Path-Consistency: Prefix Enhancement for Efficient Inference in LLM

• URL: http://arxiv.org/abs/2409.01281v1
• Date: Sun, 25 Aug 2024 01:45:53 GMT
• Title: Path-Consistency: Prefix Enhancement for Efficient Inference in LLM
• Authors: Jiace Zhu, Yingtao Shen, Jie Zhao, An Zou,
• Abstract summary: textitpath-consistency mitigates both the errors and redundancies from random or less useful sampling in self-consistency. textitpath-consistency achieves significant acceleration in inference latency ranging from $7.8%$ to $40.5%$.
• Score: 3.309813585671485
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: To enhance the reasoning capabilities of large language models (LLMs), self-consistency has gained significant popularity by combining multiple sampling with majority voting. However, the state-of-the-art self-consistency approaches consume substantial computational resources and lead to significant additional time costs due to the multiple sampling. This prevents its full potential from being realized in scenarios where computational resources are critical. To improve the inference efficiency, this paper introduces \textit{path-consistency}, a method that leverages the confidence of answers generated in earlier branches to identify the prefix of the most promising path. By dynamically guiding the generation of subsequent branches based on this prefix, the \textit{path-consistency} mitigates both the errors and redundancies from random or less useful sampling in self-consistency. As a result, it can significantly accelerate the inference process by reducing the number of tokens generated. Our extensive empirical evaluation shows that the \textit{path-consistency} achieves significant acceleration in inference latency ranging from $7.8\%$ to $40.5\%$, while maintaining or even improving task accuracy across different datasets, including mathematical reasoning, common sense reasoning, symbolic reasoning, and code generation.

Related papers

• COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement [80.18490952057125]
  Iterative refinement has emerged as an effective paradigm for enhancing the capabilities of large language models (LLMs) on complex tasks. We propose Context-Wise Order-Agnostic Language Modeling (COrAL) to overcome these challenges. Our approach models multiple token dependencies within manageable context windows, enabling the model to perform iterative refinement internally.
  arXiv  Detail & Related papers  (2024-10-12T23:56:19Z)
• Integrative Decoding: Improve Factuality via Implicit Self-consistency [45.27124252002816]
  Self-consistency-based approaches are remarkably effective in improving the factual accuracy of large language models. We present Integrative Decoding (ID), to unlock the potential of self-consistency in open-ended generation tasks.
  arXiv  Detail & Related papers  (2024-10-02T13:52:55Z)
• Dynamic Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling [9.44858963874474]
  Self-Consistency (SC) results in significant computational costs proportional to the number of samples generated. We propose Reasoning-Aware Self-Consistency (RASC), an innovative early-stopping framework that adjusts the number of sample generations. RASC significantly reduces sample usage by an average of 80% while maintaining or improving accuracy up to 5% compared to the original SC.
  arXiv  Detail & Related papers  (2024-08-30T05:14:59Z)
• Parallel Decoding via Hidden Transfer for Lossless Large Language Model Acceleration [54.897493351694195]
  We propose a novel parallel decoding approach, namely textithidden transfer, which decodes multiple successive tokens simultaneously in a single forward pass. In terms of acceleration metrics, we outperform all the single-model acceleration techniques, including Medusa and Self-Speculative decoding.
  arXiv  Detail & Related papers  (2024-04-18T09:17:06Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• Lookahead: An Inference Acceleration Framework for Large Language Model with Lossless Generation Accuracy [46.81745860690336]
  Large Language Models (LLMs) have made significant advancements across various tasks, such as question answering, translation, text summarization, and dialogue systems. This paper presents a generic framework for accelerating the inference process, resulting in a substantial increase in speed and cost reduction. We conduct extensive experiments to demonstrate the significant improvements achieved by applying our inference acceleration framework.
  arXiv  Detail & Related papers  (2023-12-20T02:55:15Z)
• Deep Ensembles Meets Quantile Regression: Uncertainty-aware Imputation for Time Series [45.76310830281876]
  We propose Quantile Sub-Ensembles, a novel method to estimate uncertainty with ensemble of quantile-regression-based task networks. Our method not only produces accurate imputations that is robust to high missing rates, but also is computationally efficient due to the fast training of its non-generative model.
  arXiv  Detail & Related papers  (2023-12-03T05:52:30Z)
• Amortizing intractable inference in large language models [56.92471123778389]
  We use amortized Bayesian inference to sample from intractable posterior distributions. We empirically demonstrate that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training. As an important application, we interpret chain-of-thought reasoning as a latent variable modeling problem.
  arXiv  Detail & Related papers  (2023-10-06T16:36:08Z)
• Improving Out-of-Distribution Generalization of Neural Rerankers with Contextualized Late Interaction [52.63663547523033]
  Late interaction, the simplest form of multi-vector, is also helpful to neural rerankers that only use the [] vector to compute the similarity score. We show that the finding is consistent across different model sizes and first-stage retrievers of diverse natures.
  arXiv  Detail & Related papers  (2023-02-13T18:42:17Z)
• Confident Adaptive Language Modeling [95.45272377648773]
  CALM is a framework for dynamically allocating different amounts of compute per input and generation timestep. We demonstrate the efficacy of our framework in reducing compute -- potential speedup of up to $times 3$ -- while provably maintaining high performance.
  arXiv  Detail & Related papers  (2022-07-14T17:00:19Z)

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.