English
Related papers

Related papers: Residual Connections and the Causal Shift: Uncover…

200 papers

Scaling large language models (LLMs) leads to an emergent capacity to learn in-context from example demonstrations. Despite progress, theoretical understanding of this phenomenon remains limited. We argue that in-context learning relies on…

Computation and Language · Computer Science 2023-03-15 Michael Hahn , Navin Goyal

Transformer models have emerged as fundamental tools across various scientific and engineering disciplines, owing to their outstanding performance in diverse applications. Despite this empirical success, the theoretical foundations of…

Machine Learning · Computer Science 2026-04-14 Zhen Qin , Jinxin Zhou , Jiachen Jiang , Zhihui Zhu

Fine-tuning pre-trained large language models (LLMs) on a diverse array of tasks has become a common approach for building models that can solve various natural language processing (NLP) tasks. However, where and to what extent these models…

Computation and Language · Computer Science 2024-10-29 Zheng Zhao , Yftah Ziser , Shay B. Cohen

Without any explicit cross-lingual training data, multilingual language models can achieve cross-lingual transfer. One common way to improve this transfer is to perform realignment steps before fine-tuning, i.e., to train the model to build…

Computation and Language · Computer Science 2023-06-06 Félix Gaschi , Patricio Cerda , Parisa Rastin , Yannick Toussaint

Autoregressive large language models (LLMs) generate text token-by-token, requiring n forward passes to produce a sequence of length n. Recent work, Exploring the Latent Capacity of LLMs for One-Step Text Reconstruction (Mezentsev and…

Machine Learning · Computer Science 2026-02-23 Ivan Bondarenko , Egor Palkin , Fedor Tikunov

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…

Machine Learning · Computer Science 2025-06-23 Tianle Gu , Kexin Huang , Zongqi Wang , Yixu Wang , Jie Li , Yuanqi Yao , Yang Yao , Yujiu Yang , Yan Teng , Yingchun Wang

We analyze how large language models (LLMs) represent out-of-context words, investigating their reliance on the given context to capture their semantics. Our likelihood-guided text perturbations reveal a correlation between token likelihood…

Computation and Language · Computer Science 2023-03-16 Valeria Ruscio , Valentino Maiorca , Fabrizio Silvestri

Recent years have seen a paradigm shift in NLP towards using pretrained language models ({PLM}) for a wide range of tasks. However, there are many difficult design decisions to represent structures (e.g. tagged text, coreference chains) in…

Computation and Language · Computer Science 2022-11-18 Tianyu Liu , Yuchen Jiang , Nicholas Monath , Ryan Cotterell , Mrinmaya Sachan

This thesis provides methods and analysis of models which make progress on this goal. The techniques outlined are task agnostic, and should provide benefit when used with nearly any transformer LM. We introduce two new finetuning methods…

Computation and Language · Computer Science 2024-08-30 Davis Yoshida

The widespread adoption of large language models (LLMs) across industries has increased the demand for high-quality and customizable outputs. However, traditional alignment methods often require retraining large pretrained models, making it…

Computation and Language · Computer Science 2025-12-16 Yi Liu , Dianqing Liu , Mingye Zhu , Junbo Guo , Yongdong Zhang , Zhendong Mao

A common approach to mechanistic interpretability is to causally manipulate model representations via targeted interventions in order to understand what those representations encode. Here we ask whether such interventions create…

Machine Learning · Computer Science 2026-04-24 Satchel Grant , Simon Jerome Han , Alexa R. Tartaglini , Christopher Potts

Pretraining large language models (LLMs) with next-token prediction has led to remarkable advances, yet the context-dependent nature of token embeddings in such models results in high intra-class variance and inter-class similarity, thus…

Computation and Language · Computer Science 2026-05-12 Yan Sun , Guoxia Wang , Jinle Zeng , JiaBin Yang , Shuai Li , Li Shen , Dacheng Tao , DianHai Yu , Haifeng Wang

This paper examines a critical yet unexplored dimension of the AI alignment problem: the potential for Large Language Models (LLMs) to inherit and amplify existing misalignments between human espoused theories and theories-in-use. Drawing…

Human-Computer Interaction · Computer Science 2025-07-04 Tim Rogers , Ben Teehankee

In decoder-only (causal) transformers, the computation graph created by causal masking routes information through both direct-path attention and indirect paths formed by intermediate tokens. We denote these indirect paths between token…

Machine Learning · Computer Science 2026-01-22 Hunjae Lee , Corey Clark

The rapid progress seen in terms of large-scale generative AI is largely based on the attention mechanism. It is conversely non-trivial to conceive small-scale applications for which attention-based architectures outperform traditional…

Machine Learning · Computer Science 2025-08-07 Claudius Gros

Large language models (LLMs) have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque. Mechanistic interpretability (i.e., the systematic study of how neural networks…

Computation and Language · Computer Science 2026-02-13 Usman Naseem

This paper addresses the limited transfer and adaptation capabilities of large language models in low-resource language scenarios. It proposes a unified framework that combines a knowledge transfer module with parameter-efficient…

Computation and Language · Computer Science 2025-07-03 Shuangquan Lyu , Yingnan Deng , Guiran Liu , Zhen Qi , Ruotong Wang

While attention has been empirically shown to improve model performance, it lacks a rigorous mathematical justification. This short paper establishes a novel connection between attention mechanisms and multinomial regression. Specifically,…

Machine Learning · Computer Science 2025-10-28 Jonas A. Actor , Anthony Gruber , Eric C. Cyr

Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this…

Cryptography and Security · Computer Science 2025-10-08 Guangyu Shen , Siyuan Cheng , Xiangzhe Xu , Yuan Zhou , Hanxi Guo , Zhuo Zhang , Xiangyu Zhang

Large language models are increasingly deployed in settings where reliability matters, yet output-level uncertainty signals such as token probabilities, entropy, and self-consistency can become brittle under calibration--deployment…

Computation and Language · Computer Science 2026-04-20 Yanli Wang , Peng Kuang , Xiaoyu Han , Kaidi Xu , Haohan Wang