RATT: A Thought Structure for Coherent and Correct LLM Reasoning
- URL: http://arxiv.org/abs/2406.02746v3
- Date: Thu, 11 Jul 2024 06:07:19 GMT
- Title: RATT: A Thought Structure for Coherent and Correct LLM Reasoning
- Authors: Jinghan Zhang, Xiting Wang, Weijieying Ren, Lu Jiang, Dongjie Wang, Kunpeng Liu,
- Abstract summary: We introduce the Retrieval Augmented Thought Tree (RATT), a novel thought structure that considers both overall logical soundness and factual correctness at each step of the thinking process.
A range of experiments on different types of tasks showcases that the RATT structure significantly outperforms existing methods in factual correctness and logical coherence.
- Score: 23.28162642780579
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large Language Models (LLMs) gain substantial reasoning and decision-making capabilities from thought structures. However, existing methods such as Tree of Thought and Retrieval Augmented Thoughts often fall short in complex tasks due to the limitations of insufficient local retrieval of factual knowledge and inadequate global selection of strategies. These limitations make it challenging for these methods to balance factual accuracy and comprehensive logical optimization effectively. To address these limitations, we introduce the Retrieval Augmented Thought Tree (RATT), a novel thought structure that considers both overall logical soundness and factual correctness at each step of the thinking process. Specifically, at every point of a thought branch, RATT performs planning and lookahead to explore and evaluate multiple potential reasoning steps, and integrate the fact-checking ability of Retrieval-Augmented Generation (RAG) with LLM's ability to assess overall strategy. Through this combination of factual knowledge and strategic feasibility, the RATT adjusts and integrates the thought tree structure to search for the most promising branches within the search space. This thought structure significantly enhances the model's coherence in logical inference and efficiency in decision-making, and thus increases the limit of the capacity of LLM to generate reliable inferences and decisions based on thought structures. A broad range of experiments on different types of tasks showcases that the RATT structure significantly outperforms existing methods in factual correctness and logical coherence.
Related papers
- Multi-step Inference over Unstructured Data [2.169874047093392]
High-stakes decision-making tasks in fields such as medical, legal and finance require a level of precision, comprehensiveness, and logical consistency.
We have developed a neuro-symbolic AI platform to tackle these problems.
The platform integrates fine-tuned LLMs for knowledge extraction and alignment with a robust symbolic reasoning engine.
arXiv Detail & Related papers (2024-06-26T00:00:45Z) - 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) - Logic Agent: Enhancing Validity with Logic Rule Invocation [24.815341366820753]
Chain-of-Thought prompting has emerged as a pivotal technique for augmenting the inferential capabilities of language models during reasoning tasks.
This paper introduces the Logic Agent (LA), an agent-based framework aimed at enhancing the validity of reasoning processes in Large Language Models.
arXiv Detail & Related papers (2024-04-28T10:02:28Z) - K-Level Reasoning with Large Language Models [80.13817747270029]
We explore the dynamic reasoning capabilities of Large Language Models (LLMs) for decision-making in rapidly evolving environments.
We introduce two game theory-based pilot challenges that mirror the complexities of real-world dynamic decision-making.
These challenges are well-defined, enabling clear, controllable, and precise evaluation of LLMs' dynamic reasoning abilities.
arXiv Detail & Related papers (2024-02-02T16:07:05Z) - Constrained Bayesian Optimization with Adaptive Active Learning of
Unknown Constraints [10.705151736050967]
optimizing objectives under constraints is a common scenario in real-world applications such as scientific experimental design, design of medical therapies, and industrial process optimization.
We propose an efficient CBO framework that intersects the ROIs identified from each aspect to determine the general ROI.
We showcase the efficiency and robustness of our proposed CBO framework through empirical evidence and discuss the fundamental challenge of deriving practical regret bounds for CBO algorithms.
arXiv Detail & Related papers (2023-10-12T22:32:00Z) - Risk-reducing design and operations toolkit: 90 strategies for managing
risk and uncertainty in decision problems [65.268245109828]
This paper develops a catalog of such strategies and develops a framework for them.
It argues that they provide an efficient response to decision problems that are seemingly intractable due to high uncertainty.
It then proposes a framework to incorporate them into decision theory using multi-objective optimization.
arXiv Detail & Related papers (2023-09-06T16:14:32Z) - When Do Program-of-Thoughts Work for Reasoning? [51.2699797837818]
We propose complexity-impacted reasoning score (CIRS) to measure correlation between code and reasoning abilities.
Specifically, we use the abstract syntax tree to encode the structural information and calculate logical complexity.
Code will be integrated into the EasyInstruct framework at https://github.com/zjunlp/EasyInstruct.
arXiv Detail & Related papers (2023-08-29T17:22:39Z) - 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) - Exploring Self-supervised Logic-enhanced Training for Large Language Models [59.227222647741094]
In this paper, we make the first attempt to investigate the feasibility of incorporating logical knowledge through self-supervised post-training.
We devise an auto-regressive objective variant of MERIt and integrate it with two LLM series, i.e., FLAN-T5 and LLaMA, with parameter size ranging from 3 billion to 13 billion.
The results on two challenging logical reasoning benchmarks demonstrate the effectiveness of LogicLLM.
arXiv Detail & Related papers (2023-05-23T06:13:10Z) - Investigating Bi-Level Optimization for Learning and Vision from a
Unified Perspective: A Survey and Beyond [114.39616146985001]
In machine learning and computer vision fields, despite the different motivations and mechanisms, a lot of complex problems contain a series of closely related subproblms.
In this paper, we first uniformly express these complex learning and vision problems from the perspective of Bi-Level Optimization (BLO)
Then we construct a value-function-based single-level reformulation and establish a unified algorithmic framework to understand and formulate mainstream gradient-based BLO methodologies.
arXiv Detail & Related papers (2021-01-27T16:20:23Z)
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.