Buchumschlag

Confidence-Calibrated Small-Large Language Model Collaboration for Cost-Efficient Reasoning

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Zhang, Chuang, Zhu, Zizhen, Wei, Yihao, Tian, Bing, Liu, Junyi, Wang, Henan, Wang, Xavier, Liu, Yaxiao
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Computation and Language Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Graph-based Confidence Calibration for Large Language Models
von: Li, Yukun, et al.
Veröffentlicht: (2024)

Efficient Long CoT Reasoning in Small Language Models
von: Wang, Zhaoyang, et al.
Veröffentlicht: (2025)

A Survey of Confidence Estimation and Calibration in Large Language Models
von: Geng, Jiahui, et al.
Veröffentlicht: (2023)

VL-Calibration: Decoupled Confidence Calibration for Large Vision-Language Models Reasoning
von: Xiao, Wenyi, et al.
Veröffentlicht: (2026)

Distilling Mathematical Reasoning Capabilities into Small Language Models
von: Zhu, Xunyu, et al.
Veröffentlicht: (2024)

LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models
von: Stengel-Eskin, Elias, et al.
Veröffentlicht: (2024)

Double-Calibration: Towards Reliable LLMs via Calibrating Knowledge and Reasoning Confidence
von: Lu, Yuyin, et al.
Veröffentlicht: (2026)

GraCoRe: Benchmarking Graph Comprehension and Complex Reasoning in Large Language Models
von: Yuan, Zike, et al.
Veröffentlicht: (2024)

LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?
von: Wang, Jingyuan, et al.
Veröffentlicht: (2025)

Collaborative Stance Detection via Small-Large Language Model Consistency Verification
von: Yan, Yu, et al.
Veröffentlicht: (2025)

SEAL: Steerable Reasoning Calibration of Large Language Models for Free
von: Chen, Runjin, et al.
Veröffentlicht: (2025)

The Dunning-Kruger Effect in Large Language Models: An Empirical Study of Confidence Calibration
von: Ghosh, Sudipta, et al.
Veröffentlicht: (2026)

Mind the Confidence Gap: Overconfidence, Calibration, and Distractor Effects in Large Language Models
von: Chhikara, Prateek
Veröffentlicht: (2025)

An Enhanced Prompt-Based LLM Reasoning Scheme via Knowledge Graph-Integrated Collaboration
von: Li, Yihao, et al.
Veröffentlicht: (2024)

How Confident Is the First Token? An Uncertainty-Calibrated Prompt Optimization Framework for Large Language Model Classification and Understanding
von: Chen, Wei, et al.
Veröffentlicht: (2026)

A Survey on Large Language Models for Mathematical Reasoning
von: Wang, Peng-Yuan, et al.
Veröffentlicht: (2025)

Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning
von: Cheng, Xiaoxue, et al.
Veröffentlicht: (2025)

Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models
von: Wang, Rui, et al.
Veröffentlicht: (2025)

Beyond Confidence: The Rhythms of Reasoning in Generative Models
von: Liu, Deyuan, et al.
Veröffentlicht: (2026)

Efficient Post-Training Refinement of Latent Reasoning in Large Language Models
von: Wang, Xinyuan, et al.
Veröffentlicht: (2025)

A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness
von: Wang, Fali, et al.
Veröffentlicht: (2025)

MONICA: Real-Time Monitoring and Calibration of Chain-of-Thought Sycophancy in Large Reasoning Models
von: Hu, Jingyu, et al.
Veröffentlicht: (2025)

InfiR : Crafting Effective Small Language Models and Multimodal Small Language Models in Reasoning
von: Xie, Congkai, et al.
Veröffentlicht: (2025)

Structured Chemistry Reasoning with Large Language Models
von: Ouyang, Siru, et al.
Veröffentlicht: (2023)

CARE-RFT: Confidence-Anchored Reinforcement Finetuning for Reliable Reasoning in Large Language Models
von: Li, Shuozhe, et al.
Veröffentlicht: (2026)

Rewarding Doubt: A Reinforcement Learning Approach to Calibrated Confidence Expression of Large Language Models
von: Bani-Harouni, David, et al.
Veröffentlicht: (2025)

Mitigating Overthinking in Large Reasoning Language Models via Reasoning Path Deviation Monitoring
von: Guan, Weixin, et al.
Veröffentlicht: (2026)

Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning Models
von: Li, Junyi, et al.
Veröffentlicht: (2025)

Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate
von: Xiong, Kai, et al.
Veröffentlicht: (2023)

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning
von: Zhu, Rongzhi, et al.
Veröffentlicht: (2025)

TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Models
von: Chu, Zheng, et al.
Veröffentlicht: (2023)

Don't Think Twice! Over-Reasoning Impairs Confidence Calibration
von: Lacombe, Romain, et al.
Veröffentlicht: (2025)

Calibrating Verbalized Confidence with Self-Generated Distractors
von: Wang, Victor, et al.
Veröffentlicht: (2025)

SmartThinker: Progressive Chain-of-Thought Length Calibration for Efficient Large Language Model Reasoning
von: Hu, Chenzhi, et al.
Veröffentlicht: (2026)

Self-Anchoring Calibration Drift in Large Language Models: How Multi-Turn Conversations Reshape Model Confidence
von: Harshavardhan
Veröffentlicht: (2026)

The Role of Model Confidence on Bias Effects in Measured Uncertainties for Vision-Language Models
von: Liu, Xinyi, et al.
Veröffentlicht: (2025)

Cost-efficient Knowledge-based Question Answering with Large Language Models
von: Dong, Junnan, et al.
Veröffentlicht: (2024)

DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language Models
von: Zhu, Yakun, et al.
Veröffentlicht: (2025)

Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals
von: Torrielli, Federico, et al.
Veröffentlicht: (2026)

Towards Collaborative Intelligence: Propagating Intentions and Reasoning for Multi-Agent Coordination with Large Language Models
von: Qiu, Xihe, et al.
Veröffentlicht: (2024)