SPD: Single Pass Decoding for Generative Reranking

• URL: http://arxiv.org/abs/2609.01807v2
• Date: Fri, 04 Sep 2026 17:18:00 GMT
• Title: SPD: Single Pass Decoding for Generative Reranking
• Abstract summary: Large language models (LLMs) achieve state-of-the-art generative ranking quality, but the ranking they produce must be decoded.<n>We introduce SPD (Single Forward Pass), a format-specialized decoding strategy that decodes all $N$ ordinals in $O(1)$ forward passes.<n>We show that LoRA-based fine-tuning combined with auto-regressive LLM ranking distillation reaches 28 ms end-to-end inference, a speed-up of 64x while maintaining ranking quality on par with the teacher.
• Score: 20.780080437181223
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) achieve state-of-the-art generative ranking quality, but the ranking they produce must be decoded, and autoregressive decoding spends one sequential forward pass per emitted token. We observe that the only tokens a ranker must emit are the $N$ ordinal values naming the items in ranked order, and that this narrow, permutation-structured output format admits decoding strategies which are much more efficient than left-to-right generation. We introduce SPD (Single Forward Pass), a format-specialized decoding strategy that decodes all $N$ ordinals in $O(1)$ forward passes. SPD reads an $N \times K$ item-position score matrix off the LLM's prefill hidden states with a lightweight self-attention head, then decodes the ordinals as the optimal bipartite assignment of that matrix via the Hungarian algorithm, yielding a valid permutation by construction rather than by repair. Through a systematic study of training signals and backbone adaptation, we show that LoRA-based fine-tuning combined with auto-regressive LLM ranking distillation reaches 28 ms end-to-end inference, a speed-up of 64x while maintaining ranking quality on par with the teacher. We provide a complete ablation decomposing the contributions of architecture, training signal, and backbone adaptation. Our framework connects generative ranking to combinatorial optimization, opening a path toward other $O(1)$-decode mechanisms for real-time ranking.

Related papers

• Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems [67.04448659688579]
  We develop a query-independent 16-entry codebook that ranks the top decoded candidates in a single batched forward pass.<n>With no iterative search and no message passing at test time, Codebook Agent is the most accurate method on all six benchmarks.
  arXiv  Detail & Related papers  (2026-09-02T08:10:22Z)
• SSTQ:Privacy-Preserving Vector Quantization via Subsampled Stochastic TurboQuant [79.24089819400126]
  Subsampled TurboQuant (SSTQ) is a framework that combines overcomplete equal-width tight frames, coordinate subsampling, and privacy-aware quantization.<n>SSTQ achieves mean squared error scaling while using only $lceil log N il + b$ bits per client, where $N = (d)$ is the frame size.<n>We also derive a surrogate privacy-aware codebook objective that reduces the codebook-dependent MSE scaling from $O(4b)$ to $O(2b)$.
  arXiv  Detail & Related papers  (2026-08-05T17:51:25Z)
• Dream at SemEval-2026 Task 13: SALSA for Single-Pass Machine-Generated Code Detection [1.9371675344367494]
  SemEval-2026 Task 13 Subtask A operationalizes detection as binary classification over code snippets.<n>We propose a SALSA-style formulation that maps each class to a dedicated output token and trains the model to emit a single-token label in a structured response.
  arXiv  Detail & Related papers  (2026-06-23T19:17:11Z)
• $\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space [71.23672814629448]
  $nabla$-Reasoner is an iterative generation framework that integrates differentiable optimization over token logits into the decoding loop.<n>$nabla$-Reasoner achieves over 20% accuracy improvement on a challenging mathematical reasoning benchmark.
  arXiv  Detail & Related papers  (2026-03-05T08:42:54Z)
• BLITZRANK: Principled Zero-shot Ranking Agents with Tournament Graphs [14.085089126904101]
  We introduce a tournament graph framework that provides a principled foundation for $k$-wise ranking.<n>Each $k$-item comparison reveals a complete tournament of $binomk2$ pairwise preferences.<n>We formalize when an item's rank is certifiably determined and design a greedy query schedule that maximizes information gain.
  arXiv  Detail & Related papers  (2026-02-05T08:41:00Z)
• Autoregressive Ranking: Bridging the Gap Between Dual and Cross Encoders [37.16464474575651]
  We show that pointwise generative ranking with multi-token docIDs is superior to that of dual encoders.<n>We propose SToICaL - a Simple Token-Item Calibrated Loss - which can incorporate rank-aware supervision at both the item and token levels.
  arXiv  Detail & Related papers  (2026-01-09T07:16:28Z)
• Route Experts by Sequence, not by Token [58.92918003265283]
  Mixture-of-Experts (MoE) architectures scale large language models (LLMs) by activating only a subset of experts per token.<n>The standard TopK routing assigns the same fixed number of experts to all tokens, ignoring their varying complexity.<n>We propose Sequence-level TopK (SeqTopK), a minimal modification that shifts the expert budget from the token level to the sequence level.
  arXiv  Detail & Related papers  (2025-11-09T18:36:07Z)
• Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning [70.6126069527741]
  ConvRec-R1 is a two-stage framework for end-to-end training of conversational recommender systems.<n>In Stage 1, we construct a behavioral-cloning dataset with a Remap-Reflect-Adjust pipeline.<n>In Stage 2, we propose Rank-GRPO, a principled extension of group relative policy optimization.
  arXiv  Detail & Related papers  (2025-10-23T02:56:00Z)
• Reinforcement Speculative Decoding for Fast Ranking [9.584558586988953]
  Large Language Models (LLMs) have been widely adopted in ranking systems such as information retrieval (IR) systems and recommender systems (RSs)<n>We propose a Reinforcementive Decoding method for fast ranking inference of LLMs.
  arXiv  Detail & Related papers  (2025-05-23T02:25:26Z)
• KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction [59.039355258637315]
  We propose KnowCoder, a Large Language Model (LLM) to conduct Universal Information Extraction (UIE) via code generation. KnowCoder introduces a code-style schema representation method to uniformly transform different schemas into Python classes. KnowCoder contains a two-phase learning framework that enhances its schema understanding ability via code pretraining and its schema following ability via instruction tuning.
  arXiv  Detail & Related papers  (2024-03-12T14:56:34Z)
• Learning-to-Rank Meets Language: Boosting Language-Driven Ordering Alignment for Ordinal Classification [60.28913031192201]
  We present a novel language-driven ordering alignment method for ordinal classification. Recent developments in pre-trained vision-language models inspire us to leverage the rich ordinal priors in human language. Experiments on three ordinal classification tasks, including facial age estimation, historical color image (HCI) classification, and aesthetic assessment demonstrate its promising performance.
  arXiv  Detail & Related papers  (2023-06-24T04:11:31Z)
• Order-sensitive Neural Constituency Parsing [9.858565876426411]
  We propose a novel algorithm that improves on the previous neural span-based CKY decoder for constituency parsing. In contrast to the traditional span-based decoding, we introduce an order-sensitive strategy, where the span combination scores are more carefully derived from an order-sensitive basis. Our decoder can be regarded as a generalization over existing span-based decoder in determining a finer-grain scoring scheme for the combination of lower-level spans into higher-level spans.
  arXiv  Detail & Related papers  (2022-11-01T12:31:30Z)
• Matching Pursuit Based Scheduling for Over-the-Air Federated Learning [67.59503935237676]
  This paper develops a class of low-complexity device scheduling algorithms for over-the-air learning via the method of federated learning. Compared to the state-of-the-art proposed scheme, the proposed scheme poses a drastically lower efficiency system. The efficiency of the proposed scheme is confirmed via experiments on the CIFAR dataset.
  arXiv  Detail & Related papers  (2022-06-14T08:14:14Z)
• Learning Autoencoders with Relational Regularization [89.53065887608088]
  A new framework is proposed for learning autoencoders of data distributions. We minimize the discrepancy between the model and target distributions, with a emphrelational regularization We implement the framework with two scalable algorithms, making it applicable for both probabilistic and deterministic autoencoders.
  arXiv  Detail & Related papers  (2020-02-07T17:27:30Z)

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.