Learn to explain: Multimodal reasoning via thought chains for science question answering

P Lu, S Mishra, T Xia, L Qiu… - Advances in …, 2022 - proceedings.neurips.cc
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 …

The llama 3 herd of models

A Dubey, A Jauhri, A Pandey, A Kadian… - arXiv preprint arXiv …, 2024 - arxiv.org
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 …

What can transformers learn in-context? a case study of simple function classes

S Garg, D Tsipras, PS Liang… - Advances in Neural …, 2022 - proceedings.neurips.cc
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 …

Large language model as attributed training data generator: A tale of diversity and bias

Y Yu, Y Zhuang, J Zhang, Y Meng… - Advances in …, 2024 - proceedings.neurips.cc
Large language models (LLMs) have been recently leveraged as training data generators
for various natural language processing (NLP) tasks. While previous research has explored …

Rethinking the role of demonstrations: What makes in-context learning work?

S Min, X Lyu, A Holtzman, M Artetxe, M Lewis… - arXiv preprint arXiv …, 2022 - arxiv.org
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 …

Super-naturalinstructions: Generalization via declarative instructions on 1600+ nlp tasks

Y Wang, S Mishra, P Alipoormolabashi, Y Kordi… - arXiv preprint arXiv …, 2022 - arxiv.org
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 …

Large language models are few-shot clinical information extractors

M Agrawal, S Hegselmann, H Lang, Y Kim… - arXiv preprint arXiv …, 2022 - arxiv.org
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 …

Measuring and narrowing the compositionality gap in language models

O Press, M Zhang, S Min, L Schmidt, NA Smith… - arXiv preprint arXiv …, 2022 - arxiv.org
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 …

Rlprompt: Optimizing discrete text prompts with reinforcement learning

M Deng, J Wang, CP Hsieh, Y Wang, H Guo… - arXiv preprint arXiv …, 2022 - arxiv.org
Prompting has shown impressive success in enabling large pretrained language models
(LMs) to perform diverse NLP tasks, especially when only few downstream data are …

Can language models learn from explanations in context?

AK Lampinen, I Dasgupta, SCY Chan… - arXiv preprint arXiv …, 2022 - arxiv.org
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 …