FutureBridge: Token Selection Beyond Local Preference in Collaborative Decoding

• URL: http://arxiv.org/abs/2608.06819v1
• Date: Fri, 07 Aug 2026 05:19:14 GMT
• Title: FutureBridge: Token Selection Beyond Local Preference in Collaborative Decoding
• Abstract summary: Token-level collaboration allows a large language model to assist a small language model when their predictions diverge.<n>We present FutureBridge, which ranks joint LLM-SLM token candidates according to how well they support the SLM's subsequent reasoning.
• Score: 22.821312636429713
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Token-level collaboration allows a large language model (LLM) to assist a small language model (SLM) when their predictions diverge. Existing methods either use LLM-generated intervention tokens or rank candidates with the LLM's next-token probabilities. Both rely on the LLM's local preference, even though an LLM-selected token may be difficult for the SLM to build on. We present FutureBridge, which ranks joint LLM-SLM token candidates according to how well they support the SLM's subsequent reasoning. During training, an answer-verified LLM trajectory supplies a fixed shared future, and a frozen SLM evaluates every candidate under this common context. The resulting counterfactual scores supervise a lightweight token reranker that observes only the current state and candidate token. At inference, FutureBridge uses the LLM only to expand the candidate pool, selects one token, and returns generation to the SLM without generating or appending a future suffix. Across five mathematical reasoning benchmarks, FutureBridge improves the Qwen3-1.7B SLM's Math Avg. by 35.1% relative to greedy SLM decoding. These results indicate that token selection benefits from modeling whether the receiving SLM can use each candidate to continue reasoning, rather than relying on the LLM's local preference alone.

Related papers

• Select to Think: Unlocking SLM Potential with Local Sufficiency [12.573615247126204]
  Small language models (SLMs) offer computational efficiency for scalable deployment, yet they often fall short of the reasoning power exhibited by larger counterparts (LLMs)<n>We propose SELECT TO THINK (S2T), which distills the selection logic into the SLM, empowering it to perform autonomous re-ranking without inferencetime dependency.
  arXiv  Detail & Related papers  (2026-04-29T17:51:39Z)
• Neural Bandit Based Optimal LLM Selection for a Pipeline of Tasks [11.389019661082415]
  We propose a neural contextual bandit-based algorithm that trains neural networks that model LLM success on each subtask in an online manner.<n> Experiments on telecommunications question answering and medical diagnosis prediction datasets illustrate the effectiveness of our proposed approach.
  arXiv  Detail & Related papers  (2025-08-13T17:19:41Z)
• LLM-Lasso: A Robust Framework for Domain-Informed Feature Selection and Regularization [59.75242204923353]
  We introduce LLM-Lasso, a framework that leverages large language models (LLMs) to guide feature selection in Lasso regression.<n>LLMs generate penalty factors for each feature, which are converted into weights for the Lasso penalty using a simple, tunable model.<n>Features identified as more relevant by the LLM receive lower penalties, increasing their likelihood of being retained in the final model.
  arXiv  Detail & Related papers  (2025-02-15T02:55:22Z)
• Efficient Real-time Refinement of Language Model Text Generation [65.1937138219008]
  Large language models (LLMs) have shown remarkable performance across a wide range of natural language tasks.<n>A critical challenge remains in that they sometimes generate factually incorrect answers.<n>We propose Streaming-VR, a novel approach designed to enhance the efficiency of verification and refinement of LLM outputs.
  arXiv  Detail & Related papers  (2025-01-14T03:59:48Z)
• Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models [49.48313161005423]
  A hybrid language model (HLM) architecture integrates a small language model (SLM) operating on a mobile device with a large language model (LLM) hosted at the base station (BS) of a wireless network.<n>The HLM token generation process follows the speculative inference principle: the SLM's vocabulary distribution is uploaded to the LLM, which either accepts or rejects it, with rejected tokens being resampled by the LLM.<n>We propose a novel HLM structure coined Uncertainty-aware opportunistic HLM (U-HLM), wherein the SLM locally measures its output uncertainty and skips both up
  arXiv  Detail & Related papers  (2024-12-17T09:08:18Z)
• Decoding with Limited Teacher Supervision Requires Understanding When to Trust the Teacher [11.136112399898481]
  How can small-scale large language models (LLMs) efficiently utilize the supervision of LLMs to improve their generative quality? We develop an algorithm to effectively aggregate the small-scale LLM and LLM predictions on initial tokens. We demonstrate that our method provides a consistent improvement over conventional decoding strategies.
  arXiv  Detail & Related papers  (2024-06-26T01:16:12Z)
• Looking Right is Sometimes Right: Investigating the Capabilities of Decoder-only LLMs for Sequence Labeling [0.0]
  Recent decoder-only large language models (LLMs) perform on par with smaller state-based encoders. We explore techniques for improving the SL performance of open LLMs on IE tasks by applying layer-wise removal of the causal mask. Our findings hold for diverse SL tasks, demonstrating that open LLMs with layer-dependent CM removal outperform strong-based encoders and even instruction-tuned LLMs.
  arXiv  Detail & Related papers  (2024-01-25T22:50:48Z)
• LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning [67.39585115936329]
  We argue that LLMs have inherent capabilities to handle long contexts without fine-tuning. We propose SelfExtend to extend the context window of LLMs by constructing bi-level attention information. We conduct comprehensive experiments on multiple benchmarks and the results show that our SelfExtend can effectively extend existing LLMs' context window length.
  arXiv  Detail & Related papers  (2024-01-02T18:30:51Z)
• LaGR-SEQ: Language-Guided Reinforcement Learning with Sample-Efficient Querying [71.86163159193327]
  Large language models (LLMs) have recently demonstrated their impressive ability to provide context-aware responses via text. This ability could potentially be used to predict plausible solutions in sequential decision making tasks pertaining to pattern completion. We introduce LaGR, which uses this predictive ability of LLMs to propose solutions to tasks that have been partially completed by a primary reinforcement learning (RL) agent.
  arXiv  Detail & Related papers  (2023-08-21T02:07:35Z)
• PALR: Personalization Aware LLMs for Recommendation [7.407353565043918]
  PALR aims to combine user history behaviors (such as clicks, purchases, ratings, etc.) with large language models (LLMs) to generate user preferred items. Our solution outperforms state-of-the-art models on various sequential recommendation tasks.
  arXiv  Detail & Related papers  (2023-05-12T17:21:33Z)
• Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling [95.9542389945259]
  Sentence scoring aims at measuring the likelihood of a sentence and is widely used in many natural language processing scenarios. We propose textitTranscormer -- a Transformer model with a novel textitsliding language modeling (SLM) for sentence scoring.
  arXiv  Detail & Related papers  (2022-05-25T18:00:09Z)

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.