Context Learning

In-context learning (ICL) is a paradigm shift in machine learning, focusing on enabling models to adapt to new tasks using only a few examples provided within the input, without requiring parameter updates. Current research emphasizes understanding ICL's mechanisms, particularly within transformer-based large language models, and improving its effectiveness through techniques like enhanced example selection, chain-of-thought prompting, and addressing issues such as spurious correlations and copy bias. This research is significant because ICL offers a more efficient and adaptable approach to many machine learning problems, impacting fields ranging from natural language processing and computer vision to scientific computing and beyond.

Papers

May 22, 2023

May 21, 2023

May 19, 2023

May 18, 2023

May 17, 2023

May 16, 2023

May 15, 2023

May 10, 2023

Multilingual LLMs are Better Cross-lingual In-context Learners with Alignment
Eshaan Tanwar, Subhabrata Dutta, Manish Borthakur, Tanmoy Chakraborty
Large Language Model Context Learning Alignment Problem Multilingual LLM Multilingual Context Cross Lingual Text Classification

May 8, 2023

Context Learning

Papers

Iterative Forward Tuning Boosts In-Context Learning in Language Models

Meta-in-context learning in large language models

Explaining Emergent In-Context Learning as Kernel Regression

Can We Edit Factual Knowledge by In-Context Learning?

PRODIGY: Enabling In-context Learning Over Graphs

Enhancing Few-shot Text-to-SQL Capabilities of Large Language Models: A Study on Prompt Design Strategies

ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings

PlugMed: Improving Specificity in Patient-Centered Medical Dialogue Generation using In-Context Learning

Post Hoc Explanations of Language Models Can Improve Language Models

Efficient Prompting via Dynamic In-Context Learning

Learning In-context Learning for Named Entity Recognition

Temporal Knowledge Graph Forecasting Without Knowledge Using In-Context Learning

Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback

What In-Context Learning "Learns" In-Context: Disentangling Task Recognition and Task Learning

Pre-Training to Learn in Context

Small Models are Valuable Plug-ins for Large Language Models

Text Classification via Large Language Models

Multilingual LLMs are Better Cross-lingual In-context Learners with Alignment

GersteinLab at MEDIQA-Chat 2023: Clinical Note Summarization from Doctor-Patient Conversations through Fine-tuning and In-context Learning

How Do In-Context Examples Affect Compositional Generalization?