limited, hindering their application in real-world scenarios where understanding the sequential nature of…

Computation and Language · Computer Science 2024-07-08 Himanshu Beniwal , Dishant Patel , Kowsik Nandagopan D , Hritik Ladia , Ankit Yadav , Mayank Singh

Large language model (LLM) inference is increasingly bottlenecked by the Key-Value (KV) cache, yet the fine-grained structure of attention-head activations remains poorly understood. We show that pretrained Transformers exhibit a pervasive…

Machine Learning · Computer Science 2026-03-17 Khalid Shaikh , Asmit Kumar Singh , Rebecca Christopher Dsouza , Shikhar Shiromani

As large language models (LLMs) are applied across diverse domains, the ability to selectively unlearn specific information is becoming increasingly essential. For instance, LLMs are expected to selectively provide confidential information…

Computation and Language · Computer Science 2025-06-04 Shota Takashiro , Takeshi Kojima , Andrew Gambardella , Qi Cao , Yusuke Iwasawa , Yutaka Matsuo

Large language models (LLMs) have recently driven striking performance improvements across a range of natural language processing tasks. The factual knowledge acquired during pretraining and instruction tuning can be useful in various…

Computation and Language · Computer Science 2023-10-10 Xuming Hu , Junzhe Chen , Xiaochuan Li , Yufei Guo , Lijie Wen , Philip S. Yu , Zhijiang Guo

Human beings primarily understand the world through concepts (e.g., dog), abstract mental representations that structure perception, reasoning, and learning. However, how large language models (LLMs) acquire, retain, and forget such…

Computation and Language · Computer Science 2026-01-08 Barry Menglong Yao , Sha Li , Yunzhi Yao , Minqian Liu , Zaishuo Xia , Qifan Wang , Lifu Huang

Large Language Models (LLMs) have achieved remarkable success, where instruction tuning is the critical step in aligning LLMs with user intentions. In this work, we investigate how the instruction tuning adjusts pre-trained models with a…

Computation and Language · Computer Science 2024-04-05 Xuansheng Wu , Wenlin Yao , Jianshu Chen , Xiaoman Pan , Xiaoyang Wang , Ninghao Liu , Dong Yu