Pith. sign in

REVIEW 3 cited by

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization

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 2502.04428 v1 pith:SUQUQRFV submitted 2025-02-06 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords routingdatallmsgeneralizationslmsstrongerbenchmarkingcalibration
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large language models (LLMs) are increasingly deployed and democratized on edge devices. To improve the efficiency of on-device deployment, small language models (SLMs) are often adopted due to their efficient decoding latency and reduced energy consumption. However, these SLMs often generate inaccurate responses when handling complex queries. One promising solution is uncertainty-based SLM routing, offloading high-stakes queries to stronger LLMs when resulting in low-confidence responses on SLM. This follows the principle of "If you lack confidence, seek stronger support" to enhance reliability. Relying on more powerful LLMs is yet effective but increases invocation costs. Therefore, striking a routing balance between efficiency and efficacy remains a critical challenge. Additionally, efficiently generalizing the routing strategy to new datasets remains under-explored. In this paper, we conduct a comprehensive investigation into benchmarking and generalization of uncertainty-driven routing strategies from SLMs to LLMs over 1500+ settings. Our findings highlight: First, uncertainty-correctness alignment in different uncertainty quantification (UQ) methods significantly impacts routing performance. Second, uncertainty distributions depend more on both the specific SLM and the chosen UQ method, rather than downstream data. Building on the insight, we propose a calibration data construction instruction pipeline and open-source a constructed hold-out set to enhance routing generalization on new downstream scenarios. The experimental results indicate calibration data effectively bootstraps routing performance without any new data.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models

    cs.AI 2026-01 conditional novelty 7.0 of 10

    Treating LoRA adapters as sparse-GP random variables with a normalizing flow yields up to 84% ECE and 76% NLL reduction at ~1.2x training cost, reverting to standard LoRA in a point-mass limit.

  2. Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models

    cs.CL 2025-06 conditional novelty 5.0 of 10

    Suppressing low-probability 'wait' tokens that trigger self-affirmation reflections shortens reasoning-model output by 8-18% with roughly unchanged accuracy.

  3. Collaborative Inference and Learning between Edge SLMs and Cloud LLMs: A Survey of Algorithms, Execution, and Open Challenges

    cs.DC 2025-07 conditional novelty 4.0 of 10

    A survey that builds a taxonomy of edge-cloud LLM-SLM collaboration for inference and training, claiming to be the first to unify both phases.

Pith tools