Loading actions...
TypeScript and ESLint rules that MUST be followed when creating, modifying, or reviewing any file under apps/frontend/, including .ts, .tsx, .js, and .jsx files. Also apply when discussing frontend li...
risks
prompt:
term: prompt
def: A text or other input to a Generatve AI
api:
term: API
def: "Application Programming Interface. Enables different systems to interact with each other programmatically. Two types of APIs are REST APIs (web APIs) and native-library APIs."
link: See What is a REST API?
self_consistency:
term: Self Consistency
def: Generating multiple chains of thought and taking the majority answer.
link: See Self Consistency
labelspace:
term: Label space
def: All of the possible labels for a given task.
few shot standard prompt:
term: few shot standard prompt
def: Standard prompts that have exemplars in them. Exemplars are examples of the task that the prompt is trying to solve, which are included in the prompt itself.
exemplars:
term: Exemplars
def: Examples of the task that the prompt is trying to solve, which are included in the prompt itself.
CoT prompting:
term: CoT prompting
def: The main idea of CoT is that by showing the LLM some few shot exemplars where the reasoning process is explained in the exemplars, the LLM will also show the reasoning process when answering the prompt.
PAL:
term: PAL
def: A method that uses code as intermediate reasoning
link: see PAL
LLM:
term: LLM
def: Large Language Model. A model that is trained to predict the next word in a sentence.
gold_labels:
term: Gold Labels
def: The correct labels for a given task.
labels:
term: labels
def: The concept of labels is best understood with an example.
Say we want to classify some Tweets as mean or not mean. If we have a list of Tweets and their corresponding label (mean or not mean), we can train a model to classify whether tweets are mean or not. Labels are generally just possibilities for the classification task.
sentiment analysis:
term: Sentiment Analysis
def: Sentiment analysis is the task of classifying text into positive, negative, or other sentiments.
prompt estándar de pocos ejemplos: term: prompt estándar de pocos ejemplos def: Los prompts estándar que incluyen ejemplos. Los ejemplos son ejemplos de la tarea que el prompt intenta resolver, los cuales se incluyen en el propio prompt. ejemplos: term: Ejemplos def: Ejemplos de la tarea que el prompt intenta resolver, los cuales se incluyen en el propio prompt.
prompting de CoT: term: prompting de CoT def: La idea principal de CoT es que al mostrarle al LLM algunos ejemplos de few-shot donde se explica el proceso de razonamiento en los ejemplos, el LLM también mostrará el proceso de razonamiento al responder a la solicitud.
prompt zh-hans: term: prompt def: 提供给生成式 AI 的文本或其他输入