Dissecting In-Context Learning of Translations in GPTs
Paper
•
2310.15987
•
Published
•
5
ICL
-
-
In-Context Learning Creates Task Vectors
Paper • 2310.15916 • Published • 42 -
ZeroGen: Efficient Zero-shot Learning via Dataset Generation
Paper • 2202.07922 • Published • 1 -
Promptor: A Conversational and Autonomous Prompt Generation Agent for Intelligent Text Entry Techniques
Paper • 2310.08101 • Published • 2 -
Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering
Paper • 2308.13259 • Published • 2 -
EcoAssistant: Using LLM Assistant More Affordably and Accurately
Paper • 2310.03046 • Published • 5 -
SCREWS: A Modular Framework for Reasoning with Revisions
Paper • 2309.13075 • Published • 15 -
MIMIC-IT: Multi-Modal In-Context Instruction Tuning
Paper • 2306.05425 • Published • 11 -
Neural Machine Translation Models Can Learn to be Few-shot Learners
Paper • 2309.08590 • Published • 1 -
Ambiguity-Aware In-Context Learning with Large Language Models
Paper • 2309.07900 • Published • 4 -
Are Emergent Abilities in Large Language Models just In-Context Learning?
Paper • 2309.01809 • Published • 3 -
FIAT: Fusing learning paradigms with Instruction-Accelerated Tuning
Paper • 2309.04663 • Published • 5 -
How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations
Paper • 2310.10616 • Published • 1 -
In-Context Pretraining: Language Modeling Beyond Document Boundaries
Paper • 2310.10638 • Published • 28 -
Large Language Models Are Also Good Prototypical Commonsense Reasoners
Paper • 2309.13165 • Published • 1 -
DialCoT Meets PPO: Decomposing and Exploring Reasoning Paths in Smaller Language Models
Paper • 2310.05074 • Published • 1 -
Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis
Paper • 2304.04675 • Published • 1 -
The Closeness of In-Context Learning and Weight Shifting for Softmax Regression
Paper • 2304.13276 • Published • 1 -
RAVEN: In-Context Learning with Retrieval Augmented Encoder-Decoder Language Models
Paper • 2308.07922 • Published • 17 -
Commonsense Knowledge Transfer for Pre-trained Language Models
Paper • 2306.02388 • Published • 1 -
Efficient Prompting via Dynamic In-Context Learning
Paper • 2305.11170 • Published • 1 -
Adapting Language Models to Compress Contexts
Paper • 2305.14788 • Published • 1 -
Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning
Paper • 2308.12219 • Published • 1 -
MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning
Paper • 2309.07915 • Published • 4 -
Steering Large Language Models for Machine Translation with Finetuning and In-Context Learning
Paper • 2310.13448 • Published • 1 -
Query2doc: Query Expansion with Large Language Models
Paper • 2303.07678 • Published • 1 -
Query Expansion by Prompting Large Language Models
Paper • 2305.03653 • Published • 1 -
Generative Relevance Feedback with Large Language Models
Paper • 2304.13157 • Published • 1 -
Context Aware Query Rewriting for Text Rankers using LLM
Paper • 2308.16753 • Published • 1 -
Self-supervised Meta-Prompt Learning with Meta-Gradient Regularization for Few-shot Generalization
Paper • 2303.12314 • Published • 1 -
Contrastive Learning for Prompt-Based Few-Shot Language Learners
Paper • 2205.01308 • Published • 1 -
Learning to Retrieve In-Context Examples for Large Language Models
Paper • 2307.07164 • Published • 21 -
Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning
Paper • 2211.03044 • Published • 1 -
ConsPrompt: Easily Exploiting Contrastive Samples for Few-shot Prompt Learning
Paper • 2211.04118 • Published • 1 -
Contrastive Demonstration Tuning for Pre-trained Language Models
Paper • 2204.04392 • Published • 1 -
Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency
Paper • 2309.17382 • Published • 4 -
Code Prompting: a Neural Symbolic Method for Complex Reasoning in Large Language Models
Paper • 2305.18507 • Published • 1 -
Boosting Language Models Reasoning with Chain-of-Knowledge Prompting
Paper • 2306.06427 • Published • 2 -
Progressive-Hint Prompting Improves Reasoning in Large Language Models
Paper • 2304.09797 • Published • 1 -
Small Language Models Improve Giants by Rewriting Their Outputs
Paper • 2305.13514 • Published • 2 -
Introspective Tips: Large Language Model for In-Context Decision Making
Paper • 2305.11598 • Published • 1 -
Tab-CoT: Zero-shot Tabular Chain of Thought
Paper • 2305.17812 • Published • 2 -
Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks
Paper • 2211.12588 • Published • 3 -
Structured Chain-of-Thought Prompting for Code Generation
Paper • 2305.06599 • Published • 1 -
Improving ChatGPT Prompt for Code Generation
Paper • 2305.08360 • Published • 1 -
Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting
Paper • 2305.07004 • Published • 1 -
Text Data Augmentation in Low-Resource Settings via Fine-Tuning of Large Language Models
Paper • 2310.01119 • Published • 1 -
Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning
Paper • 2205.05638 • Published • 3 -
Prompt Space Optimizing Few-shot Reasoning Success with Large Language Models
Paper • 2306.03799 • Published • 1 -
Prompt Engineering or Fine Tuning: An Empirical Assessment of Large Language Models in Automated Software Engineering Tasks
Paper • 2310.10508 • Published • 1 -
Large Language Model-Aware In-Context Learning for Code Generation
Paper • 2310.09748 • Published • 1 -
Few-shot training LLMs for project-specific code-summarization
Paper • 2207.04237 • Published • 1 -
ThinkSum: Probabilistic reasoning over sets using large language models
Paper • 2210.01293 • Published • 1 -
EchoPrompt: Instructing the Model to Rephrase Queries for Improved In-context Learning
Paper • 2309.10687 • Published • 1 -
ICL-D3IE: In-Context Learning with Diverse Demonstrations Updating for Document Information Extraction
Paper • 2303.05063 • Published • 1 -
SPARSEFIT: Few-shot Prompting with Sparse Fine-tuning for Jointly Generating Predictions and Natural Language Explanations
Paper • 2305.13235 • Published • 1 -
Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification
Paper • 2111.09064 • Published • 1 -
Schema-learning and rebinding as mechanisms of in-context learning and emergence
Paper • 2307.01201 • Published • 2 -
Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners
Paper • 2305.14825 • Published • 1 -
The Transient Nature of Emergent In-Context Learning in Transformers
Paper • 2311.08360 • Published • 1 -
Explore Spurious Correlations at the Concept Level in Language Models for Text Classification
Paper • 2311.08648 • Published • 2 -
NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework
Paper • 2111.04130 • Published • 1 -
Auto-ICL: In-Context Learning without Human Supervision
Paper • 2311.09263 • Published • 2 -
Gated recurrent neural networks discover attention
Paper • 2309.01775 • Published • 7 -
Generative Multimodal Models are In-Context Learners
Paper • 2312.13286 • Published • 34 -
ICE-GRT: Instruction Context Enhancement by Generative Reinforcement based Transformers
Paper • 2401.02072 • Published • 9 -
Chain of Code: Reasoning with a Language Model-Augmented Code Emulator
Paper • 2312.04474 • Published • 30 -
Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression
Paper • 2306.15063 • Published • 1 -
AceCoder: Utilizing Existing Code to Enhance Code Generation
Paper • 2303.17780 • Published • 1 -
Compositional Exemplars for In-context Learning
Paper • 2302.05698 • Published • 2 -
What Makes Good In-context Demonstrations for Code Intelligence Tasks with LLMs?
Paper • 2304.07575 • Published • 1 -
Can language models learn from explanations in context?
Paper • 2204.02329 • Published • 1 -
Post Hoc Explanations of Language Models Can Improve Language Models
Paper • 2305.11426 • Published • 1 -
Automatic Chain of Thought Prompting in Large Language Models
Paper • 2210.03493 • Published • 2 -
SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning
Paper • 2308.00436 • Published • 21 -
Learning Multi-Step Reasoning by Solving Arithmetic Tasks
Paper • 2306.01707 • Published • 1 -
Better Zero-Shot Reasoning with Role-Play Prompting
Paper • 2308.07702 • Published • 2 -
Link-Context Learning for Multimodal LLMs
Paper • 2308.07891 • Published • 15 -
Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks
Paper • 2402.04248 • Published • 30 -
Can large language models explore in-context?
Paper • 2403.15371 • Published • 32 -
XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning
Paper • 2406.08973 • Published • 86