Paper Citation Record · LEDGER

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

As of 19 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 9 inbound Pith citation observations for arXiv:2502.04428.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2502.04428 v1

Coverage vector

measured 51 of 51 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T22:49:51.844173Z

measured 60 of 60 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 9 of 9 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:57:00.320706Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

51 of 51 outbound references displayed

verified exact0
verified fuzzy12
unresolved39
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation d2a2bc24-c1a4-4b2c-9210-0a443b2e4473 · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.685048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 159af495-20ff-4067-92e5-a1fda59f0590 · outbound

This paper cites FF: Free-form question answering (including numerical answers for math tasks); MCQ: Multiple-choice question answering; TF: True/False question answering.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization FF: Free-form question answering (including numerical answers for math tasks); MCQ: Multiple-choice question answering; TF: True/False question answering

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:49:52.203211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4d0e325b-6477-4720-99fb-84d08ef23c15 · outbound

This paper cites and Mitchell, T.

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

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:49:52.339567Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3eb0df70-9763-4952-b827-2fb58d1ae35f · outbound

This paper cites MobileVLM V2: Faster and Stronger Baseline for Vision Language Model.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization MobileVLM V2: Faster and Stronger Baseline for Vision Language Model

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.705123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e187f49-85f0-4922-98d3-38f5a1187581 · outbound

This paper cites Learning to Route LLMs with Confidence Tokens.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Learning to Route LLMs with Confidence Tokens

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.708344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc6aa7aa-5e90-4843-88ea-46b0d11438d0 · outbound

This paper cites Boolq: Exploring the surprising difficulty of natural yes/no questions.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Boolq: Exploring the surprising difficulty of natural yes/no questions

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:49:52.331472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a198a7e6-51a1-4f31-bdbc-0d9414650b8c · outbound

This paper cites Multicalibration for Confidence Scoring in LLMs.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Multicalibration for Confidence Scoring in LLMs

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.721795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cad77890-a070-4ae5-a4e8-d3266f39f776 · outbound

This paper cites A survey on in- context learning.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization A survey on in- context learning

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:49:52.323112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c2897377-745b-45d4-8103-cd1653a7f600 · outbound

This paper cites The Llama 3 Herd of Models.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization The Llama 3 Herd of Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.729047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58967096-10cd-4262-88ce-18dce25411fd · outbound

This paper cites Lm-polygraph: Uncer- tainty estimation for language models.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Lm-polygraph: Uncer- tainty estimation for language models

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:49:52.313590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e2892b9b-cbfb-40a7-9cdf-aa8c7740a2d3 · outbound

This paper cites RouterBench: A Benchmark for Multi-LLM Routing System.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization RouterBench: A Benchmark for Multi-LLM Routing System

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.737894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c9985b1-0ac7-42d2-844b-922eff5d1786 · outbound

This paper cites Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Models.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.741605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66d44b64-e23e-4be6-b590-342b06263088 · outbound

This paper cites GPT-4o System Card.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization GPT-4o System Card

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.745213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbfdd575-6a44-4240-bf50-d2e37c3ef7cb · outbound

This paper cites Mixtral of Experts.

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

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.748563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9321a90-20f2-446e-bc06-434f17606ab9 · outbound

This paper cites Language Models (Mostly) Know What They Know.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Language Models (Mostly) Know What They Know

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.751528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0e2ab73-70ba-446f-a1be-035a60e79861 · outbound

This paper cites Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.755030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd64bf2e-8f9f-474f-bb9d-7d4199e673fc · outbound

This paper cites TruthfulQA: Measuring How Models Mimic Human Falsehoods.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization TruthfulQA: Measuring How Models Mimic Human Falsehoods

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.757706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1189059-4a03-498c-a570-017b44682832 · outbound

This paper cites Teaching Models to Express Their Uncertainty in Words.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Teaching Models to Express Their Uncertainty in Words

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.760366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b253e4b8-bf55-428d-96bf-d7e265570232 · outbound

This paper cites Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.763242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f90f238-7bbe-463b-9304-c76eb7148589 · outbound

This paper cites Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.769405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c318a8ca-cc00-4450-b448-de7e3cfae4ce · outbound

This paper cites Selfcheckgpt: Zero- resource black-box hallucination detection for genera- tive large language models.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Selfcheckgpt: Zero- resource black-box hallucination detection for genera- tive large language models

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:49:52.295701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation bdcbd77c-fc68-4b4e-a573-adfa71abcc53 · outbound

This paper cites Llama 3.2: Revolutionizing edge ai and vision with open, customizable models.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Llama 3.2: Revolutionizing edge ai and vision with open, customizable models

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:49:52.284402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e00f3d42-fc83-4f39-b1ab-76de36c74747 · outbound

This paper cites Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.777778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37b624ca-6a68-4237-8132-cfcafa82d03f · outbound

This paper cites OLMoE: Open Mixture-of-Experts Language Models.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization OLMoE: Open Mixture-of-Experts Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.780442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df72b521-bb48-4f07-8299-4d723edcfa79 · outbound

This paper cites an unresolved cited work.

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

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-08T22:49:52.272584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1e0da4b9-a75f-4a6d-b8f9-6c4467fb7e6f · outbound

This paper cites RWKV: Reinventing RNNs for the Transformer Era.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization RWKV: Reinventing RNNs for the Transformer Era

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.785535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 471afd14-88eb-4719-b4ba-73a98c730532 · outbound

This paper cites H2O-Danube3 Technical Report.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization H2O-Danube3 Technical Report

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.788735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d482f99d-af9e-486a-bf39-18db2a1daa15 · outbound

This paper cites Solving General Arithmetic Word Problems.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Solving General Arithmetic Word Problems

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.791988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01ceda28-21f7-4eaf-985e-c1443065f06b · outbound

This paper cites Social iqa: Commonsense reasoning about social interactions.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Social iqa: Commonsense reasoning about social interactions

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:49:52.261153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6bd6de6c-f446-4a20-876a-8e2dfb717e85 · outbound

This paper cites TensorOpera Router: A Multi-Model Router for Efficient LLM Inference.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization TensorOpera Router: A Multi-Model Router for Efficient LLM Inference

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.798116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a3ad4a9-1538-454c-b9a3-99d3dd588fc2 · outbound

This paper cites Com- monsenseQA: A question answering challenge targeting commonsense knowledge.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Com- monsenseQA: A question answering challenge targeting commonsense knowledge

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:49:52.249179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b98b9a32-93a5-4424-9d08-3263171c10c5 · outbound

This paper cites an unresolved cited work.

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

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-08-08T22:49:52.237635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c23fc0c9-9d5d-4eba-9085-257a2cf1b101 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization LLaMA: Open and Efficient Foundation Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.808067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f15208aa-59f6-4af0-a11b-effed09ec339 · outbound

This paper cites Efficient out-of-domain detection for sequence to sequence models.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Efficient out-of-domain detection for sequence to sequence models

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:49:52.225335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 617f0116-9939-4e88-89f1-d0a55cad236b · outbound

This paper cites P., Delucia, A., and Dredze, M.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization P., Delucia, A., and Dredze, M

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:49:52.214900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 53cf45e0-4a02-4e0b-b466-579d79a89f42 · outbound

This paper cites Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.818627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c56e0578-04c2-460e-99dd-9f52340e97b7 · outbound

This paper cites Qwen2 Technical Report.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Qwen2 Technical Report

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.821773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb0d7eee-d9d4-4b3c-9117-27a1c2e6778f · outbound

This paper cites Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words?.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words?

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.825552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4ed9843-160a-41b4-9e8e-37e63a187db6 · outbound

This paper cites TinyLlama: An Open-Source Small Language Model.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization TinyLlama: An Open-Source Small Language Model

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.829271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c62a21fb-2f1b-4edb-875b-eedfaaa0e91d · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization OPT: Open Pre-trained Transformer Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.832594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 180ffce6-3923-48b9-9311-9142254dacad · outbound

This paper cites A Survey of Large Language Models.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization A Survey of Large Language Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.835823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbd77d84-474a-4913-8b03-b6b035e119d7 · outbound

This paper cites Eagle: Efficient Training-Free Router for Multi-LLM Inference.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Eagle: Efficient Training-Free Router for Multi-LLM Inference

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.838616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be1e8f29-6557-41b4-90c0-4bf57f1e86cb · outbound

This paper cites Mini-Giants: "Small" Language Models and Open Source Win-Win.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Mini-Giants: "Small" Language Models and Open Source Win-Win

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.841392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bc13ef9-9f95-487c-934c-7b5a71f985d4 · outbound

This paper cites A survey of confidence estimation and calibration in large language models.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization A survey of confidence estimation and calibration in large language models

Reference 2016

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T22:49:52.305076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5b821494-1088-44df-8176-a17f2a9289fd · outbound

This paper cites Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.766316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3aa7bb1-8702-49cd-81fe-a2bd8370c28b · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Training Verifiers to Solve Math Word Problems

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.715003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92e0b825-6ad6-4248-8d42-71a72784f47f · outbound

This paper cites Discovering Latent Knowledge in Language Models Without Supervision.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Discovering Latent Knowledge in Language Models Without Supervision

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.698774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f942d742-5198-4b63-a132-003de8d12982 · outbound

This paper cites Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.718501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c44fd253-9c0f-434d-a3a7-eb485b754587 · outbound

This paper cites What is the Role of Small Models in the LLM Era: A Survey.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization What is the Role of Small Models in the LLM Era: A Survey

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.701759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4473d77-4f6f-4d7b-9fe7-3353c1be7c2b · outbound

This paper cites Qwen Technical Report.

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

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.695700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82580ddc-e3e9-409d-848b-517a52985a89 · outbound

This paper cites GPT-4 Technical Report.

Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization GPT-4 Technical Report

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-08T22:49:51.689459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation c37b93d1-a14e-4fe0-9281-4a6480356d16 · inbound

Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models cites this paper.

Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:00.320706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e16f40c1-1915-40bf-a9e3-ffc0c2c0c6b0 · inbound

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

Collaborative Inference and Learning between Edge SLMs and Cloud LLMs: A Survey of Algorithms, Execution, and Open Challenges Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-06T15:06:48.156908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cda870a6-3693-44f1-bec5-e9b615073d49 · inbound

A Greedy PDE Router for Blending Neural Operators and Classical Methods cites this paper.

A Greedy PDE Router for Blending Neural Operators and Classical Methods Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-18T12:32:36.204473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 905ca03c-2dfc-488e-b02c-4fae425b8b9b · inbound

Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models cites this paper.

Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T07:14:24.229128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94b7cb36-fe5c-4ff2-a420-0222f3863743 · inbound

Do Small Language Models Know When They're Wrong? Confidence-Based Cascade Scoring for Educational Assessment cites this paper.

Do Small Language Models Know When They're Wrong? Confidence-Based Cascade Scoring for Educational Assessment Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-14T21:17:58.436227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fafb6711-bb17-4ee8-9906-e6ec68d14b2c · inbound

Zero-Shot Confidence Estimation for Small LLMs: When Supervised Baselines Aren't Worth Training cites this paper.

Zero-Shot Confidence Estimation for Small LLMs: When Supervised Baselines Aren't Worth Training Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:31:07.472454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4226c244-b079-491f-81cc-eb3abf4cc3d6 · inbound

Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost cites this paper.

Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization

Reference 84

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T20:06:09.079876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 644b0a1f-8c50-48fd-9e30-98f0e604dcbd · inbound

Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning cites this paper.

Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T13:34:41.164791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 82b2bf88-ca9d-45db-8019-c8bfce3ac5fd · inbound

CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models cites this paper.

CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-07-02T13:26:58.122547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.