Image de couverture de livre

Provable Benefits of Task-Specific Prompts for In-context Learning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chang, Xiangyu, Li, Yingcong, Kara, Muti, Oymak, Samet, Roy-Chowdhury, Amit K.
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

When and How Unlabeled Data Provably Improve In-Context Learning
par: Li, Yingcong, et autres
Publié: (2025)

Fine-grained Analysis of In-context Linear Estimation: Data, Architecture, and Beyond
par: Li, Yingcong, et autres
Publié: (2024)

Gating is Weighting: Understanding Gated Linear Attention through In-context Learning
par: Li, Yingcong, et autres
Publié: (2025)

Transformers as Support Vector Machines
par: Tarzanagh, Davoud Ataee, et autres
Publié: (2023)

From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers
par: Ildiz, M. Emrullah, et autres
Publié: (2024)

Mechanics of Next Token Prediction with Self-Attention
par: Li, Yingcong, et autres
Publié: (2024)

Selective Attention: Enhancing Transformer through Principled Context Control
par: Zhang, Xuechen, et autres
Publié: (2024)

Extrapolation by Association: Length Generalization Transfer in Transformers
par: Cai, Ziyang, et autres
Publié: (2025)

PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts
par: Chowdhury, Anjir Ahmed, et autres
Publié: (2026)

Enabling Intrinsic Reasoning over Dense Geospatial Embeddings with DFR-Gemma
par: Zhang, Xuechen, et autres
Publié: (2026)

Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning
par: Zhang, Xuechen, et autres
Publié: (2024)

Fusion Steering: Prompt-Specific Activation Control
par: Chang, Waldemar, et autres
Publié: (2025)

SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG
par: Zhang, Xuechen, et autres
Publié: (2025)

Task Facet Learning: A Structured Approach to Prompt Optimization
par: Juneja, Gurusha, et autres
Publié: (2024)

Automatic Prompt Engineering with No Task Cues and No Tuning
par: Chowdhury, Faisal, et autres
Publié: (2026)

Mitigating Participation Imbalance Bias in Asynchronous Federated Learning
par: Chang, Xiangyu, et autres
Publié: (2025)

Plug-and-Play Transformer Modules for Test-Time Adaptation
par: Chang, Xiangyu, et autres
Publié: (2024)

Attention with Trained Embeddings Provably Selects Important Tokens
par: Wu, Diyuan, et autres
Publié: (2025)

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

Jatmo: Prompt Injection Defense by Task-Specific Finetuning
par: Piet, Julien, et autres
Publié: (2023)

FIBER: A Multilingual Evaluation Resource for Factual Inference Bias
par: Munis, Evren Ayberk, et autres
Publié: (2025)

Prompt Recursive Search: A Living Framework with Adaptive Growth in LLM Auto-Prompting
par: Zhao, Xiangyu, et autres
Publié: (2024)

StaICC: Standardized Evaluation for Classification Task in In-context Learning
par: Cho, Hakaze, et autres
Publié: (2025)

A Survey on In-context Learning
par: Dong, Qingxiu, et autres
Publié: (2022)

ICPC: In-context Prompt Compression with Faster Inference
par: Yu, Ziyang, et autres
Publié: (2025)

Benchmarking Large Language Models on Multiple Tasks in Bioinformatics NLP with Prompting
par: Jiang, Jiyue, et autres
Publié: (2025)

What Was Your Prompt? A Remote Keylogging Attack on AI Assistants
par: Weiss, Roy, et autres
Publié: (2024)

Long-context LLMs Struggle with Long In-context Learning
par: Li, Tianle, et autres
Publié: (2024)

Conformal P-Value in Multiple-Choice Question Answering Tasks with Provable Risk Control
par: Ye, Yuanchang
Publié: (2025)

Can LLMs Generate High-Quality Task-Specific Conversations?
par: Li, Shengqi, et autres
Publié: (2025)

Mechanism of Task-oriented Information Removal in In-context Learning
par: Cho, Hakaze, et autres
Publié: (2025)

Beyond Captioning: Task-Specific Prompting for Improved VLM Performance in Mathematical Reasoning
par: Singh, Ayush, et autres
Publié: (2024)

PromptGuard at BLP-2025 Task 1: A Few-Shot Classification Framework Using Majority Voting and Keyword Similarity for Bengali Hate Speech Detection
par: Hossan, Rakib, et autres
Publié: (2025)

Enhancing Few-Shot Transfer Learning with Optimized Multi-Task Prompt Tuning through Modular Prompt Composition
par: Pouramini, Ahmad, et autres
Publié: (2024)

Beyond One-Size-Fits-All Summarization: Customizing Summaries for Diverse Users
par: Duran, Mehmet Samet, et autres
Publié: (2025)

RAG-based Crowdsourcing Task Decomposition via Masked Contrastive Learning with Prompts
par: Yang, Jing, et autres
Publié: (2024)

Outlier Dimensions Encode Task-Specific Knowledge
par: Rudman, William, et autres
Publié: (2023)

Dynamic Task Vector Grouping for Efficient Multi-Task Prompt Tuning
par: Zhang, Pieyi, et autres
Publié: (2025)

DETAIL: Task DEmonsTration Attribution for Interpretable In-context Learning
par: Zhou, Zijian, et autres
Publié: (2024)

FOSSIL: Harnessing Feedback on Suboptimal Samples for Data-Efficient Generalisation with Imitation Learning for Embodied Vision-and-Language Tasks
par: McCallum, Sabrina, et autres
Publié: (2025)