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

• Learning More Effective Representations for Dense Retrieval through Deliberate Thinking Before Search [65.53881294642451]
  Deliberate Thinking based Dense Retriever (DEBATER) DEBATER enhances recent dense retrievers by enabling them to learn more effective document representations through a step-by-step thinking process. Experimental results show that DEBATER significantly outperforms existing methods across several retrieval benchmarks.
  arXiv  Detail & Related papers  (2025-02-18T15:56:34Z)
• Inference-Time Computations for LLM Reasoning and Planning: A Benchmark and Insights [49.42133807824413]
  We examine the reasoning and planning capabilities of large language models (LLMs) in solving complex tasks. Recent advances in inference-time techniques demonstrate the potential to enhance LLM reasoning without additional training. OpenAI's o1 model shows promising performance through its novel use of multi-step reasoning and verification.
  arXiv  Detail & Related papers  (2025-02-18T04:11:29Z)
• BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning [78.63421517563056]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. We present a unified probabilistic framework that formalizes LLM reasoning through a novel graphical model. We introduce the Bootstrapping Reinforced Thinking Process (BRiTE) algorithm, which works in two steps.
  arXiv  Detail & Related papers  (2025-01-31T02:39:07Z)
• Optimizing Chain-of-Thought Reasoning: Tackling Arranging Bottleneck via Plan Augmentation [34.042565099565934]
  We propose a plan-based training and reasoning method that guides models to generate arranging steps through abstract plans. Results show that compared to fine-tuning directly with CoT data, our approach achieves a better performance on alleviating arranging bottleneck.
  arXiv  Detail & Related papers  (2024-10-22T08:38:50Z)
• Spatial Reasoning and Planning for Deep Embodied Agents [2.7195102129095003]
  This thesis explores the development of data-driven techniques for spatial reasoning and planning tasks. It focuses on enhancing learning efficiency, interpretability, and transferability across novel scenarios.
  arXiv  Detail & Related papers  (2024-09-28T23:05:56Z)
• Bidirectional Decoding: Improving Action Chunking via Closed-Loop Resampling [51.38330727868982]
  Bidirectional Decoding (BID) is a test-time inference algorithm that bridges action chunking with closed-loop operations. We show that BID boosts the performance of two state-of-the-art generative policies across seven simulation benchmarks and two real-world tasks.
  arXiv  Detail & Related papers  (2024-08-30T15:39:34Z)
• 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)
• 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)
• 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)

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.