ResiSpec: Enhancing Multi-Candidate Speculative Sampling via Residual Distribution Shaping

• URL: http://arxiv.org/abs/2608.24411v1
• Date: Tue, 25 Aug 2026 11:25:55 GMT
• Title: ResiSpec: Enhancing Multi-Candidate Speculative Sampling via Residual Distribution Shaping
• Abstract summary: ResiSpec is a framework that strategically reforms the proposal distribution during verification.<n>It prevents candidate obsolescence and achieves up to 1.92$times$ speedup over state-of-the-art multi-candidate methods.
• Score: 79.1905186547363
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The efficiency of Large Language Model (LLM) serving is fundamentally limited by the sequential nature of autoregressive decoding. Speculative Decoding (SD) mitigates this by using a lightweight draft model to speculate future tokens, which are then validated by the LLM in a single parallel forward pass. To further boost efficiency, multi-candidate schemes propose diverse candidate sets to increase the likelihood of token acceptance. However, we show that these schemes are bottlenecked by Residual Drift: a phenomenon where the rejection of initial candidates causes the residual target distribution to diverge from the draft model's predictions. This shift renders subsequent candidates ineffective and forces the system into expensive resampling. To resolve this, we propose ResiSpec, a framework that strategically reforms the proposal distribution during verification to anchor the residual target mass within the draft model's high-confidence regions. By mathematically re-aligning the verification process without compromising output exactness, ResiSpec prevents candidate obsolescence and achieves up to 1.92$\times$ speedup over state-of-the-art multi-candidate methods. Code is available at https://github.com/Czzzk/Resispec.

Related papers

• Selective Regenerative Decoding: Trajectory-Level Intervention for Inference-Time Reasoning [12.065412919637525]
  Selective Regenerative Decoding routes each candidate to discard, keep, or refine only the degraded portion of the suffix.<n>SRD achieves a provable 1.28-to-1.36-fold gain in sample efficiency over rejection sampling.<n>Across MATH500, GPQA Diamond, HotpotQA, and AlpacaEval with multiple generation-reward model pairs, SRD matches Best-of-N accuracy with substantially fewer generated tokens.
  arXiv  Detail & Related papers  (2026-08-25T10:01:56Z)
• The Model Knows, the Decoder Finds: Future Value Guided Particle Power Sampling [13.856943842803561]
  Auxiliary Particle Power Sampling (APPS) is a blockwise particle algorithm for approxing the sequence-level power target with a bounded population of partial solutions.<n>APPS propagates hypotheses in parallel using proposal-corrected power reweighting and refines their survival through future-value-guided selection.<n>APPS improves the accuracy-runtime trade-off of training-free decoding and suggests that part of the gap to post-trained systems can be recovered through more faithful inference-time power approximation.
  arXiv  Detail & Related papers  (2026-05-04T10:26:34Z)
• PROMISE: Process Reward Models Unlock Test-Time Scaling Laws in Generative Recommendations [52.67948063133533]
  Generative Recommendation has emerged as a promising paradigm, reformulating recommendation as a sequence-to-sequence generation task over hierarchical Semantic IDs.<n>Existing methods suffer from a critical issue we term Semantic Drift, where errors in early, high-level tokens irreversibly divert the generation trajectory into irrelevant semantic subspaces.<n>We propose Promise, a novel framework that integrates dense, step-by-step verification into generative models.
  arXiv  Detail & Related papers  (2026-01-08T07:38:46Z)
• Efficient Adaptive Rejection Sampling for Accelerating Speculative Decoding in Large Language Models [2.4065240342323384]
  This paper introduces Efficient Adaptive Rejection Sampling (EARS)<n>EARS dynamically adjusts the acceptance threshold by incorporating the target model's own predictive uncertainty, measured as 1 - max(P_target)<n>It significantly enhances the efficiency of speculative decoding, achieving up to an 18.12% increase in throughput with a negligible 0.84% accuracy drop on the GSM8K benchmark.
  arXiv  Detail & Related papers  (2025-12-15T11:08:56Z)
• Think Before You Accept: Semantic Reflective Verification for Faster Speculative Decoding [48.52389201779425]
  Speculative decoding accelerates inference by generating multiple draft tokens using a lightweight model and verifying them in parallel.<n>Existing verification methods rely heavily on distributional consistency while overlooking semantic correctness.<n>We propose Reflective Verification, a training-free and semantics-aware approach that achieves a better trade-off between correctness and efficiency.
  arXiv  Detail & Related papers  (2025-05-24T10:26:27Z)
• Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE [15.003006630308517]
  Speculative decoding (SD) accelerates large language model inference by using a smaller draft model to predict multiple tokens.<n>We propose Jakiro, leveraging Mixture of Experts (MoE), where independent experts generate diverse predictions.<n>Our method significantly boosts prediction accuracy and achieves higher inference speedups.
  arXiv  Detail & Related papers  (2025-02-10T09:24:06Z)
• Graph-Structured Speculative Decoding [52.94367724136063]
  Speculative decoding has emerged as a promising technique to accelerate the inference of Large Language Models. We introduce an innovative approach utilizing a directed acyclic graph (DAG) to manage the drafted hypotheses. We observe a remarkable speedup of 1.73$times$ to 1.96$times$, significantly surpassing standard speculative decoding.
  arXiv  Detail & Related papers  (2024-07-23T06:21:24Z)
• Multi-Candidate Speculative Decoding [82.05519287513444]
  Large language models have shown impressive capabilities across a variety of NLP tasks, yet their generating text autoregressively is time-consuming. One way to speed them up is speculative decoding, which generates candidate segments from a fast draft model that is then verified in parallel by the target model. This paper proposes sampling multiple candidates from a draft model and then organising them in batches for verification. We design algorithms for efficient multi-candidate verification while maintaining the distribution of the target model.
  arXiv  Detail & Related papers  (2024-01-12T17:15:23Z)
• 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)

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.