English
Related papers

Related papers: What Is the Minimum Architecture for Prolepsis? Ea…

200 papers

Mechanistic interpretability identifies internal circuits responsible for model behaviors, yet translating these findings into human-understandable explanations remains an open problem. We present a pipeline that bridges circuit-level…

Computation and Language · Computer Science 2026-03-12 Ajay Pravin Mahale

Transformer architectures based on the attention mechanism have revolutionized natural language processing (NLP), driving major breakthroughs across virtually every NLP task. However, their substantial memory and computational requirements…

Computation and Language · Computer Science 2026-03-25 Riccardo Bravin , Massimo Pavan , Hazem Hesham Yousef Shalby , Fabrizio Pittorino , Manuel Roveri

Transformer networks, driven by self-attention, are central to Large Language Models. In generative Transformers, self-attention uses cache memory to store token projections, avoiding recomputation at each time step. However, GPU-stored…

Neural and Evolutionary Computing · Computer Science 2024-11-26 Nathan Leroux , Paul-Philipp Manea , Chirag Sudarshan , Jan Finkbeiner , Sebastian Siegel , John Paul Strachan , Emre Neftci

Search is an ability foundational in many important tasks, and recent studies have shown that large language models (LLMs) struggle to perform search robustly. It is unknown whether this inability is due to a lack of data, insufficient…

We propose a synthetic reasoning task, LEGO (Learning Equality and Group Operations), that encapsulates the problem of following a chain of reasoning, and we study how the Transformer architectures learn this task. We pay special attention…

Machine Learning · Computer Science 2023-02-21 Yi Zhang , Arturs Backurs , Sébastien Bubeck , Ronen Eldan , Suriya Gunasekar , Tal Wagner

Recent work suggests that large language models (LLMs) can perform multi-hop reasoning implicitly -- producing correct answers without explicitly verbalizing intermediate steps -- but the underlying mechanisms remain poorly understood. In…

Machine Learning · Computer Science 2025-11-07 Jiaran Ye , Zijun Yao , Zhidian Huang , Liangming Pan , Jinxin Liu , Yushi Bai , Amy Xin , Weichuan Liu , Xiaoyin Che , Lei Hou , Juanzi Li

We study the error rate of LLMs on tasks like arithmetic that require a deterministic output, and repetitive processing of tokens drawn from a small set of alternatives. We argue that incorrect predictions arise when small errors in the…

Machine Learning · Computer Science 2026-01-21 Suvrat Raju , Praneeth Netrapalli

Large language models exhibit sophisticated capabilities, yet understanding how they work internally remains a central challenge. A fundamental obstacle is that training selects for behavior, not circuitry, so many weight configurations can…

Machine Learning · Computer Science 2026-02-27 Joshua S. Schiffman

Language models can be persuaded to abandon factual knowledge. This vulnerability is central to AI safety, but its internal mechanism remains poorly understood. We uncover a compact causal mechanism for persuasion-induced factual errors. A…

Artificial Intelligence · Computer Science 2026-05-12 Xiangkun Sun , Lingkai Kong , Aoqi Zhang , Liang Zeng , Tonghan Wang

In-context learning (ICL) is a cornerstone of large language model (LLM) functionality, yet its theoretical foundations remain elusive due to the complexity of transformer architectures. In particular, most existing work only theoretically…

Machine Learning · Computer Science 2024-09-18 Siyu Chen , Heejune Sheen , Tianhao Wang , Zhuoran Yang

Transformer-based large language models (LLMs) excel in modeling complex language patterns but face significant computational costs during inference, especially with long inputs due to the attention mechanism's memory overhead. We observe…

Computation and Language · Computer Science 2024-10-18 Ruiqing Yan , Linghan Zheng , Xingbo Du , Han Zou , Yufeng Guo , Jianfei Yang

Large Language Models are prone to biased predictions and hallucinations, underlining the paramount importance of understanding their model-internal reasoning process. However, achieving faithful attributions for the entirety of a black-box…

Transformers evaluated in a single, fixed-depth pass are provably limited in expressive power to the constant-depth circuit class TC0. Running a Transformer autoregressively removes that ceiling -- first in next-token prediction and, more…

Machine Learning · Computer Science 2025-07-21 Mrinal Mathur , Mike Doan , Barak Pearlmutter , Sergey Plis

While Transformers have revolutionized deep learning, their quadratic attention complexity hinders their ability to process infinitely long inputs. We propose Feedback Attention Memory (FAM), a novel Transformer architecture that leverages…

Machine Learning · Computer Science 2024-05-08 Dongseong Hwang , Weiran Wang , Zhuoyuan Huo , Khe Chai Sim , Pedro Moreno Mengibar

Attention-based architectures have become ubiquitous in machine learning, yet our understanding of the reasons for their effectiveness remains limited. This work proposes a new way to understand self-attention networks: we show that their…

Machine Learning · Computer Science 2023-08-02 Yihe Dong , Jean-Baptiste Cordonnier , Andreas Loukas

Despite the empirical success of prompt tuning in adapting pretrained language models to new tasks, theoretical analyses of its capabilities remain limited. Existing theoretical work primarily addresses universal approximation properties,…

Machine Learning · Computer Science 2025-09-03 Maxime Meyer , Mario Michelessa , Caroline Chaux , Vincent Y. F. Tan

Transformer-based models have emerged as a leading architecture for natural language processing, natural language generation, and image generation tasks. A fundamental element of the transformer architecture is self-attention, which allows…

Machine Learning · Computer Science 2025-07-01 Venmugil Elango

Standard Transformers have a fixed computational depth, fundamentally limiting their ability to generalize to tasks requiring variable-depth reasoning, such as multi-hop graph traversal or nested logic. We propose a depth-recurrent…

Machine Learning · Computer Science 2026-03-24 Hung-Hsuan Chen

Transformers have reshaped machine learning by utilizing attention mechanisms to capture complex patterns in large datasets, leading to significant improvements in performance. This success has contributed to the belief that "bigger means…

Machine Learning · Computer Science 2025-05-28 Hemanth Saratchandran , Damien Teney , Simon Lucey

The reasoning pattern of Large language models (LLMs) remains opaque, and Reinforcement learning (RL) typically applies uniform credit across an entire generation, blurring the distinction between pivotal and routine steps. This work…

Computation and Language · Computer Science 2025-10-16 Yang Li , Zhichen Dong , Yuhan Sun , Weixun Wang , Shaopan Xiong , Yijia Luo , Jiashun Liu , Han Lu , Jiamang Wang , Wenbo Su , Bo Zheng , Junchi Yan