Chain-of-thought prompting, by including intermediate reasoning steps in few-shot examples, elicits strong reasoning abilities in large language models on arithmetic, commonsense, and symbolic tasks.
Kurt Shuster, Spencer Poff, Moya Chen, Douwe Kiela, and Jason Weston
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
GPT-3 can learn to express well-calibrated uncertainty about its answers using natural language phrases rather than logits.
The authors present a catalog of prompt patterns that provide reusable solutions to common problems in generating and interacting with outputs from LLMs.
Adding the fixed prompt 'Let's think step by step' enables large language models to achieve substantial zero-shot gains on arithmetic, symbolic, and logical reasoning benchmarks without any task-specific examples.
Multitask fine-tuning of an encoder-decoder model on prompted datasets produces zero-shot generalization that often beats models up to 16 times larger on standard benchmarks.
Emergent abilities are capabilities present in large language models but absent in smaller ones and cannot be predicted by extrapolating smaller model performance.
Introduces Augment Engineering as a six-phase multi-tool orchestration methodology, supported by exploratory statistics from a single-practitioner case study across seven domains.
Applies sparse autoencoders to locate and steer latent features for OCEAN personality traits in LLMs while preserving benchmark performance.
A systematic review finds research on the sustainability of LLM-generated code to be limited, fragmented, and without accepted frameworks for measurement or benchmarking.
citing papers explorer
-
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Chain-of-thought prompting, by including intermediate reasoning steps in few-shot examples, elicits strong reasoning abilities in large language models on arithmetic, commonsense, and symbolic tasks.
-
Teaching Models to Express Their Uncertainty in Words
GPT-3 can learn to express well-calibrated uncertainty about its answers using natural language phrases rather than logits.
-
A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT
The authors present a catalog of prompt patterns that provide reusable solutions to common problems in generating and interacting with outputs from LLMs.
-
Large Language Models are Zero-Shot Reasoners
Adding the fixed prompt 'Let's think step by step' enables large language models to achieve substantial zero-shot gains on arithmetic, symbolic, and logical reasoning benchmarks without any task-specific examples.
-
Multitask Prompted Training Enables Zero-Shot Task Generalization
Multitask fine-tuning of an encoder-decoder model on prompted datasets produces zero-shot generalization that often beats models up to 16 times larger on standard benchmarks.
-
Emergent Abilities of Large Language Models
Emergent abilities are capabilities present in large language models but absent in smaller ones and cannot be predicted by extrapolating smaller model performance.
-
Augment Engineering: A Methodology for Multi-Tool AI Orchestration Across Professional Domains
Introduces Augment Engineering as a six-phase multi-tool orchestration methodology, supported by exploratory statistics from a single-practitioner case study across seven domains.
-
Mechanistic Personality Analysis of LLMs Steering Personality via Latent Feature Interventions
Applies sparse autoencoders to locate and steer latent features for OCEAN personality traits in LLMs while preserving benchmark performance.
-
Sustainable Code Generation Using Large Language Models: A Systematic Literature Review
A systematic review finds research on the sustainability of LLM-generated code to be limited, fragmented, and without accepted frameworks for measurement or benchmarking.