paper-with-me

홈 › Papers

Attention Heads of Large Language Models: A Survey

2024-09-05 · Zifan Zheng, Yezhaohui Wang, Yuxin Huang, Shichao Song, MingChuan Yang, Bo Tang, Feiyu Xiong, Zhiyu Li

Since the advent of ChatGPT, Large Language Models (LLMs) have excelled in various tasks but remain as black-box systems. Understanding the reasoning bottlenecks of LLMs has become a critical challenge, as these limitations are deeply tied to their internal architecture. Among these, attention heads have emerged as a focal point for investigating the underlying mechanics of LLMs. In this survey, we aim to demystify the internal reasoning processes of LLMs by systematically exploring the roles and mechanisms of attention heads. We first introduce a novel four-stage framework inspired by the human thought process: Knowledge Recalling, In-Context Identification, Latent Reasoning, and Expression Preparation. Using this framework, we comprehensively review existing research to identify and categorize the functions of specific attention heads. Additionally, we analyze the experimental methodologies used to discover these special heads, dividing them into two categories: Modeling-Free and Modeling-Required methods. We further summarize relevant evaluation methods and benchmarks. Finally, we discuss the limitations of current research and propose several potential future directions.

📄 PDF Abstract BibTeX arXiv:2409.03752

Code (1)

iaar-shanghai/awesome-attention-heads 공식 구현

Tasks

Survey

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Interpreting Language Models Through Concept Descriptions: A Survey

2025-10-01 · Nils Feldhus, Laura Kopf arxiv

Understanding the decision-making processes of neural networks is a central goal of mechanistic interpretability. In the context of Large Language Models (LLMs), this involves uncovering the underlying mechanisms and ide…

Identifying Semantic Induction Heads to Understand In-Context Learning

2024-02-20 · Jie Ren, Qipeng Guo, Hang Yan, Dongrui Liu 외

Although large language models (LLMs) have demonstrated remarkable performance, the lack of transparency in their inference logic raises concerns about their trustworthiness. To gain a better understanding of LLMs, we co…

In-Context LearningKnowledge Graphs

KV Shifting Attention Enhances Language Modeling

2024-11-29 · Mingyu Xu, Wei Cheng, Bingning Wang, WeiPeng Chen

The current large language models are mainly based on decode-only structure transformers, which have great in-context learning (ICL) capabilities. It is generally believed that the important foundation of its ICL capabil…

In-Context LearningLanguage ModelingLanguage Modelling

Interpreting Attention Heads for Image-to-Text Information Flow in Large Vision-Language Models

2025-09-22 · Jinyeong Kim, Seil Kang, Jiwoo Park, Junhyeok Kim 외 arxiv

Large Vision-Language Models (LVLMs) answer visual questions by transferring information from images to text through a series of attention heads. While this image-to-text information flow is central to visual question an…

Visual Question Answering

Toward Localizing and Repairing Bias in Transformer Attention Heads

2026-07-14 · Sigma Jahan arxiv

Transformer language models are increasingly used as software components, yet biased outputs remain difficult to localize and repair inside the model. Existing fairness testing and repair methods largely operate at the i…