Copertina

Attention Basin: Why Contextual Position Matters in Large Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yi, Zihao, Zeng, Delong, Ling, Zhenqing, Luo, Haohao, Xu, Zhe, Liu, Wei, Luan, Jian, Cao, Wanxia, Shen, Ying
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MindGYM: What Matters in Question Synthesis for Thinking-Centric Fine-Tuning?
di: Xu, Zhe, et al.
Pubblicazione: (2025)

On the Convergence of Zeroth-Order Federated Tuning for Large Language Models
di: Ling, Zhenqing, et al.
Pubblicazione: (2024)

A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems
di: Yi, Zihao, et al.
Pubblicazione: (2024)

Intent-driven In-context Learning for Few-shot Dialogue State Tracking
di: Yi, Zihao, et al.
Pubblicazione: (2024)

Video-LevelGauge: Investigating Contextual Positional Bias in Large Video Language Models
di: Xia, Hou, et al.
Pubblicazione: (2025)

Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined Data
di: Ling, Zhenqing, et al.
Pubblicazione: (2025)

Delta-K: Boosting Multi-Instance Generation via Cross-Attention Augmentation
di: Wang, Zitong, et al.
Pubblicazione: (2026)

Position: Open and Closed Large Language Models in Healthcare
di: Xu, Jiawei, et al.
Pubblicazione: (2025)

Enhancing Multimodal Retrieval via Complementary Information Extraction and Alignment
di: Zeng, Delong, et al.
Pubblicazione: (2026)

Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey
di: Kuang, Jiayi, et al.
Pubblicazione: (2024)

Targeted Poverty Alleviation and Analyst Attention
di: Hui Wang, et al.
Pubblicazione: (2026)

C$^2$-Cite: Contextual-Aware Citation Generation for Attributed Large Language Models
di: Yu, Yue, et al.
Pubblicazione: (2025)

Cooperative Photoredox and Cobalt‐Catalyzed Acceptorless Dehydrogenative Functionalization of Cyclopropylamides towards Allylic N,O‐Acyl‐acetal Derivatives
di: Haohao Huang, et al.
Pubblicazione: (2024)

Cooperative Photoredox and Cobalt‐Catalyzed Acceptorless Dehydrogenative Functionalization of Cyclopropylamides towards Allylic N,O‐Acyl‐acetal Derivatives
di: Haohao Huang, et al.
Pubblicazione: (2024)

Dynamic Demonstration Retrieval and Cognitive Understanding for Emotional Support Conversation
di: Xu, Zhe, et al.
Pubblicazione: (2024)

Enhancing HOI Detection with Contextual Cues from Large Vision-Language Models
di: Zhan, Yu-Wei, et al.
Pubblicazione: (2023)

On the Higher-Rank Askey-Wilson Algebras
di: Wang, Wanxia, et al.
Pubblicazione: (2024)

Game changers or money pits? Asymmetric impact of sports facilities investment on football revenue
di: Wanxia Tang, et al.
Pubblicazione: (2024)

Making Large Vision Language Models to be Good Few-shot Learners
di: Liu, Fan, et al.
Pubblicazione: (2024)

Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations
di: Shen, Bowen, et al.
Pubblicazione: (2024)

Learning Positional Attention for Sequential Recommendation
di: Luo, Fan, et al.
Pubblicazione: (2024)

Continuous Embedding Attacks via Clipped Inputs in Jailbreaking Large Language Models
di: Xu, Zihao, et al.
Pubblicazione: (2024)

Scaling Model and Data for Multilingual Machine Translation with Open Large Language Models
di: Shang, Yuzhe, et al.
Pubblicazione: (2026)

Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study
di: Cui, Menglong, et al.
Pubblicazione: (2025)

Contextual Attention Modulation: Towards Efficient Multi-Task Adaptation in Large Language Models
di: Pan, Dayan, et al.
Pubblicazione: (2025)

Position IDs Matter: An Enhanced Position Layout for Efficient Context Compression in Large Language Models
di: Zhao, Runsong, et al.
Pubblicazione: (2024)

IntentRL: Training Proactive User-intent Agents for Open-ended Deep Research via Reinforcement Learning
di: Luo, Haohao, et al.
Pubblicazione: (2026)

BOTS: A Unified Framework for Bayesian Online Task Selection in LLM Reinforcement Finetuning
di: Shen, Qianli, et al.
Pubblicazione: (2025)

Position: Contextual Integrity is Inadequately Applied to Language Models
di: Shvartzshnaider, Yan, et al.
Pubblicazione: (2025)

PIP: Perturbation-based Iterative Pruning for Large Language Models
di: Cao, Yi, et al.
Pubblicazione: (2025)

Measuring Political Bias in Large Language Models: What Is Said and How It Is Said
di: Bang, Yejin, et al.
Pubblicazione: (2024)

SA-MDKIF: A Scalable and Adaptable Medical Domain Knowledge Injection Framework for Large Language Models
di: Xu, Tianhan, et al.
Pubblicazione: (2024)

Reverse Physician-AI Relationship: Full-process Clinical Diagnosis Driven by a Large Language Model
di: Xu, Shicheng, et al.
Pubblicazione: (2025)

Non‐state shareholder governance and technological innovations of state‐owned enterprises: The moderating effect of executive compensation incentives
di: Zhenqing Liu, et al.
Pubblicazione: (2024)

Study on Vibration Control of Wind Turbine With an Optimised Eddy Current Tuned Rolling Cylinder Damper
di: Zhenqing Liu, et al.
Pubblicazione: (2025)

Development and Application of the GIS-Based Water Mass Analysis Integrated System.
di: Zhang, Yuexia, et al.
Pubblicazione: (2008)

Stable Knowledge Editing in Large Language Models
di: Wei, Zihao, et al.
Pubblicazione: (2024)

A Curcumin‐Derived HSP70 Inhibitor Disrupts Lysosomal Function to Suppress Triple‐Negative Breast Cancer Progression
di: Zijian Li, et al.
Pubblicazione: (2026)

Contextual Object Detection with Multimodal Large Language Models
di: Zang, Yuhang, et al.
Pubblicazione: (2023)

KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Models
di: Chen, Weijie, et al.
Pubblicazione: (2024)