Image de couverture de livre

Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Han, Seungwook, Song, Jinyeop, Gore, Jeff, Agrawal, Pulkit
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Training Language Models via Neural Cellular Automata
par: Lee, Dan, et autres
Publié: (2026)

Value Augmented Sampling for Language Model Alignment and Personalization
par: Han, Seungwook, et autres
Publié: (2024)

A Resource Model For Neural Scaling Law
par: Song, Jinyeop, et autres
Publié: (2024)

Estimating the Empowerment of Language Model Agents
par: Song, Jinyeop, et autres
Publié: (2025)

RAVEN: In-Context Learning with Retrieval-Augmented Encoder-Decoder Language Models
par: Huang, Jie, et autres
Publié: (2023)

Superposition Yields Robust Neural Scaling
par: Liu, Yizhou, et autres
Publié: (2025)

Encoder vs Decoder: Comparative Analysis of Encoder and Decoder Language Models on Multilingual NLU Tasks
par: Nielsen, Dan Saattrup, et autres
Publié: (2024)

The Blessing of Dimensionality in LLM Fine-tuning: A Variance-Curvature Perspective
par: Liang, Qiyao, et autres
Publié: (2026)

In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
par: Liu, Sheng, et autres
Publié: (2023)

Understanding Emergent In-Context Learning from a Kernel Regression Perspective
par: Han, Chi, et autres
Publié: (2023)

Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning
par: Huang, Brandon, et autres
Publié: (2024)

Vector Policy Optimization: Training for Diversity Improves Test-Time Search
par: Bahlous-Boldi, Ryan, et autres
Publié: (2026)

TURNA: A Turkish Encoder-Decoder Language Model for Enhanced Understanding and Generation
par: Uludoğan, Gökçe, et autres
Publié: (2024)

Predicting Task Performance with Context-aware Scaling Laws
par: Montgomery, Kyle, et autres
Publié: (2025)

Training on the Test Task Confounds Evaluation and Emergence
par: Dominguez-Olmedo, Ricardo, et autres
Publié: (2024)

Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures
par: Bronzini, Marco, et autres
Publié: (2025)

A Theoretical Perspective for Speculative Decoding Algorithm
par: Yin, Ming, et autres
Publié: (2024)

Evaluating the Effectiveness of XAI Techniques for Encoder-Based Language Models
par: Mersha, Melkamu Abay, et autres
Publié: (2025)

Spiffy: Multiplying Diffusion LLM Acceleration via Lossless Speculative Decoding
par: Agrawal, Sudhanshu, et autres
Publié: (2025)

Decoding-based Regression
par: Song, Xingyou, et autres
Publié: (2025)

Small Encoders Can Rival Large Decoders in Detecting Groundedness
par: Abbes, Istabrak, et autres
Publié: (2025)

Curry-DPO: Enhancing Alignment using Curriculum Learning & Ranked Preferences
par: Pattnaik, Pulkit, et autres
Publié: (2024)

GATech at AbjadMed: Bidirectional Encoders vs. Causal Decoders: Insights from 82-Class Arabic Medical Classification
par: Khamis, Ahmed Khaled
Publié: (2026)

Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs
par: Siddique, Zara, et autres
Publié: (2025)

Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning
par: Geng, Saibo, et autres
Publié: (2023)

Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition
par: Xiong, Zheyang, et autres
Publié: (2024)

KV Cache Offloading for Context-Intensive Tasks
par: Bocharnikov, Andrey, et autres
Publié: (2026)

Curiosity-driven Red-teaming for Large Language Models
par: Hong, Zhang-Wei, et autres
Publié: (2024)

Can Generative AI Solve Your In-Context Learning Problem? A Martingale Perspective
par: Jesson, Andrew, et autres
Publié: (2024)

Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics
par: Nair, Jishnu Sethumadhavan, et autres
Publié: (2026)

LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
par: Yang, Penghui, et autres
Publié: (2025)

The Unreasonable Effectiveness of Easy Training Data for Hard Tasks
par: Hase, Peter, et autres
Publié: (2024)

Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts
par: Chen, Yingfa, et autres
Publié: (2026)

Task-Aware LoRA Adapter Composition via Similarity Retrieval in Vector Databases
par: Adsul, Riya, et autres
Publié: (2026)

100-LongBench: Are de facto Long-Context Benchmarks Literally Evaluating Long-Context Ability?
par: Yang, Wang, et autres
Publié: (2025)

Beyond Next Word Prediction: Developing Comprehensive Evaluation Frameworks for measuring LLM performance on real world applications
par: Agrawal, Vishakha, et autres
Publié: (2025)

Illuminate: A novel approach for depression detection with explainable analysis and proactive therapy using prompt engineering
par: Agrawal, Aryan
Publié: (2024)

Language Models as Hierarchy Encoders
par: He, Yuan, et autres
Publié: (2024)

Towards More Effective Table-to-Text Generation: Assessing In-Context Learning and Self-Evaluation with Open-Source Models
par: Iravani, Sahar, et autres
Publié: (2024)

Is In-Context Learning Learning?
par: de Wynter, Adrian
Publié: (2025)