Reasoning Glossary
Browse 30 reasoning terms defined in plain English, from the cultural dictionary of computing.
30 Reasoning Terms
- Chain of Thought
- Chain of Thought is a prompting technique and reasoning approach in large language models where the model is encouraged to show its step-by-step reasoning...
- Chain of Thought Prompting
- A prompting technique that encourages a model to produce intermediate reasoning steps before the final answer. It influences how models are trained, evaluated,...
- Code Puzzle
- A technical problem that feels interesting and solvable through careful reasoning rather than pure chaos. In engineering slang, code puzzle is what people call...
- Dual Process Theory
- A theory from cognitive science that distinguishes between fast intuitive reasoning and slower deliberate reasoning. In AI discussions it is often used as an...
- Duck Test
- An informal heuristic captured by the idea that if something looks and behaves like a duck, it is probably a duck. Engineers use it when pattern recognition is...
- First Principle
- A foundational assumption or basic truth from which further reasoning can be built. In tech culture, talking from first principles usually means trying to...
- Implicit Reasoning
- Reasoning that appears in a model's behavior without being explicitly exposed step by step in the output. The term is used when a system seems to perform...
- Knowledge Graph
- A graph of entities and relationships used to represent structured knowledge for retrieval or reasoning. It influences how models are trained, evaluated, or...
- Mental Model
- An internal conceptual map of how something works, used to predict behavior, explain failures, and make decisions. Strong engineers often differ less in syntax...
- Mental Model AI
- The user's or designer's conceptual model of how an AI system works, what it knows, and how it will behave in different situations. Clear mental models are...
- MMLU Benchmark
- A benchmark that measures broad multitask knowledge and reasoning across many academic and professional domains.
- Multi-Step Reasoning
- Reasoning that unfolds across several logical or computational steps rather than a single immediate response. Multi-step reasoning is important for tasks like...
- Overthinking AI
- A situation where an AI system applies unnecessary complexity or excessive reasoning to a simple task, often leading to slower responses or avoidable mistakes....
- Problem Solving
- The process of identifying a problem, understanding constraints, evaluating options, and arriving at an effective solution. In software culture, problem...
- Reasoning Agent
- An agentic AI component focused on planning, decomposing problems, or carrying out reasoning-heavy tasks, often with access to tools or memory. Reasoning...
- Reasoning Benchmark
- A benchmark designed to test reasoning ability, such as multi-step logic, math, planning, or problem decomposition. Reasoning benchmarks are useful, but they...
- Reasoning Error
- An error caused by faulty logical steps, invalid assumptions, or broken inference inside an AI system's reasoning process. Reasoning errors can occur even when...
- Reasoning Model
- A model optimized or selected for tasks that require stronger multi-step inference, planning, or problem decomposition rather than simple pattern matching...
- Reasoning Step
- An individual step within a larger reasoning process or chain of inference. Teams talk about reasoning steps when analyzing how an AI system reached a...
- Reasoning Token
- A token used during reasoning-focused generation or internal reasoning traces, often discussed in the context of cost, latency, or long multi-step responses....
- Reasoning Trace
- A record or visible sequence of reasoning-related steps, intermediate thoughts, or problem-solving actions used to analyze how an AI system arrived at its...
- Self-Consistency
- A prompting or decoding strategy in which multiple reasoning paths or outputs are generated and then compared to select the most consistent answer....
- Self-Correction
- The ability or workflow by which an AI system identifies and fixes its own mistakes after initial generation. Self-correction can improve quality, though it...
- Self-Reflection
- A reflective step where an AI system reviews its own reasoning, assumptions, or output quality and may revise accordingly. Self-reflection is often used to...
- Situational Awareness
- Awareness of relevant context about the environment, task, capabilities, and constraints in which a system is operating. In AI discussions, situational...
- Step-by-Step
- Describing instructions or outputs that proceed one step at a time rather than jumping directly to the conclusion. Step-by-step prompting is often used to...
- Thinking Token
- A token associated with intermediate reasoning or extended deliberation in a model's generation process. The term is often used when discussing tradeoffs...
- Think Step by Step
- A prompting instruction intended to encourage the model to reason in a more deliberate multi-step way rather than answering immediately. It is commonly used in...
- Uncertainty
- A measure or acknowledgment of how unsure an AI system is about an answer, prediction, or decision. Handling uncertainty well is important because systems...
- Working Memory AI
- The short-term memory mechanism an AI system uses to hold relevant information while reasoning or carrying out a task. Working memory is important for...
Related Topics
- Ai (21 terms in common)
- Prompting (4 terms in common)
- Evaluation (2 terms in common)
- Tokens (2 terms in common)
- Thinking (1 terms in common)
- Graphs (1 terms in common)
- Benchmarks (1 terms in common)
- Debugging (1 terms in common)
- Models (1 terms in common)
- Failure Modes (1 terms in common)
- Cognition (1 terms in common)
- Uncertainty (1 terms in common)
- Technique (1 terms in common)
- Errors (1 terms in common)
- Ux (1 terms in common)
- Memory (1 terms in common)
- Knowledge (1 terms in common)
- Awareness (1 terms in common)
- Decoding (1 terms in common)
- Learning (1 terms in common)