Imagen de Portada

ConfSpec: Efficient Step-Level Speculative Reasoning via Confidence-Gated Verification

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Siran, He, Cyril Y.
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
por: Yang, Penghui, et al.
Publicado: (2025)

SpecExit: Accelerating Large Reasoning Model via Speculative Exit
por: Yang, Rubing, et al.
Publicado: (2025)

SpecBound: Adaptive Bounded Self-Speculation with Layer-wise Confidence Calibration
por: Wen, Zhuofan, et al.
Publicado: (2026)

ConfTuner: Training Large Language Models to Express Their Confidence Verbally
por: Li, Yibo, et al.
Publicado: (2025)

BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents
por: Ou, Litu, et al.
Publicado: (2025)

ML-SpecQD: Multi-Level Speculative Decoding with Quantized Drafts
por: Georganas, Evangelos, et al.
Publicado: (2025)

HeteroSpec: Leveraging Contextual Heterogeneity for Efficient Speculative Decoding
por: Liu, Siran, et al.
Publicado: (2025)

DistillSpec: Improving Speculative Decoding via Knowledge Distillation
por: Zhou, Yongchao, et al.
Publicado: (2023)

DiffuSpec: Unlocking Diffusion Language Models for Speculative Decoding
por: Li, Guanghao, et al.
Publicado: (2025)

SpecHub: Provable Acceleration to Multi-Draft Speculative Decoding
por: Sun, Ryan, et al.
Publicado: (2024)

EvoSpec: Evolving Speculative Decoding via Real-Time Vocabulary and Parameter Adaptation
por: Zhang, Shuyu, et al.
Publicado: (2026)

HiSpec: Hierarchical Speculative Decoding for LLMs
por: Kumar, Avinash, et al.
Publicado: (2025)

SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths
por: Huang, Kaixuan, et al.
Publicado: (2024)

AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence
por: Liu, Yuliang, et al.
Publicado: (2025)

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization
por: Yoon, Hee Suk, et al.
Publicado: (2025)

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control
por: He, Xingyang, et al.
Publicado: (2025)

SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding
por: Li, Shenggui, et al.
Publicado: (2026)

Step-by-Step Fact Verification System for Medical Claims with Explainable Reasoning
por: Vladika, Juraj, et al.
Publicado: (2025)

ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning
por: Qiao, Ziqing, et al.
Publicado: (2025)

FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling
por: Zhao, Weilin, et al.
Publicado: (2025)

Arbitrage: Efficient Reasoning via Advantage-Aware Speculation
por: Maheswaran, Monishwaran, et al.
Publicado: (2025)

Reward-Guided Speculative Decoding for Efficient LLM Reasoning
por: Liao, Baohao, et al.
Publicado: (2025)

CAMEL: Confidence-Gated Reflection for Reward Modeling
por: Zhu, Zirui, et al.
Publicado: (2026)

SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification
por: Yoon, Kanghoon, et al.
Publicado: (2025)

Traversal Verification for Speculative Tree Decoding
por: Weng, Yepeng, et al.
Publicado: (2025)

Verbalized Confidence Triggers Self-Verification: Emergent Behavior Without Explicit Reasoning Supervision
por: Jang, Chaeyun, et al.
Publicado: (2025)

SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning
por: Ji, Yicheng, et al.
Publicado: (2025)

Entropy-Aware Speculative Decoding Toward Improved LLM Reasoning
por: Su, Tiancheng, et al.
Publicado: (2025)

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

Hybrid Verified Decoding: Learning to Allocate Verification in Speculative Decoding
por: Su, Xin, et al.
Publicado: (2026)

Accelerating Large Language Model Reasoning via Speculative Search
por: Wang, Zhihai, et al.
Publicado: (2025)

DynaSpec: Context-aware Dynamic Speculative Sampling for Large-Vocabulary Language Models
por: Zhang, Jinbin, et al.
Publicado: (2025)

Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation
por: Zhang, Ziyin, et al.
Publicado: (2024)

Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification
por: Liu, Chengwu, et al.
Publicado: (2025)

ChestX-Reasoner: Advancing Radiology Foundation Models with Reasoning through Step-by-Step Verification
por: Fan, Ziqing, et al.
Publicado: (2025)

Confidence-Modulated Speculative Decoding for Large Language Models
por: Sen, Jaydip, et al.
Publicado: (2025)

Entropy-Gated Branching for Efficient Test-Time Reasoning
por: Li, Xianzhi, et al.
Publicado: (2025)

ConMax: Confidence-Maximizing Compression for Efficient Chain-of-Thought Reasoning
por: Hu, Minda, et al.
Publicado: (2026)

Where Does Reasoning Break? Step-Level Hallucination Detection via Hidden-State Transport Geometry
por: Alvarez, Tyler, et al.
Publicado: (2026)

Geo-Expert: Towards Expert-Level Geological Reasoning via Parameter-Efficient Fine-Tuning
por: Guo, Chenyou, et al.
Publicado: (2026)