Cover Image

Confidence-Guided Stepwise Model Routing for Cost-Efficient Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lee, Sangmook, Kim, Dohyung, Koh, Hyukhun, Yang, Nakyeong, Jung, Kyomin
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Conditional [MASK] Discrete Diffusion Language Model
by: Koh, Hyukhun, et al.
Published: (2024)

Can LLMs Recognize Toxicity? A Structured Investigation Framework and Toxicity Metric
by: Koh, Hyukhun, et al.
Published: (2024)

Fine-grained Gender Control in Machine Translation with Large Language Models
by: Lee, Minwoo, et al.
Published: (2024)

Persona is a Double-edged Sword: Mitigating the Negative Impact of Role-playing Prompts in Zero-shot Reasoning Tasks
by: Kim, Junseok, et al.
Published: (2024)

Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic Encoding
by: Joo, Seongho, et al.
Published: (2025)

Public Data Assisted Differentially Private In-Context Learning
by: Joo, Seongho, et al.
Published: (2025)

Casual as an Anchor: Resolving Supervision Misalignment in Formality Transfer Dataset
by: Yu, Hyojeong, et al.
Published: (2026)

Reliability-Aware Adaptive Self-Consistency for Efficient Sampling in LLM Reasoning
by: Kim, Junseok, et al.
Published: (2026)

Persona Switch: Mixing Distinct Perspectives in Decoding Time
by: Kim, Junseok, et al.
Published: (2026)

ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection
by: Kim, Jeonghye, et al.
Published: (2025)

Avoidance Decoding for Diverse Multi-Branch Story Generation
by: Park, Kyeongman, et al.
Published: (2025)

LongStory: Coherent, Complete and Length Controlled Long story Generation
by: Park, Kyeongman, et al.
Published: (2023)

VLind-Bench: Measuring Language Priors in Large Vision-Language Models
by: Lee, Kang-il, et al.
Published: (2024)

Unplug and Play Language Models: Decomposing Experts in Language Models at Inference Time
by: Yang, Nakyeong, et al.
Published: (2024)

FaithUn: Toward Faithful Forgetting in Language Models by Investigating the Interconnectedness of Knowledge
by: Yang, Nakyeong, et al.
Published: (2025)

Program Synthesis via Test-Time Transduction
by: Lee, Kang-il, et al.
Published: (2025)

Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination
by: Yang, Nakyeong, et al.
Published: (2023)

Rethinking Stepwise Model Routing: A Cost-Efficient Table Reasoning Perspective
by: Ye, Shenghao, et al.
Published: (2026)

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
by: Kim, Jeonghye, et al.
Published: (2026)

MVMR: A New Framework for Evaluating Faithfulness of Video Moment Retrieval against Multiple Distractors
by: Yang, Nakyeong, et al.
Published: (2023)

How Training Data Shapes the Use of Parametric and In-Context Knowledge in Language Models
by: Kim, Minsung, et al.
Published: (2025)

Rethinking Post-Unlearning Behavior of Large Vision-Language Models
by: Kim, Minsung, et al.
Published: (2025)

Rubric-Guided Process Reward for Stepwise Model Routing
by: Ye, Shenghao, et al.
Published: (2026)

Generating Diverse Hypotheses for Inductive Reasoning
by: Lee, Kang-il, et al.
Published: (2024)

Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding
by: Min, Kyungmin, et al.
Published: (2024)

A Character-Centric Creative Story Generation via Imagination
by: Park, Kyeongman, et al.
Published: (2024)

AdvisorQA: Towards Helpful and Harmless Advice-seeking Question Answering with Collective Intelligence
by: Kim, Minbeom, et al.
Published: (2024)

RouteGoT: Node-Adaptive Routing for Cost-Efficient Graph of Thoughts Reasoning
by: Liu, Yuhang, et al.
Published: (2026)

Confidence-Calibrated Small-Large Language Model Collaboration for Cost-Efficient Reasoning
by: Zhang, Chuang, et al.
Published: (2026)

Guaranteed Generation from Large Language Models
by: Kim, Minbeom, et al.
Published: (2024)

Reasoning Models Better Express Their Confidence
by: Yoon, Dongkeun, et al.
Published: (2025)

Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models
by: Cui, Yingqian, et al.
Published: (2025)

BAPO: Base-Anchored Preference Optimization for Overcoming Forgetting in Large Language Models Personalization
by: Lee, Gihun, et al.
Published: (2024)

Can You Trick the Grader? Adversarial Persuasion of LLM Judges
by: Hwang, Yerin, et al.
Published: (2025)

Are LLM-Judges Robust to Expressions of Uncertainty? Investigating the effect of Epistemic Markers on LLM-based Evaluation
by: Lee, Dongryeol, et al.
Published: (2024)

Stepwise Informativeness Search for Efficient and Effective LLM Reasoning
by: Wang, Siyuan, et al.
Published: (2025)

LifeTox: Unveiling Implicit Toxicity in Life Advice
by: Kim, Minbeom, et al.
Published: (2023)

Policy-Guided Stepwise Model Routing for Cost-Effective Reasoning
by: Si, Wenwen, et al.
Published: (2026)

Return of EM: Entity-driven Answer Set Expansion for QA Evaluation
by: Lee, Dongryeol, et al.
Published: (2024)

Drift: Decoding-time Personalized Alignments with Implicit User Preferences
by: Kim, Minbeom, et al.
Published: (2025)