Buchumschlag

DeCoVec: Building Decoding Space based Task Vector for Large Language Models via In-Context Learning

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Li, Feiyang, Wang, Yile
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

AnchorMem: Anchored Facts with Associative Contexts for Building Memory in Large Language Models
von: Shen, Zhanyu, et al.
Veröffentlicht: (2026)

VecGlypher: Unified Vector Glyph Generation with Language Models
von: Huang, Xiaoke, et al.
Veröffentlicht: (2026)

Ranked Voting based Self-Consistency of Large Language Models
von: Wang, Weiqin, et al.
Veröffentlicht: (2025)

Reasoning in Conversation: Solving Subjective Tasks through Dialogue Simulation for Large Language Models
von: Wang, Xiaolong, et al.
Veröffentlicht: (2024)

Perspective Transition of Large Language Models for Solving Subjective Tasks
von: Wang, Xiaolong, et al.
Veröffentlicht: (2025)

Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective
von: Han, Seungwook, et al.
Veröffentlicht: (2024)

Assessment of Generative Named Entity Recognition in the Era of Large Language Models
von: Zhan, Qi, et al.
Veröffentlicht: (2026)

Gram2Vec: An Interpretable Document Vectorizer
von: Zeng, Peter, et al.
Veröffentlicht: (2024)

Does In-Context Learning Really Learn? Rethinking How Large Language Models Respond and Solve Tasks via In-Context Learning
von: Long, Quanyu, et al.
Veröffentlicht: (2024)

Language Models Implement Simple Word2Vec-style Vector Arithmetic
von: Merullo, Jack, et al.
Veröffentlicht: (2023)

Exploring Context Window of Large Language Models via Decomposed Positional Vectors
von: Dong, Zican, et al.
Veröffentlicht: (2024)

Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrieval
von: Liu, Zheng, et al.
Veröffentlicht: (2023)

CoCoA: Confidence and Context-Aware Adaptive Decoding for Resolving Knowledge Conflicts in Large Language Models
von: Khandelwal, Anant, et al.
Veröffentlicht: (2025)

One Task Vector is not Enough: A Large-Scale Study for In-Context Learning
von: Tikhonov, Pavel, et al.
Veröffentlicht: (2025)

AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code
von: Li, Shangzhan, et al.
Veröffentlicht: (2026)

Decoding In-Context Learning: Neuroscience-inspired Analysis of Representations in Large Language Models
von: Yousefi, Safoora, et al.
Veröffentlicht: (2023)

Adaptive Task Vectors for Large Language Models
von: Kang, Joonseong, et al.
Veröffentlicht: (2025)

AttriLens-Mol: Attribute Guided Reinforcement Learning for Molecular Property Prediction with Large Language Models
von: Lin, Xuan, et al.
Veröffentlicht: (2025)

LLM2Vec-Gen: Generative Embeddings from Large Language Models
von: BehnamGhader, Parishad, et al.
Veröffentlicht: (2026)

Label Words as Local Task Vectors in In-Context Learning
von: Zheng, Bowen, et al.
Veröffentlicht: (2024)

Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models
von: Li, Jiaqian, et al.
Veröffentlicht: (2026)

DySem: Uncovering Dynamic Semantic Components of Large Language Models for Calculating Semantic Textual Similarity
von: Zheng, Kaijie, et al.
Veröffentlicht: (2026)

IndiVec: An Exploration of Leveraging Large Language Models for Media Bias Detection with Fine-Grained Bias Indicators
von: Lin, Luyang, et al.
Veröffentlicht: (2024)

Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models
von: Huang, Yanwen, et al.
Veröffentlicht: (2025)

Element2Vec: Build Chemical Element Representation from Text for Property Prediction
von: Li, Yuanhao, et al.
Veröffentlicht: (2025)

Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning
von: Yang, Haolin, et al.
Veröffentlicht: (2025)

VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization
von: Yao, Dingyu, et al.
Veröffentlicht: (2025)

GT2Vec: Large Language Models as Multi-Modal Encoders for Text and Graph-Structured Data
von: Lin, Jiacheng, et al.
Veröffentlicht: (2024)

Causal2Vec: Improving Decoder-only LLMs as Embedding Models through a Contextual Token
von: Lin, Ailiang, et al.
Veröffentlicht: (2025)

VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks
von: Jiang, Ziyan, et al.
Veröffentlicht: (2024)

LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
von: BehnamGhader, Parishad, et al.
Veröffentlicht: (2024)

Advancing Multimodal In-Context Learning in Large Vision-Language Models with Task-aware Demonstrations
von: Li, Yanshu
Veröffentlicht: (2025)

Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages
von: Zhang, Yuanchi, et al.
Veröffentlicht: (2024)

Parallel Decoding via Hidden Transfer for Lossless Large Language Model Acceleration
von: Wu, Pengfei, et al.
Veröffentlicht: (2024)

GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models
von: Li, Shilong, et al.
Veröffentlicht: (2024)

Beyond In-Context Learning: Aligning Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelines
von: Long, Do Xuan, et al.
Veröffentlicht: (2025)

CoT-RAG: Integrating Chain of Thought and Retrieval-Augmented Generation to Enhance Reasoning in Large Language Models
von: Li, Feiyang, et al.
Veröffentlicht: (2025)

Visual In-Context Learning for Large Vision-Language Models
von: Zhou, Yucheng, et al.
Veröffentlicht: (2024)

SemPA: Improving Sentence Embeddings of Large Language Models through Semantic Preference Alignment
von: Chen, Ziyang, et al.
Veröffentlicht: (2026)

Speak It Out: Solving Symbol-Related Problems with Symbol-to-Language Conversion for Language Models
von: Wang, Yile, et al.
Veröffentlicht: (2024)