chat model
In plain wordsA language model trained to hold a back-and-forth conversation, keeping track of who said what and replying as a helpful assistant. It is the engine inside chat apps.
A language modellanguage model, n.: A system that has learned how likely different sequences of words are, so it can predict the next word in a text and, by doing that repeatedly, write text of its own. post-trained to conduct multi-turn dialogue in a role-based format: a conversation is a list of messages labeled system, user, assistant and often tool, serialized into tokens by the model's chat templatechat template, n.: The exact text layout a chat AI was trained on for marking who is speaking — system, user or assistant. Software must reproduce it precisely, or the model performs noticeably worse., with special tokensspecial token, n.: A reserved symbol in an AI model's vocabulary that is not ordinary text but a signal — 'start of message', 'end of answer', 'begin thinking' — used to structure what the model reads and writes. marking turn boundaries. Training combines supervised fine-tuningsupervised fine-tuning, n.: Teaching a pretrained AI model by showing it many examples of good answers to requests, so it learns to imitate them — like learning a job by studying worked examples. on dialogues with preference optimization, giving the model a consistent assistant persona, the ability to draw on earlier turns, and conventions for clarification, refusalsrefusal, n.: When an AI declines to do what it was asked — 'I can't help with that' — usually because the request seems harmful or breaks the rules it was trained to follow. and tool callstool call, n.: A single request from an AI model to use one of its tools — naming the tool and filling in the details — which the surrounding software then carries out and reports back on.. Chat models are accessed through message-based APIs rather than raw text completion, and are the basis of chat assistants, agentsAI agent, n.: An AI system that does not just answer but acts: given a goal, it decides on steps, uses tools such as a browser or code editor, checks the results and keeps going until the job is done. and most reasoning modelsreasoning model, n.: An AI model trained to work through a problem step by step in hidden 'thinking' text before it answers. Letting it think longer generally makes it better at math, coding and planning..
Send the history as a list of messages; the chat model was never trained on raw transcripts.
Origin
Dialogue-tuned neural models such as Google's Meena (2020) and LaMDA (2021) preceded wide use of the term. ChatGPTChatGPT, prop. n.: OpenAI's AI chatbot, released free to the public in November 2022, which answers questions, writes and converses in everyday language. Its sudden popularity began the current AI boom. (November 2022) made chat the dominant interface to language models, and OpenAI's Chat Completions API (March 2023) and Meta's Llama 2-Chat (July 2023) established 'chat model' as a standard category of release.
Usage note
Distinguish from chatbotchatbot, n.: Software you chat with in ordinary language, by typing or talking, as you would with a person. The newest ones, such as ChatGPT, can answer questions, draft writing and keep long conversations going., any conversational program, including rule-based ones such as ELIZAELIZA, prop. n.: A 1960s computer program that chatted by turning a user's own words back into questions, like a therapist. Many users felt understood, though the program understood nothing.. The chat model is the trained network; the chatbot or assistant is the product built on it.
Related
- chat templatechat template, n.: The exact text layout a chat AI was trained on for marking who is speaking — system, user or assistant. Software must reproduce it precisely, or the model performs noticeably worse.
- system promptsystem prompt, n.: Background instructions given to a chatbot before the conversation starts, setting its role, rules, tone and tools. Users usually never see it, but it shapes every reply.
- instruction-tuned modelinstruction-tuned model, n.: A language model given extra training on examples of instructions paired with good responses, so it does what you ask instead of merely continuing your text.
- ChatGPTChatGPT, prop. n.: OpenAI's AI chatbot, released free to the public in November 2022, which answers questions, writes and converses in everyday language. Its sudden popularity began the current AI boom.
- conversational AIconversational AI, n.: The technology that lets computers hold conversations with people in everyday language, by text or voice. It powers chatbots, voice assistants and automated customer-service lines.
- base modelbase model, n.: A language model fresh from its first broad training on text, before being taught to follow instructions or chat. It continues whatever text it is given instead of answering.
- reinforcement learning from human feedbackreinforcement learning from human feedback, n.: A way of training AI using people's judgments: humans compare pairs of answers, a scoring model learns their preferences, and the AI is then trained to produce answers that score well.
- base modelbase model, n.: A language model fresh from its first broad training on text, before being taught to follow instructions or chat. It continues whatever text it is given instead of answering.
- chatbotchatbot, n.: Software you chat with in ordinary language, by typing or talking, as you would with a person. The newest ones, such as ChatGPT, can answer questions, draft writing and keep long conversations going.
Sources
- OpenAI (2023). Introducing ChatGPT and Whisper APIs. OpenAI blog. openai.com/index/introducing-chatgpt-and-whisper-apis
Mentioned in
chatbotchatbot, n.: Software you chat with in ordinary language, by typing or talking, as you would with a person. The newest ones, such as ChatGPT, can answer questions, draft writing and keep long conversations going., large language modellarge language model, n.: A computer program trained on enormous amounts of text to predict the words that come next. At vast scale, that simple skill lets it chat, answer questions, translate, summarize and write code., reasoning modelreasoning model, n.: An AI model trained to work through a problem step by step in hidden 'thinking' text before it answers. Letting it think longer generally makes it better at math, coding and planning., AI assistantAI assistant, n.: An AI program, such as ChatGPT, Claude or Gemini, that helps a person through conversation: answering questions, writing, summarizing, coding and, increasingly, taking actions on their behalf., base modelbase model, n.: A language model fresh from its first broad training on text, before being taught to follow instructions or chat. It continues whatever text it is given instead of answering., instruction-tuned modelinstruction-tuned model, n.: A language model given extra training on examples of instructions paired with good responses, so it does what you ask instead of merely continuing your text., system promptsystem prompt, n.: Background instructions given to a chatbot before the conversation starts, setting its role, rules, tone and tools. Users usually never see it, but it shapes every reply., chat templatechat template, n.: The exact text layout a chat AI was trained on for marking who is speaking — system, user or assistant. Software must reproduce it precisely, or the model performs noticeably worse., decision modeldecision model, n.: A kind of AI language model that reads text but answers only with numbers — a yes-or-no probability, a choice or a score — instead of writing words., hybrid reasoning modelhybrid reasoning model, n.: A single AI model that can either answer right away or first think at length, with the user or developer choosing how much thinking to allow., MT-BenchMT-Bench, prop. n.: A set of 80 two-part questions — in writing, reasoning, math, coding and more — whose answers are graded by a strong AI model, used to compare chat assistants quickly.