English
Related papers

Related papers: Identifying and Evaluating Inactive Heads in Pretr…

200 papers

The Transformer architecture, a cornerstone of modern Large Language Models (LLMs), has achieved extraordinary success in sequence modeling, primarily due to its attention mechanism. However, despite its power, the standard attention…

Machine Learning · Computer Science 2026-01-08 Zichuan Fu , Wentao Song , Guojing Li , Yejing Wang , Xian Wu , Yimin Deng , Hanyu Yan , Yefeng Zheng , Xiangyu Zhao

Large language models (LLMs) often concentrate their attention on a few specific tokens referred to as attention sinks. Common examples include the first token, a prompt-independent sink, and punctuation tokens, which are prompt-dependent.…

Computation and Language · Computer Science 2025-09-23 Stephen Zhang , Mustafa Khan , Vardan Papyan

Large Language Models (LLMs) often allocate disproportionate attention to specific tokens, a phenomenon commonly referred to as the attention sink. While such sinks are generally considered detrimental, prior studies have identified a…

Machine Learning · Computer Science 2026-03-10 Runyu Peng , Ruixiao Li , Mingshu Chen , Yunhua Zhou , Qipeng Guo , Xipeng Qiu

Language models have been shown to perform better with an increase in scale on a wide variety of tasks via the in-context learning paradigm. In this paper, we investigate the hypothesis that the ability of a large language model to…

Computation and Language · Computer Science 2023-08-17 Hritik Bansal , Karthik Gopalakrishnan , Saket Dingliwal , Sravan Bodapati , Katrin Kirchhoff , Dan Roth

Deploying Large Language Models (LLMs) in streaming applications such as multi-round dialogue, where long interactions are expected, is urgently needed but poses two major challenges. Firstly, during the decoding stage, caching previous…

Computation and Language · Computer Science 2024-04-09 Guangxuan Xiao , Yuandong Tian , Beidi Chen , Song Han , Mike Lewis

Large language models can follow complex instructions in a single turn, yet over long multi-turn interactions they often lose the thread of instructions, persona, and rules. This degradation has been measured behaviorally but not…

Artificial Intelligence · Computer Science 2026-05-14 Vardhan Dongre , Joseph Hsieh , Viet Dac Lai , Seunghyun Yoon , Trung Bui , Dilek Hakkani-Tür

Large language models (LLMs) have shown a remarkable ability to learn and perform complex tasks through in-context learning (ICL). However, a comprehensive understanding of its internal mechanisms is still lacking. This paper explores the…

Computation and Language · Computer Science 2025-04-03 Joy Crosbie , Ekaterina Shutova

Attention is a fundamental component behind the remarkable achievements of large language models (LLMs). However, our current understanding of the attention mechanism, especially regarding how attention distributions are established,…

Machine Learning · Computer Science 2024-06-25 Zhongzhi Yu , Zheng Wang , Yonggan Fu , Huihong Shi , Khalid Shaikh , Yingyan Celine Lin

Large Language Models (LLMs) have revolutionized various domains but remain vulnerable to prompt injection attacks, where malicious inputs manipulate the model into ignoring original instructions and executing designated action. In this…

Cryptography and Security · Computer Science 2025-04-24 Kuo-Han Hung , Ching-Yun Ko , Ambrish Rawat , I-Hsin Chung , Winston H. Hsu , Pin-Yu Chen

Large language model (LLM) unlearning has become a critical mechanism for removing undesired data, knowledge, or behaviors from pre-trained models while retaining their general utility. Yet, with the rise of open-weight LLMs, we ask: can…

Machine Learning · Computer Science 2025-10-21 Bingqi Shang , Yiwei Chen , Yihua Zhang , Bingquan Shen , Sijia Liu

Large Language Models (LLMs) are known to contain significant redundancy, yet a systematic explanation for why certain components, particularly in higher layers, are more redundant has remained elusive. In this work, we identify the BOS…

Computation and Language · Computer Science 2026-01-13 Jaewon Sok , Jewon Yeom , Seonghyeon Park , Jeongjae Park , Taesup Kim

Hallucinations in Speech Large Language Models (SpeechLLMs) pose significant risks, yet existing detection methods typically rely on gold-standard outputs that are costly or impractical to obtain. Moreover, hallucination detection methods…

Computation and Language · Computer Science 2026-04-22 Jonas Waldendorf , Bashar Awwad Shiekh Hasan , Evgenii Tsymbalov

Transformer-based Large Language Models (LLMs) are the state-of-the-art for natural language tasks. Recent work has attempted to decode, by reverse engineering the role of linear layers, the internal mechanisms by which LLMs arrive at their…

Computation and Language · Computer Science 2023-10-26 Mansi Sakarvadia , Arham Khan , Aswathy Ajith , Daniel Grzenda , Nathaniel Hudson , André Bauer , Kyle Chard , Ian Foster

Vision-language models (VLMs) typically encode substantially more visual tokens than text tokens, resulting in significant token redundancy. Pruning uninformative visual tokens is therefore crucial for improving computational efficiency,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-19 Kai Zhao , Wubang Yuan , Yuchen Lin , Liting Ruan , Xiaofeng Lu , Deng-Ping Fan , Ming-Ming Cheng , Dan Zeng

Attention is a state of arousal capable of dealing with limited processing bottlenecks in human beings by focusing selectively on one piece of information while ignoring other perceptible information. For decades, concepts and functions of…

Machine Learning · Computer Science 2021-12-14 Alana Santana , Esther Colombini

Large language models frequently exhibit hallucinations: fluent and confident outputs that are factually incorrect or unsupported by the input context. While recent hallucination detection methods have explored various features derived from…

Computation and Language · Computer Science 2026-04-14 Jakub Binkowski , Kamil Adamczewski , Tomasz Kajdanowicz

Large language models (LLMs) have demonstrated strong performance on a variety of natural language processing (NLP) tasks. However, they often struggle with long-text sequences due to the ``lost in the middle'' phenomenon. This issue has…

Computation and Language · Computer Science 2025-12-16 Zewen Qiang , Sendong Zhao , Haochun Wang , Bing Qin , Ting Liu

Hallucination detection is critical for ensuring the reliability of large language models (LLMs) in context-based generation. Prior work has explored intrinsic signals available during generation, among which attention offers a direct view…

Computation and Language · Computer Science 2026-02-23 Siya Qi , Yudong Chen , Runcong Zhao , Qinglin Zhu , Zhanghao Hu , Wei Liu , Yulan He , Zheng Yuan , Lin Gui

Understanding the decision-making processes of large language models (LLMs) is essential for their trustworthy development and deployment. However, current interpretability methods often face challenges such as low resolution and high…

Computation and Language · Computer Science 2025-10-14 Tian Lan , Jinyuan Xu , Xue He , Jenq-Neng Hwang , Lei Li

Despite the rapid evolution of training paradigms, the decoder backbone of large vision--language models (LVLMs) remains fundamentally rooted in the residual-connection Transformer architecture. Therefore, deciphering the distinct roles of…

Artificial Intelligence · Computer Science 2026-05-08 Gongli Xi , Ye Tian , Mengyu Yang , Huahui Yi , Liang Lin , Xiaoshuai Hao , Kun Wang , Wendong Wang