SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding
- URL: http://arxiv.org/abs/2406.18200v1
- Date: Wed, 26 Jun 2024 09:33:41 GMT
- Title: SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding
- Authors: Zhenglin Wang, Jialong Wu, Yilong Lai, Congzhi Zhang, Deyu Zhou,
- Abstract summary: Large Language Models (LLMs) demonstrate remarkable emergent abilities across various tasks, yet fall short of complex reasoning and planning tasks.
This paper introduces SeeD, a novel and efficient inference framework to optimize runtime speed and GPU memory management concurrently.
- Score: 16.380389806465733
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large Language Models (LLMs) demonstrate remarkable emergent abilities across various tasks, yet fall short of complex reasoning and planning tasks. The tree-search-based reasoning methods address this by surpassing the capabilities of chain-of-thought prompting, encouraging exploration of intermediate steps. However, such methods introduce significant inference latency due to the systematic exploration and evaluation of multiple thought paths. This paper introduces SeeD, a novel and efficient inference framework to optimize runtime speed and GPU memory management concurrently. By employing a scheduled speculative execution, SeeD efficiently handles multiple iterations for the thought generation and the state evaluation, leveraging a rounds-scheduled strategy to manage draft model dispatching. Extensive experimental evaluations on three reasoning datasets demonstrate superior speedup performance of SeeD, providing a viable path for batched inference in training-free speculative decoding.
Related papers
- Fine-Tuning with Divergent Chains of Thought Boosts Reasoning Through Self-Correction in Language Models [63.36637269634553]
We present a novel method of further improving performance by requiring models to compare multiple reasoning chains.
We find that instruction tuning on DCoT datasets boosts the performance of even smaller, and therefore more accessible, language models.
arXiv Detail & Related papers (2024-07-03T15:01:18Z) - DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language Models [42.95876831743256]
Large language models (LLMs) have demonstrated emergent capabilities across diverse reasoning tasks via Chains-of-Thought prompting.
This paper addresses the challenge of enabling LLMs to autonomously select between fast and slow inference methods.
We introduce a dynamic decision-making framework that categorizes tasks into two distinct pathways: 'Fast', designated for tasks where the LLM quickly identifies a high-confidence solution, and 'Slow', allocated for tasks that the LLM perceives as complex.
arXiv Detail & Related papers (2024-07-01T06:45:13Z) - Can Github issues be solved with Tree Of Thoughts? [0.0]
This research introduces the application of the Tree of Thoughts (ToT) language model reasoning framework for enhancing the decision-making and problem-solving abilities of LLMs.
We experimentally deploy ToT in tackling a Github issue contained within an instance of the SWE-bench.
arXiv Detail & Related papers (2024-05-20T11:05:56Z) - Pattern-Aware Chain-of-Thought Prompting in Large Language Models [26.641713417293538]
Chain-of-thought (CoT) prompting can guide language models to engage in complex multi-step reasoning.
We show that the underlying reasoning patterns play a more crucial role in such tasks.
We propose Pattern-Aware CoT, a prompting method that considers the diversity of demonstration patterns.
arXiv Detail & Related papers (2024-04-23T07:50:00Z) - Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing [61.98556945939045]
We propose a framework to learn planning-based reasoning through Direct Preference Optimization (DPO) on collected trajectories.
Our results on challenging logical reasoning benchmarks demonstrate the effectiveness of our learning framework.
arXiv Detail & Related papers (2024-02-01T15:18:33Z) - PathFinder: Guided Search over Multi-Step Reasoning Paths [80.56102301441899]
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.
arXiv Detail & Related papers (2023-12-08T17:05:47Z) - Let's reward step by step: Step-Level reward model as the Navigators for
Reasoning [64.27898739929734]
Process-Supervised Reward Model (PRM) furnishes LLMs with step-by-step feedback during the training phase.
We propose a greedy search algorithm that employs the step-level feedback from PRM to optimize the reasoning pathways explored by LLMs.
To explore the versatility of our approach, we develop a novel method to automatically generate step-level reward dataset for coding tasks and observed similar improved performance in the code generation tasks.
arXiv Detail & Related papers (2023-10-16T05:21:50Z) - 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) - Densely Nested Top-Down Flows for Salient Object Detection [137.74130900326833]
This paper revisits the role of top-down modeling in salient object detection.
It designs a novel densely nested top-down flows (DNTDF)-based framework.
In every stage of DNTDF, features from higher levels are read in via the progressive compression shortcut paths (PCSP)
arXiv Detail & Related papers (2021-02-18T03:14:02Z) - Finding Action Tubes with a Sparse-to-Dense Framework [62.60742627484788]
We propose a framework that generates action tube proposals from video streams with a single forward pass in a sparse-to-dense manner.
We evaluate the efficacy of our model on the UCF101-24, JHMDB-21 and UCFSports benchmark datasets.
arXiv Detail & Related papers (2020-08-30T15:38:44Z)
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.