Pith. sign in

REVIEW 9 cited by

CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.01976 v6 pith:AIZJIPD3 submitted 2025-02-04 cs.CL cs.AIcs.LGcs.PF

CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing

classification cs.CL cs.AIcs.LGcs.PF
keywords citerinferenceroutingcoststoken-levellanguagelargerouter
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large language models have achieved remarkable success in various tasks but suffer from high computational costs during inference, limiting their deployment in resource-constrained applications. To address this issue, we propose a novel Collaborative Inference with Token-lEvel Routing (CITER) framework that enables efficient collaboration between small and large language models (SLMs \& LLMs) through a token-level routing strategy. Specifically, CITER routes non-critical tokens to an SLM for efficiency and routes critical tokens to an LLM for generalization quality. We formulate router training as a policy optimization, where the router receives rewards based on both the quality of predictions and the inference costs of generation. This allows the router to learn to predict token-level routing scores and make routing decisions based on both the current token and the future impact of its decisions. To further accelerate the reward evaluation process, we introduce a shortcut which significantly reduces the costs of the reward estimation and improving the practicality of our approach. Extensive experiments on five benchmark datasets demonstrate that CITER reduces the inference costs while preserving high-quality generation, offering a promising solution for real-time and resource-constrained applications. Our data and code are available at https://github.com/aiming-lab/CITER.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order Optimization

    cs.LG 2026-04 unverdicted novelty 7.0

    NI Sampling accelerates discrete diffusion language models up to 14.3 times by training a neural indicator to select which tokens to sample at each step using a trajectory-preserving objective.

  2. Sampling from Your Language Model One Byte at a Time

    cs.CL 2025-06 unverdicted novelty 7.0

    An inference-time technique turns BPE-based LMs into byte- or character-level models, solving the prompt boundary problem while unifying vocabularies across different tokenizers.

  3. Divergence Decoding: Training-Free Capability Fusion

    cs.AI 2026-07 conditional novelty 6.0

    Divergence Decoding routes each token to either a domain specialist or a general reasoning LLM based on Jensen-Shannon divergence, outperforming either model alone on most tested scientific tasks.

  4. TRACE-ROUTER: Task-Consistent and Adaptive Online Routing for Agentic AI

    cs.AI 2026-07 conditional novelty 6.0

    Task-consistent sticky routing with a contextual bandit improves accuracy-latency trade-offs on agentic benchmarks by learning from delayed task-level reward.

  5. PyroDash: Cost-Efficient Token-Level Small-Large Language Model Collaborative Inference

    cs.CL 2026-07 conditional novelty 6.0

    PyroDash lets a small model decide mid-generation to hand off once to a frozen LLM, achieving 64.04% accuracy (+6.36 points vs LLM) at lambda=0.05 and 96.4% lower estimated cost at lambda=0.6.

  6. Rethinking LLM Ensembling from the Perspective of Mixture Models

    cs.LG 2026-05 unverdicted novelty 6.0

    ME reinterprets LLM ensembling as token-level sampling from a mixture model, enabling single-model invocation per token with claimed mathematical equivalence to full ensembling and measured speedups of 1.78x-2.68x.

  7. Rethinking LLM Ensembling from the Perspective of Mixture Models

    cs.LG 2026-05 unverdicted novelty 6.0

    ME reinterprets LLM ensembling as a mixture model by sampling a single model stochastically at each token step, matching the ensemble distribution while invoking only one model per step for substantial speed gains.

  8. Accelerating Heterogeneous Agent Collaboration in Dynamic Edge Networks

    cs.NI 2026-04 conditional novelty 6.0

    PRADA distills a process reward model into an edge screening policy and uses a threshold-based server scheduler to retain most LLM reasoning accuracy while sharply cutting multi-user latency.

  9. Harnessing Multiple Large Language Models: A Survey on LLM Ensemble

    cs.CL 2025-02 unverdicted novelty 2.0

    A systematic survey of LLM ensemble methods organized into a taxonomy of ensemble-before-inference, ensemble-during-inference, and ensemble-after-inference stages, with review of benchmarks, applications, and future d...