paper-with-me

Papers

On the token distance modeling ability of higher RoPE attention dimension

2024-10-11 · Xiangyu Hong, Che Jiang, Biqing Qi, Fandong Meng, Mo Yu, BoWen Zhou, Jie zhou

Length extrapolation algorithms based on Rotary position embedding (RoPE) have shown promising results in extending the context length of language models. However, understanding how position embedding can capture longer-range contextual information remains elusive. Based on the intuition that different dimensions correspond to different frequency of changes in RoPE encoding, we conducted a dimension-level analysis to investigate the correlation between a hidden dimension of an attention head and its contribution to capturing long-distance dependencies. Using our correlation metric, we identified a particular type of attention heads, which we named Positional Heads, from various length-extrapolated models. These heads exhibit a strong focus on long-range information interaction and play a pivotal role in long input processing, as evidence by our ablation. We further demonstrate the correlation between the efficiency of length extrapolation and the extension of the high-dimensional attention allocation of these heads. The identification of Positional Heads provides insights for future research in long-text comprehension.

📄 PDF Abstract BibTeX arXiv:2410.08703

Code (0)

등록된 구현이 없습니다.

Tasks

PositionReading Comprehension

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
Focus 설명 없음

Similar Papers 제목 키워드 기반

Mitigating Object Hallucination via Concentric Causal Attention

2024-10-21 · Yun Xing, Yiheng Li, Ivan Laptev, Shijian Lu

Recent Large Vision Language Models (LVLMs) present remarkable zero-shot conversational and reasoning capabilities given multimodal queries. Nevertheless, they suffer from object hallucination, a phenomenon where LVLMs a…

HallucinationObjectObject Hallucination

Remember Me: Bridging the Long-Range Gap in LVLMs with Three-Step Inference-Only Decay Resilience Strategies

2025-11-13 · Peng Gao, Yujian Lee, Xiaofeng Zhang, Zailong Chen 외 arxiv

Large Vision-Language Models (LVLMs) have achieved impressive performance across a wide range of multimodal tasks. However, they still face critical challenges in modeling long-range dependencies under the usage of Rotar…

Question Answering

A Hybrid Algorithm for Matching Arabic Names

2013-09-22 · T. El-Shishtawy

In this paper, a new hybrid algorithm which combines both of token-based and character-based approaches is presented. The basic Levenshtein approach has been extended to token-based distance metric. The distance metric i…

TCDA: Thread-Constrained Discourse-Aware Modeling for Conversational Sentiment Quadruple Analysis

2026-05-03 · Xinran Li, Xinze Che, Yifan Lyu, Zhiqi Huang 외 arxiv

Conversational Aspect-based Sentiment Quadruple Analysis (DiaASQ) needs to capture the complex interrelationships in multiple rounds of dialogues. Existing methods usually employ simple Graph Convolutional Networks (GCN)…

DA-Transformer: Distance-aware Transformer

2020-10-14 · NAACL 2021 4 · Chuhan Wu, Fangzhao Wu, Yongfeng Huang

Transformer has achieved great success in the NLP field by composing various advanced models like BERT and GPT. However, Transformer and its existing variants may not be optimal in capturing token distances because the p…