Add to ORKGWith a handful of demonstration examples, large-scale language models show strong capability to perform various tasks by in-context learning from these examples, without any fine-tuning. We demonstrate that in-context learning performance can be highly unstable across samples of examples, indicating the idiosyncrasies of how language models acquire information. We formulate example selection for in-context learning as a sequential decision problem, and propose a reinforcement learning algorithm for identifying generalizable policies to select demonstration examples. For GPT-2, our learned policies demonstrate strong abilities of generalizing to unseen tasks in training, with a $5.8\%$ improvement on average. Examples selected from our learn...
Many recent studies on large-scale language models have reported successful in-context zero- and few...
Large language models are able to perform a task by conditioning on a few input-output demonstration...
Pre-trained models of source code have gained widespread popularity in many code intelligence tasks....
Large language models have exhibited emergent abilities, demonstrating exceptional performance acros...
Large language models (LMs) are able to in-context learn -- perform a new task via inference alone b...
Large language models (LMs) such as GPT-3 have the surprising ability to do in-context learning, whe...
In-context learning is a recent paradigm in natural language understanding, where a large pre-traine...
In-context learning (ICL) i.e. showing LLMs only a few task-specific demonstrations has led to downs...
Large language models (LLMs) have shown incredible performance in completing various real-world task...
This work presents In-Context Policy Iteration, an algorithm for performing Reinforcement Learning (...
Pretrained large language models (LLMs) are strong in-context learners that are able to perform few-...
Large Language models (LLMs) possess the capability to engage In-context Learning (ICL) by leveragin...
Large language models (LLMs) exhibit remarkable performance improvement through in-context learning ...
Language model fine-tuning is essential for modern natural language processing, but is computational...
We explore using a moderately sized large language model (GPT-J 6B parameters) to create a plan for ...
Many recent studies on large-scale language models have reported successful in-context zero- and few...
Large language models are able to perform a task by conditioning on a few input-output demonstration...
Pre-trained models of source code have gained widespread popularity in many code intelligence tasks....
Large language models have exhibited emergent abilities, demonstrating exceptional performance acros...
Large language models (LMs) are able to in-context learn -- perform a new task via inference alone b...
Large language models (LMs) such as GPT-3 have the surprising ability to do in-context learning, whe...
In-context learning is a recent paradigm in natural language understanding, where a large pre-traine...
In-context learning (ICL) i.e. showing LLMs only a few task-specific demonstrations has led to downs...
Large language models (LLMs) have shown incredible performance in completing various real-world task...
This work presents In-Context Policy Iteration, an algorithm for performing Reinforcement Learning (...
Pretrained large language models (LLMs) are strong in-context learners that are able to perform few-...
Large Language models (LLMs) possess the capability to engage In-context Learning (ICL) by leveragin...
Large language models (LLMs) exhibit remarkable performance improvement through in-context learning ...
Language model fine-tuning is essential for modern natural language processing, but is computational...
We explore using a moderately sized large language model (GPT-J 6B parameters) to create a plan for ...
Many recent studies on large-scale language models have reported successful in-context zero- and few...
Large language models are able to perform a task by conditioning on a few input-output demonstration...
Pre-trained models of source code have gained widespread popularity in many code intelligence tasks....