Imagen de Portada

Distilling Many-Shot In-Context Learning into a Cheat Sheet

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Honda, Ukyo, Murakami, Soichiro, Zhang, Peinan
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

FaithCAMERA: Construction of a Faithful Dataset for Ad Text Generation
por: Kato, Akihiko, et al.
Publicado: (2024)

Does Self-Consistency Improve the Recall of Encyclopedic Knowledge?
por: Hoshino, Sho, et al.
Publicado: (2026)

Exploring the Relationship Between Diversity and Quality in Ad Text Generation
por: Aoki, Yoichi, et al.
Publicado: (2025)

Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding
por: Jinnai, Yuu, et al.
Publicado: (2024)

Not Eliminate but Aggregate: Post-Hoc Control over Mixture-of-Experts to Address Shortcut Shifts in Natural Language Understanding
por: Honda, Ukyo, et al.
Publicado: (2024)

Exploring Explanations Improves the Robustness of In-Context Learning
por: Honda, Ukyo, et al.
Publicado: (2025)

Striking Gold in Advertising: Standardization and Exploration of Ad Text Generation
por: Mita, Masato, et al.
Publicado: (2023)

Cross-lingual Transfer or Machine Translation? On Data Augmentation for Monolingual Semantic Textual Similarity
por: Hoshino, Sho, et al.
Publicado: (2024)

Routing by Analogy: kNN-Augmented Expert Assignment for Mixture-of-Experts
por: Lyu, Boxuan, et al.
Publicado: (2026)

Revisiting the Capacity Gap in Chain-of-Thought Distillation from a Practical Perspective
por: Kajitsuka, Tokio, et al.
Publicado: (2026)

Toward LLMs Beyond English-Centric Development
por: Takase, Sho, et al.
Publicado: (2026)

AdParaphrase v2.0: Generating Attractive Ad Texts Using a Preference-Annotated Paraphrase Dataset
por: Murakami, Soichiro, et al.
Publicado: (2025)

Annotation-Efficient Language Model Alignment via Diverse and Representative Response Texts
por: Jinnai, Yuu, et al.
Publicado: (2024)

AdParaphrase: Paraphrase Dataset for Analyzing Linguistic Features toward Generating Attractive Ad Texts
por: Murakami, Soichiro, et al.
Publicado: (2025)

Reinforcement Learning for Edit-Based Non-Autoregressive Neural Machine Translation
por: Wang, Hao, et al.
Publicado: (2024)

Many-Shot In-Context Learning
por: Agarwal, Rishabh, et al.
Publicado: (2024)

On Many-Shot In-Context Learning for Long-Context Evaluation
por: Zou, Kaijian, et al.
Publicado: (2024)

On the True Distribution Approximation of Minimum Bayes-Risk Decoding
por: Ohashi, Atsumoto, et al.
Publicado: (2024)

A Single Linear Layer Yields Task-Adapted Low-Rank Matrices
por: Kim, Hwichan, et al.
Publicado: (2024)

Efficient Many-Shot In-Context Learning with Dynamic Block-Sparse Attention
por: Xiao, Emily, et al.
Publicado: (2025)

Selecting Demonstrations for Many-Shot In-Context Learning via Gradient Matching
por: Zhang, Jianfei, et al.
Publicado: (2025)

Many-Shot In-Context Learning for Molecular Inverse Design
por: Moayedpour, Saeed, et al.
Publicado: (2024)

Model-Based Minimum Bayes Risk Decoding for Text Generation
por: Jinnai, Yuu, et al.
Publicado: (2023)

An Empirical Study of Many-Shot In-Context Learning for Machine Translation of Low-Resource Languages
por: Lu, Yinhan, et al.
Publicado: (2026)

Out-of-the-Box Conditional Text Embeddings from Large Language Models
por: Yamada, Kosuke, et al.
Publicado: (2025)

Towards Compute-Optimal Many-Shot In-Context Learning
por: Golchin, Shahriar, et al.
Publicado: (2025)

In-Context Learning Distillation for Efficient Few-Shot Fine-Tuning
por: Duan, Yifei, et al.
Publicado: (2024)

Many-Shot In-Context Learning in Multimodal Foundation Models
por: Jiang, Yixing, et al.
Publicado: (2024)

GAIN: A Benchmark for Goal-Aligned Decision-Making of Large Language Models under Imperfect Norms
por: Kawarada, Masayuki, et al.
Publicado: (2026)

Can Many-Shot In-Context Learning Help LLMs as Evaluators? A Preliminary Empirical Study
por: Song, Mingyang, et al.
Publicado: (2024)

Scaling Laws for Many-Shot In-Context Learning with Self-Generated Annotations
por: Gu, Zhengyao, et al.
Publicado: (2025)

Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning
por: Huang, Brandon, et al.
Publicado: (2024)

More is not always better? Enhancing Many-Shot In-Context Learning with Differentiated and Reweighting Objectives
por: Zhang, Xiaoqing, et al.
Publicado: (2025)

CaughtCheating: Is Your MLLM a Good Cheating Detective? Exploring the Boundary of Visual Perception and Reasoning
por: Li, Ming, et al.
Publicado: (2025)

Many-Shot Regurgitation (MSR) Prompting
por: Sonkar, Shashank, et al.
Publicado: (2024)

Oogiri-Master: Benchmarking Humor Understanding via Oogiri
por: Murakami, Soichiro, et al.
Publicado: (2025)

Who Laughs with Whom? Disentangling Influential Factors in Humor Preferences across User Clusters and LLMs
por: Murakami, Soichiro, et al.
Publicado: (2026)

Improving In-Context Learning with Reasoning Distillation
por: Sadeq, Nafis, et al.
Publicado: (2025)

In-Context Learning for Few-Shot Nested Named Entity Recognition
por: Zhang, Meishan, et al.
Publicado: (2024)

What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMs
por: Kim, Sangyeop, et al.
Publicado: (2025)