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.
For example: • Modify the value of a parameter so that it no longer corresponds to the data of the set
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.