BPP-Search combines beam search, a process reward model, and pairwise preference ranking to improve tree-of-thought selection for LLM mathematical modeling, beating CoT and ToT baselines on the new StructuredOR and two existing OR datasets.
This approach expands the dataset with additional examples while ensuring consistency and alignment with the hierarchical structure
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving
BPP-Search combines beam search, a process reward model, and pairwise preference ranking to improve tree-of-thought selection for LLM mathematical modeling, beating CoT and ToT baselines on the new StructuredOR and two existing OR datasets.