Learn to explain: Multimodal reasoning via thought chains for science question answering
When answering a question, humans utilize the information available across different
modalities to synthesize a consistent and complete chain of thought (CoT). This process is …
modalities to synthesize a consistent and complete chain of thought (CoT). This process is …
The llama 3 herd of models
Modern artificial intelligence (AI) systems are powered by foundation models. This paper
presents a new set of foundation models, called Llama 3. It is a herd of language models …
presents a new set of foundation models, called Llama 3. It is a herd of language models …
What can transformers learn in-context? a case study of simple function classes
In-context learning is the ability of a model to condition on a prompt sequence consisting of
in-context examples (input-output pairs corresponding to some task) along with a new query …
in-context examples (input-output pairs corresponding to some task) along with a new query …
Large language model as attributed training data generator: A tale of diversity and bias
Large language models (LLMs) have been recently leveraged as training data generators
for various natural language processing (NLP) tasks. While previous research has explored …
for various natural language processing (NLP) tasks. While previous research has explored …
Rethinking the role of demonstrations: What makes in-context learning work?
Large language models (LMs) are able to in-context learn--perform a new task via inference
alone by conditioning on a few input-label pairs (demonstrations) and making predictions for …
alone by conditioning on a few input-label pairs (demonstrations) and making predictions for …
Super-naturalinstructions: Generalization via declarative instructions on 1600+ nlp tasks
How well can NLP models generalize to a variety of unseen tasks when provided with task
instructions? To address this question, we first introduce Super-NaturalInstructions, a …
instructions? To address this question, we first introduce Super-NaturalInstructions, a …
Large language models are few-shot clinical information extractors
A long-running goal of the clinical NLP community is the extraction of important variables
trapped in clinical notes. However, roadblocks have included dataset shift from the general …
trapped in clinical notes. However, roadblocks have included dataset shift from the general …
Measuring and narrowing the compositionality gap in language models
We investigate the ability of language models to perform compositional reasoning tasks
where the overall solution depends on correctly composing the answers to sub-problems …
where the overall solution depends on correctly composing the answers to sub-problems …
Rlprompt: Optimizing discrete text prompts with reinforcement learning
Prompting has shown impressive success in enabling large pretrained language models
(LMs) to perform diverse NLP tasks, especially when only few downstream data are …
(LMs) to perform diverse NLP tasks, especially when only few downstream data are …
Can language models learn from explanations in context?
Language Models (LMs) can perform new tasks by adapting to a few in-context examples.
For humans, explanations that connect examples to task principles can improve learning …
For humans, explanations that connect examples to task principles can improve learning …