Path-Consistency with Prefix Enhancement for Efficient Inference in LLMs

• URL: http://arxiv.org/abs/2409.01281v3
• Date: Tue, 04 Nov 2025 05:59:14 GMT
• Title: Path-Consistency with Prefix Enhancement for Efficient Inference in LLMs
• Authors: Jiace Zhu, Yuanzhe Huang, Yingtao Shen, Jie Zhao, An Zou,
• Abstract summary: path-consistency improves inference latency by up to 40.5%, while maintaining task accuracy across various tasks.<n>Our empirical results demonstrate that path-consistency improves inference latency by up to 40.5%, while maintaining task accuracy across various tasks.
• Score: 3.6696973040141034
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: To enhance the reasoning capabilities of large language models (LLMs), self-consistency has become a popular approach, combining multiple samplings with majority voting. However, current methods are computationally expensive and time-consuming due to the need for numerous samplings. To address this, this paper introduces path-consistency, which leverages the confidence of earlier-generated answers to identify the most promising prefix and guide the generation of subsequent branches. By dynamically guiding the generation of subsequent branches based on this prefix, path-consistency mitigates both the errors and redundancies from random or less useful sampling in self-consistency. This approach reduces errors and redundancies from random sampling, significantly accelerating inference by minimizing token consumption. Our extensive empirical results demonstrate that path-consistency improves inference latency by up to 40.5\%, while maintaining task accuracy across various tasks, including mathematical reasoning, commonsense reasoning, and symbolic reasoning.

Related papers

• Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching [66.39914384073145]
  We propose a self-consistency framework that turns cheap diffusion-sampled reasoning into a reusable pool of step-level candidates.<n>We find that step-level recombination is most beneficial on harder problems.<n>Our training-free framework improves average accuracy by up to 2 across six math and coding tasks.
  arXiv  Detail & Related papers  (2026-02-26T11:08:39Z)
• Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models [29.56923793047279]
  We introduce Dynamic Outlier Truncation (DOT), a training-time intervention that selectively suppresses redundant tokens.<n>DOT targets only the extreme tail of response lengths within fully correct rollout groups while preserving long-horizon reasoning capabilities.<n>Our method reduces inference token usage by 78% while simultaneously increasing accuracy compared to the initial policy.
  arXiv  Detail & Related papers  (2026-01-07T14:31:07Z)
• Arbitrage: Efficient Reasoning via Advantage-Aware Speculation [71.45710345765528]
  Speculative Decoding accelerates inference by employing a fast but inaccurate draft model to autoregressively propose tokens.<n>But due to unnecessary rejections caused by token mismatches in semantically equivalent steps, traditional token-level Speculative Decoding struggles in reasoning tasks.<n>We propose Arbitrage, a novel step-level speculative generation framework that routes generation dynamically based on the relative advantage between draft and target models.
  arXiv  Detail & Related papers  (2025-12-04T17:50:53Z)
• Efficient Thought Space Exploration through Strategic Intervention [54.35208611253168]
  We propose a novel Hint-Practice Reasoning (HPR) framework that operationalizes this insight through two synergistic components.<n>The framework's core innovation lies in Distributional Inconsistency Reduction (DIR), which dynamically identifies intervention points.<n> Experiments across arithmetic and commonsense reasoning benchmarks demonstrate HPR's state-of-the-art efficiency-accuracy tradeoffs.
  arXiv  Detail & Related papers  (2025-11-13T07:26:01Z)
• Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall [28.243098541421755]
  We introduce Loopholing, a novel and simple mechanism that preserves information via a deterministic latent pathway.<n>LDDMs achieve substantial gains-reducing generative perplexity by up to 61% over prior baselines.<n>Results also indicate that loopholing mitigates idle steps and oscillations, providing a scalable path toward high-quality non-autoregressive text generation.
  arXiv  Detail & Related papers  (2025-10-22T07:08:47Z)
• Efficiently Generating Correlated Sample Paths from Multi-step Time Series Foundation Models [66.60042743462175]
  We present a copula-based approach to efficiently generate accurate, correlated sample paths from time series foundation models.<n>Our approach generates correlated sample paths orders of magnitude faster than autoregressive sampling.
  arXiv  Detail & Related papers  (2025-10-02T17:08:58Z)
• PCSR: Pseudo-label Consistency-Guided Sample Refinement for Noisy Correspondence Learning [17.302186298424836]
  Cross-modal retrieval aims to align different modalities via semantic similarity.<n>Existing methods often assume that image-text pairs are perfectly aligned, overlooking Noisy Correspondences in real data.
  arXiv  Detail & Related papers  (2025-09-19T05:41:17Z)
• On the Bias of Next-Token Predictors Toward Systematically Inefficient Reasoning: A Shortest-Path Case Study [4.319482898846564]
  We study two key factors for improving reasoning in large language models.<n>We train decoder-only transformers on question-trace-answer triples using a custom tokenizer.<n>With the same training-token budget, models trained on inefficient traces generalize better to unseen graphs.
  arXiv  Detail & Related papers  (2025-07-07T18:00:06Z)
• Multipole Attention for Efficient Long Context Reasoning [64.94673641704289]
  Large Reasoning Models (LRMs) have shown promising accuracy improvements on complex problem-solving tasks.<n>LRMs need to generate long chain-of-thought reasoning in order to think before answering.<n>We introduce Multipole Attention, which accelerates autoregressive reasoning by only computing exact attention for the most important tokens.
  arXiv  Detail & Related papers  (2025-06-16T03:00:40Z)
• Accelerated Test-Time Scaling with Model-Free Speculative Sampling [58.69141724095398]
  We introduce STAND (STochastic Adaptive N-gram Drafting), a novel model-free speculative decoding approach.<n>We show that STAND reduces inference latency by 60-65% compared to standard autoregressive decoding.<n>As a model-free approach, STAND can be applied to any existing language model without additional training.
  arXiv  Detail & Related papers  (2025-06-05T07:31:18Z)
• Beyond Exponential Decay: Rethinking Error Accumulation in Large Language Models [0.0]
  We show that errors are not uniformly distributed but are concentrated at sparse "key tokens" representing critical decision junctions.<n>We propose a framework for next-generation systems centered on selective preservation of semantically vital tokens.
  arXiv  Detail & Related papers  (2025-05-30T03:57:31Z)
• PixelThink: Towards Efficient Chain-of-Pixel Reasoning [70.32510083790069]
  PixelThink is a simple yet effective scheme that integrates externally estimated task difficulty and internally measured model uncertainty.<n>It learns to compress reasoning length in accordance with scene complexity and predictive confidence.<n> Experimental results demonstrate that the proposed approach improves both reasoning efficiency and overall segmentation performance.
  arXiv  Detail & Related papers  (2025-05-29T17:55:49Z)
• LIMOPro: Reasoning Refinement for Efficient and Effective Test-time Scaling [29.721108461390973]
  We introduce PIR (Perplexity-based Importance Refinement), a principled framework that quantitatively evaluates the importance of each reasoning step.<n>PIR identifies and selectively prunes only low-importance functional steps while preserving progressive reasoning components.<n>Our approach demonstrates strong generalizability across different model sizes, data sources, and token budgets.
  arXiv  Detail & Related papers  (2025-05-25T15:17:57Z)
• Fractured Chain-of-Thought Reasoning [61.647243580650446]
  We introduce Fractured Sampling, a unified inference-time strategy that interpolates between full CoT and solution-only sampling.<n>We show that Fractured Sampling consistently achieves superior accuracy-cost trade-offs, yielding steep log-linear scaling gains in Pass@k versus token budget.
  arXiv  Detail & Related papers  (2025-05-19T11:30:41Z)
• Generative Recommendation with Continuous-Token Diffusion [11.23267167046234]
  We propose a novel framework for large language model (LLM)-based recommender systems (RecSys) DeftRec incorporates textbfdenoising ditextbfffusion models to enable LLM-based RecSys to seamlessly support continuous textbftoken as input and target. Given a continuous token as output, recommendations can be easily generated through score-based retrieval.
  arXiv  Detail & Related papers  (2025-04-16T12:01:03Z)
• Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Sampling [90.86991492288487]
  evaluating constraint on every token can be prohibitively expensive. LCD can distort the global distribution over strings, sampling tokens based only on local information. We show that our approach is superior to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-04-07T18:30:18Z)
• Saliency-driven Dynamic Token Pruning for Large Language Models [32.903622070917194]
  Saliency-driven Dynamic Token Pruning (SDTP) A lightweight saliency-driven prediction module is designed to estimate the importance score of each token with its hidden state. A ranking-based optimization strategy is proposed to minimize the ranking divergence of the saliency score and the predicted importance score.
  arXiv  Detail & Related papers  (2025-04-06T15:15:07Z)
• Scalable Best-of-N Selection for Large Language Models via Self-Certainty [65.31658824274894]
  Best-of-N selection is a key technique for improving the reasoning performance of Large Language Models. We propose self-certainty, a novel and efficient metric to estimate response quality without requiring external reward models. Our findings establish self-certainty as a practical and efficient way for improving LLM reasoning capabilities.
  arXiv  Detail & Related papers  (2025-02-25T19:08:07Z)
• 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.