Copertina

Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Yiwei, Yuan, Peiwen, Feng, Shaoxiong, Pan, Boyuan, Wang, Xinglin, Sun, Bin, Wang, Heda, Li, Kan
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation
di: Wang, Xinglin, et al.
Pubblicazione: (2024)

Poor-Supervised Evaluation for SuperLLM via Mutual Consistency
di: Yuan, Peiwen, et al.
Pubblicazione: (2024)

BatchEval: Towards Human-like Text Evaluation
di: Yuan, Peiwen, et al.
Pubblicazione: (2023)

Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning
di: Wang, Xinglin, et al.
Pubblicazione: (2024)

Generative Dense Retrieval: Memory Can Be a Burden
di: Yuan, Peiwen, et al.
Pubblicazione: (2024)

CogLM: Tracking Cognitive Development of Large Language Models
di: Wang, Xinglin, et al.
Pubblicazione: (2024)

Instruction Embedding: Latent Representations of Instructions Towards Task Identification
di: Li, Yiwei, et al.
Pubblicazione: (2024)

Focused Large Language Models are Stable Many-Shot Learners
di: Yuan, Peiwen, et al.
Pubblicazione: (2024)

Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation
di: Li, Yiwei, et al.
Pubblicazione: (2025)

Silencer: From Discovery to Mitigation of Self-Bias in LLM-as-Benchmark-Generator
di: Yuan, Peiwen, et al.
Pubblicazione: (2025)

UniCBE: An Uniformity-driven Comparing Based Evaluation Framework with Unified Multi-Objective Optimization
di: Yuan, Peiwen, et al.
Pubblicazione: (2025)

Diagnosing and Mitigating System Bias in Self-Rewarding RL
di: Tan, Chuyi, et al.
Pubblicazione: (2025)

Speculative Decoding for Multi-Sample Inference
di: Li, Yiwei, et al.
Pubblicazione: (2025)

Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation
di: Yuan, Peiwen, et al.
Pubblicazione: (2025)

Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time Scaling
di: Wang, Xinglin, et al.
Pubblicazione: (2025)

Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules
di: Zhang, Yueqi, et al.
Pubblicazione: (2025)

From Sub-Ability Diagnosis to Human-Aligned Generation: Bridging the Gap for Text Length Control via MARKERGEN
di: Yuan, Peiwen, et al.
Pubblicazione: (2025)

LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient
di: Yuan, Peiwen, et al.
Pubblicazione: (2025)

InsBank: Evolving Instruction Subset for Ongoing Alignment
di: Shi, Jiayi, et al.
Pubblicazione: (2025)

PatternKV: Flattening KV Representation Expands Quantization Headroom
di: Zhang, Ji, et al.
Pubblicazione: (2025)

Do Not Waste Your Rollouts: Recycling Search Experience for Efficient Test-Time Scaling
di: Wang, Xinglin, et al.
Pubblicazione: (2026)

On Time, Within Budget: Constraint-Driven Online Resource Allocation for Agentic Workflows
di: Wang, Xinglin, et al.
Pubblicazione: (2026)

Learning More from Less: Unlocking Internal Representations for Benchmark Compression
di: Zhang, Yueqi, et al.
Pubblicazione: (2026)

Dynamic Stochastic Decoding Strategy for Open-Domain Dialogue Generation
di: Li, Yiwei, et al.
Pubblicazione: (2024)

Assessment of the Relationship Between Music Students' Self‐Efficacy, Academic Performance and Their Artificial Intelligence Readiness
di: Xinzheng Wang, et al.
Pubblicazione: (2024)

Stitch and Tell: A Structured Multimodal Data Augmentation Method for Spatial Understanding
di: Yin, Hang, et al.
Pubblicazione: (2025)

MRFD: Multi-Region Fusion Decoding with Self-Consistency for Mitigating Hallucinations in LVLMs
di: Ge, Haonan, et al.
Pubblicazione: (2025)

Early-stopping for Transformer model training
di: He, Jing, et al.
Pubblicazione: (2025)

Bridging Internal Probability and Self-Consistency for Effective and Efficient LLM Reasoning
di: Zhou, Zhi, et al.
Pubblicazione: (2025)

ParZC: Parametric Zero-Cost Proxies for Efficient NAS
di: Dong, Peijie, et al.
Pubblicazione: (2024)

A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning
di: Zhou, Zhi, et al.
Pubblicazione: (2025)

Favourable Outcomes, Challenges and Discipline‐Specific Implications of Teacher Scaffolding in Chinese University Music Classes: A Qualitative Study
di: Peiwen Li, et al.
Pubblicazione: (2026)

Test-Time Scaling of Reasoning Models for Machine Translation
di: Li, Zihao, et al.
Pubblicazione: (2025)

Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency
di: Liu, Junming, et al.
Pubblicazione: (2026)

ConsistencyDet: A Few-step Denoising Framework for Object Detection Using the Consistency Model
di: Jiang, Lifan, et al.
Pubblicazione: (2024)

Viscometric investigations and molecular interactions of some derivatives of 5-substituted indole dihydropyrimidines in mixed organic solvents
di: L. C. Heda
Pubblicazione: (2010)

Music Education With GenAI : Exploring the Mediating Roles of Enjoyment Between Smart Service Interactional Experience and Behavioural Intention
di: Peiwen Li
Pubblicazione: (2025)

EscapeCraft: A 3D Room Escape Environment for Benchmarking Complex Multimodal Reasoning Ability
di: Wang, Ziyue, et al.
Pubblicazione: (2025)

The Neural-Wave Quick Escape Manual 2036: A Field Guide to Adversarial Living in the Era of "Empathic" AIoT
di: Gu, Boyuan, et al.
Pubblicazione: (2026)

Beyond Correctness: Exposing LLM-generated Logical Flaws in Reasoning via Multi-step Automated Theorem Proving
di: Zheng, Xinyi, et al.
Pubblicazione: (2025)