Direct Conclusion Generation with Hidden Reasoning

Single-Run Multi-Step Reasoning

Multi-Run Problem Decomposition for Complex Reasoning

Self-Refinement in LLMs

Predict-then-Verify Approaches in LLM Reasoning

Principle of Generating Longer Reasoning Paths

Modifying Decoding for Longer Reasoning Paths

Multi-Stage Generation for Incremental Reasoning

An engineer is building a system to solve complex logic puzzles. When a puzzle is submitted, the system sends a single, carefully crafted prompt to a large language model. The model's output is a complete, step-by-step explanation of how it solved the puzzle, followed by the final answer, all generated in one response. Which approach to multi-step reasoning does this system exemplify?

Prompting for a Reasoning Process to Mitigate Errors in Complex Tasks

Compositional Generalization in LLMs

Choosing a Reasoning Strategy for a Financial AI

You are designing systems that use a large language model to solve complex problems. Match each system description with the reasoning approach it employs.

Predict-then-Verify Approaches in LLM Reasoning

Synergy of Training-Based and Training-Free Reasoning Methods

A development team wants to improve a large language model's performance on solving complex logic puzzles without modifying its pre-trained parameters. Their approach involves two stages: first, they prompt the model to generate five distinct potential solutions for a single puzzle. Second, they use an automated checker to evaluate the logical consistency of each of the five generated solutions and select the most valid one as the final output. Which category of training-free reasoning enhancement does this approach primarily represent?

Comparing Training-Free Reasoning Strategies

Match each scenario describing a method to improve a language model's reasoning with the correct training-free approach it exemplifies. Both approaches are applied at inference time without altering the model's pre-trained parameters.