Communication-Efficient Hybrid Language Model via Uncertainty-Aware Opportunistic and Compressed Transmission

• URL: http://arxiv.org/abs/2505.11788v1
• Date: Sat, 17 May 2025 02:10:34 GMT
• Title: Communication-Efficient Hybrid Language Model via Uncertainty-Aware Opportunistic and Compressed Transmission
• Authors: Seungeun Oh, Jinhyuk Kim, Jihong Park, Seung-Woo Ko, Jinho Choi, Tony Q. S. Quek, Seong-Lyun Kim,
• Abstract summary: Hybrid language model (HLM) generates draft tokens that are validated and corrected by a remote large language model (LLM)<n>We propose communication-efficient and uncertainty-aware HLM (CU-HLM)<n>We show that CU-HLM achieves up to 206$times$ higher token throughput by skipping 74.8% transmissions with 97.4% vocabulary compression, while maintaining 97.4% accuracy.
• Score: 65.17811759381978
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: To support emerging language-based applications using dispersed and heterogeneous computing resources, the hybrid language model (HLM) offers a promising architecture, where an on-device small language model (SLM) generates draft tokens that are validated and corrected by a remote large language model (LLM). However, the original HLM suffers from substantial communication overhead, as the LLM requires the SLM to upload the full vocabulary distribution for each token. Moreover, both communication and computation resources are wasted when the LLM validates tokens that are highly likely to be accepted. To overcome these limitations, we propose communication-efficient and uncertainty-aware HLM (CU-HLM). In CU-HLM, the SLM transmits truncated vocabulary distributions only when its output uncertainty is high. We validate the feasibility of this opportunistic transmission by discovering a strong correlation between SLM's uncertainty and LLM's rejection probability. Furthermore, we theoretically derive optimal uncertainty thresholds and optimal vocabulary truncation strategies. Simulation results show that, compared to standard HLM, CU-HLM achieves up to 206$\times$ higher token throughput by skipping 74.8% transmissions with 97.4% vocabulary compression, while maintaining 97.4% accuracy.

Related papers

• Federated Learning-Enabled Hybrid Language Models for Communication-Efficient Token Transmission [87.68447072141402]
  Hybrid Language Models (HLMs) combine the low-latency efficiency of Small Language Models (SLMs) on edge devices with the high accuracy of Large Language Models (LLMs) on centralized servers.<n>We propose FedHLM, a communication-efficient HLM framework that integrates uncertainty-aware inference with Federated Learning (FL)
  arXiv  Detail & Related papers  (2025-06-30T02:56:11Z)
• 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)
• REQUAL-LM: Reliability and Equity through Aggregation in Large Language Models [10.684722193666607]
  We introduce REQUAL-LM, a novel method for finding reliable and equitable large language models (LLMs) outputs through aggregation. Specifically, we develop a Monte Carlo method based on repeated sampling to find a reliable output close to the mean of the underlying distribution of possible outputs. We formally define the terms such as reliability and bias, and design an equity-aware aggregation to minimize harmful bias while finding a highly reliable output.
  arXiv  Detail & Related papers  (2024-04-17T22:12:41Z)
• Beyond Natural Language: LLMs Leveraging Alternative Formats for Enhanced Reasoning and Communication [79.79948834910579]
  Natural language (NL) has long been the predominant format for human cognition and communication. In this work, we challenge the default use of NL by exploring the utility of non-NL formats in different contexts.
  arXiv  Detail & Related papers  (2024-02-28T16:07:54Z)
• Language Models with Conformal Factuality Guarantees [44.767328168194815]
  Conformal factuality is a framework that can ensure high probability correctness guarantees for language model (LM) outputs. We show that conformal prediction in language models corresponds to a back-off algorithm that provides high probability correctness guarantees.
  arXiv  Detail & Related papers  (2024-02-15T18:31:53Z)
• Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes [53.4856038354195]
  Pre-trained large language models (LLMs) need fine-tuning to improve their responsiveness to natural language instructions. FedKSeed employs zeroth-order optimization with a finite set of random seeds. It significantly reduces transmission requirements between the server and clients to just a few random seeds.
  arXiv  Detail & Related papers  (2023-12-11T13:03:21Z)
• Let Models Speak Ciphers: Multiagent Debate through Embeddings [84.20336971784495]
  We introduce CIPHER (Communicative Inter-Model Protocol Through Embedding Representation) to address this issue. By deviating from natural language, CIPHER offers an advantage of encoding a broader spectrum of information without any modification to the model weights. This showcases the superiority and robustness of embeddings as an alternative "language" for communication among LLMs.
  arXiv  Detail & Related papers  (2023-10-10T03:06:38Z)

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.