protologue

Reasoning Elicitation

Techniques that get a model to produce intermediate reasoning, decompose problems, or explore multiple solution paths before answering.

Definitions

Analogical Prompting
Analogical prompting asks the model to recall or generate relevant example problems and their solutions on its own before solving the target problem, removing the need for hand-written exemplars.
Automatic Chain-of-Thought
Automatic chain-of-thought (Auto-CoT) builds chain-of-thought demonstrations without manual writing, by clustering questions for diversity and generating a reasoning chain for a representative of each cluster with zero-shot CoT.
Chain-of-Thought Prompting
Chain-of-thought (CoT) prompting elicits a sequence of intermediate reasoning steps from a language model before its final answer, which improves performance on multi-step arithmetic, commonsense, and symbolic reasoning tasks.
Contrastive Chain-of-Thought
Contrastive chain-of-thought adds both valid and deliberately invalid reasoning demonstrations to a prompt, so the model learns which mistakes to avoid as well as what correct reasoning looks like.
Generated Knowledge Prompting
Generated knowledge prompting first asks the model to produce relevant facts about a question, then supplies those generated facts as context when answering it.
Graph of Thoughts
Graph of Thoughts (GoT) models a language model's reasoning as an arbitrary graph, in which thoughts can be combined, refined, and looped back on, generalizing chain and tree structures.
Least-to-Most Prompting
Least-to-most prompting first asks the model to break a complex problem into simpler subproblems, then solves them in order, feeding each answer into the next.
Maieutic Prompting
Maieutic prompting generates a tree of recursive explanations for and against an answer, then infers the most logically consistent answer from the relations among them.
Plan-and-Solve Prompting
Plan-and-solve prompting is a zero-shot method that instructs the model to first devise a plan dividing the task into subtasks and then carry out the plan step by step.
Program of Thoughts
Program of Thoughts (PoT) prompting expresses numerical reasoning as executable code, separating computation, done by an interpreter, from reasoning, done by the model.
Program-Aided Language Models
Program-aided language models (PAL) have the model write a program, typically Python, that expresses its reasoning, and then delegate the actual computation to an interpreter.
Rephrase and Respond
Rephrase and Respond (RaR) asks the model to rephrase and expand the user's question in its own words before answering, reducing misunderstandings caused by ambiguous phrasing.
Scratchpad
A scratchpad is a region of model output reserved for intermediate computation, which the model writes before its final answer so that multi-step calculations can be carried out explicitly.
Self-Ask
Self-ask prompting has the model explicitly pose and answer follow-up sub-questions before answering a multi-hop question, a format that can plug a search engine in to answer each sub-question.
Self-Consistency
Self-consistency samples multiple chain-of-thought reasoning paths for the same question and returns the answer that appears most often, rather than relying on a single greedy decode.
Self-Discover
Self-Discover has the model compose a task-specific reasoning structure by selecting, adapting, and combining general reasoning modules, such as critical thinking or step-by-step analysis, before solving instances of the task.
Skeleton-of-Thought
Skeleton-of-thought first asks the model for a brief outline of its answer, then expands each outline point in parallel, reducing end-to-end generation latency.
Step-Back Prompting
Step-back prompting has the model first answer a more general, abstract question about the underlying principle, then use that answer to reason about the original specific question.
System 2 Attention
System 2 Attention (S2A) first prompts the model to rewrite the input so that it keeps only the relevant, unbiased content, then answers using the rewritten context.
Thread of Thought
Thread of Thought is a prompting strategy for long, chaotic contexts that asks the model to walk through the context in manageable parts, summarizing and analyzing each before answering.
Tree of Thoughts
Tree of Thoughts (ToT) lets a model explore multiple reasoning branches as a search tree, evaluating partial solutions and backtracking, rather than committing to a single left-to-right chain of thought.
Universal Self-Consistency
Universal self-consistency extends self-consistency to free-form outputs by asking the model itself to select the most consistent response among several samples, instead of counting exact-match answers.
Zero-shot Chain-of-Thought
Zero-shot chain-of-thought prompting triggers step-by-step reasoning without examples by appending a cue such as "Let's think step by step" to the question.