Copertina

Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Xinglin, Li, Yiwei, Feng, Shaoxiong, Yuan, Peiwen, Pan, Boyuan, Wang, Heda, Hu, Yao, 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

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

Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning
di: Li, Yiwei, et al.
Pubblicazione: (2024)

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

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

Generative Dense Retrieval: Memory Can Be a Burden
di: Yuan, Peiwen, 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)

Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning
di: Wang, Xinglin, 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)

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

UniCBE: An Uniformity-driven Comparing Based Evaluation Framework with Unified Multi-Objective Optimization
di: Yuan, Peiwen, 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)

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

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

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

Take its Essence, Discard its Dross! Debiasing for Toxic Language Detection via Counterfactual Causal Effect
di: Lu, Junyu, et al.
Pubblicazione: (2024)

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

Self‐Consistent Cation–Anion Integration Eliminates Passivation Crosstalk for Inverted Perovskite Solar Cells
di: Zhen Guan, et al.
Pubblicazione: (2025)

Self‐Consistent Cation–Anion Integration Eliminates Passivation Crosstalk for Inverted Perovskite Solar Cells
di: Zhen Guan, et al.
Pubblicazione: (2025)

CharaConsist: Fine-Grained Consistent Character Generation
di: Wang, Mengyu, et al.
Pubblicazione: (2025)

Ha hablado Dross. Rutinas y rituales de un grupo de fans peruanos del youtuber DrossRotzank
di: Diana Félix
Pubblicazione: (2019)

UniRefiner: Teaching Pre-trained ViTs to Self-Dispose Dross via Contrastive Register
di: Qiu, Congpei, et al.
Pubblicazione: (2026)

Efficient MoE Inference with Fine-Grained Scheduling of Disaggregated Expert Parallelism
di: Pan, Xinglin, et al.
Pubblicazione: (2025)

The Essence of Balance for Self-Improving Agents in Vision-and-Language Navigation
di: Liu, Zhen, et al.
Pubblicazione: (2026)

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)

Sample Transform Cost-Based Training-Free Hallucination Detector for Large Language Models
di: Ding, Zeyang, et al.
Pubblicazione: (2026)

HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router
di: Mei, Lingrui, et al.
Pubblicazione: (2024)

Self-NPO: Data-Free Diffusion Model Enhancement via Truncated Diffusion Fine-Tuning
di: Wang, Fu-Yun, et al.
Pubblicazione: (2025)

Parameter-Free Fine-tuning via Redundancy Elimination for Vision Foundation Models
di: Long, Jiahuan, et al.
Pubblicazione: (2025)

Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models
di: Bi, Baolong, et al.
Pubblicazione: (2025)

FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models
di: Weng, Zixuan, et al.
Pubblicazione: (2026)