Tree of Problems: Improving structured problem solving with compositionality
Large Language Models (LLMs) have demonstrated remarkable performance across multiple tasks through in-context learning. For complex reasoning tasks that require step-by-step thinking, Chain-of-Thought (CoT) prompting has given impressive results, especially when combined with self-consistency. Nonetheless, some tasks remain particularly difficult for LLMs to solve. Tree of Thoughts (ToT) and Graph of Thoughts (GoT) emerged as alternatives, dividing the complex problem into paths of subproblems. In this paper, we propose Tree of Problems (ToP), a simpler version of ToT, which we hypothesise can work better for complex tasks that can be divided into identical subtasks. Our empirical results show that our approach outperforms ToT and GoT, and in addition performs better than CoT on complex reasoning tasks. All code for this paper is publicly available here: https://github.com/ArmelRandy/tree-of-problems.
Code (2)
Tasks
In-Context LearningSimilar Papers 제목 키워드 기반
Tree-structured Decoding for Solving Math Word Problems
Automatically solving math word problems is an interesting research topic that needs to bridge natural language descriptions and formal math equations. Previous studies introduced end-to-end neural network methods, but t…
MathGraph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem
The celebrated Seq2Seq technique and its numerous variants achieve excellent performance on many tasks such as neural machine translation, semantic parsing, and math word problem solving. However, these models either onl…
DecoderMachine TranslationMathMath Word Problem Solving+2Solving Arithmetic Word Problems by Scoring Equations with Recursive Neural Networks
Solving arithmetic word problems is a cornerstone task in assessing language understanding and reasoning capabilities in NLP systems. Recent works use automatic extraction and ranking of candidate solution equations prov…
A Goal-Driven Tree-Structured Neural Model for Math Word Problems
Most existing neural models for math word problems exploit Seq2Seq model to generate solution expressions sequentially from left to right, whose results are far from satisfactory due to the lack of goal-driven mechani…
MathMath Word Problem SolvingHierarchical Attention Decoder for Solving Math Word Problems
To answer math word problems (MWPs), models need to formalize equations from the source text of math problems. Recently, the tree-structured decoder has significantly improved model performance on this task by generating…
DecoderMath