Live briefing
Everything about Context window
Token limit for LLM context
The context window of a large language model (LLM) is the maximum number of tokens that can be used by the model at one time when generating an output. It determines how much information, such as text from a conversation or document, the model can take into account when producing a response. Wikipedia →
🧭 Start here: a 6-step reading path
- Read the overview: Context windowA 5-minute orientation
- Skim a recent paper: Context matters: Optimal green wall geometry for window views vary with sound conditionsInfluential work since 2022
- Pick up a classic book: Select ModulesThe most-reprinted book on the subject
- Read the landmark paper: Building energy conservation potentials of semi-transparent CdTe integrated photovoltaic window systems in Bangladesh contextCited 46 times
- Go sideways: Training of large language modelsA closely related topic
- Go sideways: Prompt engineeringA closely related topic
📖 Definitions
No dictionary entry for this exact phrase.
🗂️ The subject at a glance
🏆 Landmark papers (most cited)
Building energy conservation potentials of semi-transparent CdTe integrated photovoltaic window systems in Bangladesh context
Efficient Contextformer: Spatio-Channel Window Attention for Fast Context Modeling in Learned Image Compression
Context Window Based Co-occurrence Approach for Improving Feedback Based Query Expansion in Information Retrieval
Does More Context Help? Effects of Context Window and Application Source on Retrieval Performance
“A Window of Opportunity”: Parenting and Addiction in the Context of Pregnancy
Sliding Time Window Electricity Consumption Optimization Algorithm for Communities in the Context of Big Data Processing
Extending Context Window in Large Language Models with Segmented Base Adjustment for Rotary Position Embeddings
Automatic context window composition for distant speech recognition
🆕 Influential since 2022
Context matters: Optimal green wall geometry for window views vary with sound conditions
Long context window-based zero-shot legal interpretation of building codes and regulations
SW-SpeedDLM: Sliding Window Speculative Decoding for Diffusion Language Models Under Long Context Constraints
Neurons in auditory cortex integrate information within a constrained and context-invariant temporal window
Context Is What You Need: The Maximum Effective Context Window for Real World Limits of LLMs
📚 Books worth reading
- 📕Select ModulesSelect · 1997
Active DirectoryRobbie Allen, Joe Richards · 2003
Situational context of educationMaria Brisk, Mar¡a Estela Brisk · 2003
OpenGL superbibleWright, Richard S., Richard S. Wright Jr. · 1996- 📕ScharpfSelect · 1997
Windows on writingLaurie G. Kirszner · 1995- 📕Readings in glass historyAnita Engle · 1973
Short Stories for StudentsKathleen Wilson, Jennifer Smith · 2010
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
🔗 Related topics
- Training of large language models A large language model (LLM) needs to be trained. The training of an LLM has become more complex over time. Pretraining is the training stage where the…
- Prompt engineering Prompt engineering is the process of structuring natural language inputs (known as prompts) to produce specified outputs from a generative AI model. Context…
- BERT (language model) Bidirectional encoder representations from transformers (BERT) is a language model introduced in October 2018 by researchers at Google. It learns to represent…
- LLM-as-a-Judge LLM-as-a-Judge (also LLM-based evaluation or language model-based evaluation) is a technique in natural language processing in which a large language model…
- Retrieval-augmented generation Retrieval-augmented generation (RAG) is a technique that enables large language models (LLMs) to retrieve and incorporate new information from external…
- Language model A language model is a computational model that predicts sequences in natural language. Language models are useful for a variety of tasks, including speech…
- Large language model A large language model (LLM) is a machine learning model (typically a neural network) trained on a vast amount of text for natural language processing…
- Sentence embedding In natural language processing, a sentence embedding (or document embedding) is a representation of a natural language text as a vector of numbers which…