Large language models represent a significant advancement in the field of AI. The
underlying technology is key to further innovations and, despite critical views and even bans …

Self-correction is an approach to improving responses from large language models (LLMs)
by refining the responses using LLMs during inference. Prior work has proposed various self …

In recent years, large language models have greatly improved in their ability to perform
complex multi-step reasoning. However, even state-of-the-art models still regularly produce …

Few-shot learning is a challenging task that requires language models to generalize from
limited examples. Large language models like GPT-3 and PaLM have made impressive …

Large language models (LLMs), such as GPT-4, have shown remarkable performance in
natural language processing (NLP) tasks, including challenging mathematical reasoning …

The advent of large language models trained on code (code LLMs) has led to significant
progress in language-to-code generation. State-of-the-art approaches in this area combine …

We explore how generating a chain of thought---a series of intermediate reasoning steps---
significantly improves the ability of large language models to perform complex reasoning. In …

Abstract Large Language Models (LLMs) significantly benefit from Chain-of-thought (CoT)
prompting in performing various reasoning tasks. While CoT allows models to produce more …

State-of-the-art language models can match human performance on many tasks, but they
still struggle to robustly perform multi-step mathematical reasoning. To diagnose the failures …

Can world knowledge learned by large language models (LLMs) be used to act in
interactive environments? In this paper, we investigate the possibility of grounding high-level …