PathFinder: Guided Search over Multi-Step Reasoning Paths
- URL: http://arxiv.org/abs/2312.05180v2
- Date: Tue, 12 Dec 2023 16:06:32 GMT
- Title: PathFinder: Guided Search over Multi-Step Reasoning Paths
- Authors: Olga Golovneva, Sean O'Brien, Ramakanth Pasunuru, Tianlu Wang, Luke
Zettlemoyer, Maryam Fazel-Zarandi, Asli Celikyilmaz
- Abstract summary: We propose PathFinder, a tree-search-based reasoning path generation approach.
It enhances diverse branching and multi-hop reasoning through the integration of dynamic decoding.
Our model generalizes well to longer, unseen reasoning chains, reflecting similar complexities to beam search with large branching factors.
- Score: 80.56102301441899
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: With recent advancements in large language models, methods like
chain-of-thought prompting to elicit reasoning chains have been shown to
improve results on reasoning tasks. However, tasks that require multiple steps
of reasoning still pose significant challenges to state-of-the-art models.
Drawing inspiration from the beam search algorithm, we propose PathFinder, a
tree-search-based reasoning path generation approach. It enhances diverse
branching and multi-hop reasoning through the integration of dynamic decoding,
enabled by varying sampling methods and parameters. Using constrained
reasoning, PathFinder integrates novel quality constraints, pruning, and
exploration methods to enhance the efficiency and the quality of generation.
Moreover, it includes scoring and ranking features to improve candidate
selection. Our approach outperforms competitive baselines on three complex
arithmetic and commonsense reasoning tasks by 6% on average. Our model
generalizes well to longer, unseen reasoning chains, reflecting similar
complexities to beam search with large branching factors.
Related papers
- Combinatorial Reasoning: Selecting Reasons in Generative AI Pipelines via Combinatorial Optimization [2.090904951468026]
Large Language Models (LLMs) have demonstrated impressive capabilities at tasks that require human intelligence.
Yet the reasoning capability of LLMs is a matter of significant debate.
We introduce a framework for what we call Combinatorial Reasoning (CR), a fully-automated prompting method.
arXiv Detail & Related papers (2024-06-19T16:47:44Z) - What Matters in Hierarchical Search for Combinatorial Reasoning Problems? [0.0]
Recent efforts have sought to enhance planning by incorporating hierarchical high-level search strategies, known as subgoal methods.
While promising, their performance against traditional low-level planners is inconsistent, raising questions about their application contexts.
We identify the attributes pivotal for leveraging the advantages of high-level search: hard-to-learn value functions, complex action spaces, presence of dead ends in the environment, or using data collected from diverse experts.
arXiv Detail & Related papers (2024-06-05T15:14:58Z) - Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Models [84.15513004135576]
Current research enhances the reasoning performance of Large Language Models (LLMs) by sampling multiple reasoning chains and ensembling based on the answer frequency.
This approach fails in scenarios where the correct answers are in the minority.
We introduce a hierarchical reasoning aggregation framework AoR, which selects answers based on the evaluation of reasoning chains.
arXiv Detail & Related papers (2024-05-21T17:12:19Z) - Tree-of-Mixed-Thought: Combining Fast and Slow Thinking for Multi-hop
Visual Reasoning [16.495754104540605]
Large language models (LLMs) can generate code-like plans for complex inference tasks such as visual reasoning.
We propose a hierarchical plan-searching algorithm that integrates the one-stop reasoning (fast) and the Tree-of-thought (slow)
arXiv Detail & Related papers (2023-08-18T16:21:40Z) - Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement [50.62461749446111]
Self-Polish (SP) is a novel method that facilitates the model's reasoning by guiding it to progressively refine the given problems to be more comprehensible and solvable.
SP is to all other prompting methods of answer/reasoning side like CoT, allowing for seamless integration with state-of-the-art techniques for further improvement.
arXiv Detail & Related papers (2023-05-23T19:58:30Z) - Reasoning Circuits: Few-shot Multihop Question Generation with
Structured Rationales [11.068901022944015]
Chain-of-thought rationale generation has been shown to improve performance on multi-step reasoning tasks.
We introduce a new framework for applying chain-of-thought inspired structured rationale generation to multi-hop question generation under a very low supervision regime.
arXiv Detail & Related papers (2022-11-15T19:36:06Z) - Learning to Reason With Relational Abstractions [65.89553417442049]
We study how to build stronger reasoning capability in language models using the idea of relational abstractions.
We find that models that are supplied with such sequences as prompts can solve tasks with a significantly higher accuracy.
arXiv Detail & Related papers (2022-10-06T00:27:50Z) - Complexity-Based Prompting for Multi-Step Reasoning [72.0057198610614]
We study the task of prompting large-scale language models to perform multi-step reasoning.
A central question is which reasoning examples make the most effective prompts.
We propose complexity-based prompting, a simple and effective example selection scheme for multi-step reasoning.
arXiv Detail & Related papers (2022-10-03T05:33:27Z) - Reinforcement Learning for Branch-and-Bound Optimisation using
Retrospective Trajectories [72.15369769265398]
Machine learning has emerged as a promising paradigm for branching.
We propose retro branching; a simple yet effective approach to RL for branching.
We outperform the current state-of-the-art RL branching algorithm by 3-5x and come within 20% of the best IL method's performance on MILPs with 500 constraints and 1000 variables.
arXiv Detail & Related papers (2022-05-28T06:08:07Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.