.png){kind=icon}
Return
Adaptive-solver framework for dynamic strategy selection in large language model reasoning
.png){kind=icon}
OA
AI
DOI：10.1016/j.ipm.2024.104052.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Large Language Models (LLMs) demonstrate impressive ability in handling reasoning tasks. However, unlike humans who can instinctively adapt their problem-solving strategies to the complexity of task, most LLM-based methods adopt a one-size-fits-all approach. These methods employ consistent models, sample sizes, prompting methods and levels of problem decomposition, regardless of the problem complexity. The inflexibility of these methods can bring unnecessary computational overhead or sub-optimal performance. To address this limitation, we introduce an Adaptive-Solver (AS) framework that dynamically adapts solving strategies to suit various problems, enabling the flexible allocation of test-time computational resources. The framework functions with two primary modules. The initial evaluation module assesses the reliability of the current solution using answer consistency. If the solution is deemed unreliable, the subsequent adaptation module comes into play. Within this module, various types of adaptation strategies are employed collaboratively. Through such dynamic and multi-faceted adaptations, our framework can help reduce computational consumption and improve performance. Experimental results from complex reasoning benchmarks reveal that our method can significantly reduce API costs (up to 85%) while maintaining original performance. Alternatively, it achieves up to 4.5% higher accuracy compared to the baselines at the same cost. The datasets and code are available at https://github.com/john1226966735/Adaptive-Solver.
Keywords:
Large language models
Reasoning
Math word problems
Test-time computation allocation
Dynamic strategy selection
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
I
IF:
6.9
Papers:
5.2K
Citations:
1.4W
Organization
Cited Papers
.png){kind=icon}
ShareSaveExplainable Knowledge reasoning via thought chains for knowledge-based visual question answering
PREAI
ShareSaveShareSaveShareSaveProgram Induction by Rationale Generation: Learning to Solve and
Explain Algebraic Word Problems
OAAI
OAAIShareSavePlan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language ModelsOAAI
OAAIShareSaveShareSaveShareSave
View more