Imagen de Portada

Hit the Sweet Spot! Span-Level Ensemble for Large Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xu, Yangyifan, Chen, Jianghao, Wu, Junhong, Zhang, Jiajun
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

LADM: Long-context Training Data Selection with Attention-based Dependency Measurement for LLMs
por: Chen, Jianghao, et al.
Publicado: (2025)

Bridging the Gap between Different Vocabularies for LLM Ensemble
por: Xu, Yangyifan, et al.
Publicado: (2024)

Diver: Large Language Model Decoding with Span-Level Mutual Information Verification
por: Lu, Jinliang, et al.
Publicado: (2024)

Boosting LLM Translation Skills without General Ability Loss via Rationale Distillation
por: Wu, Junhong, et al.
Publicado: (2024)

LR^2Bench: Evaluating Long-chain Reflective Reasoning Capabilities of Large Language Models via Constraint Satisfaction Problems
por: Chen, Jianghao, et al.
Publicado: (2025)

SSL: Sweet Spot Learning for Differentiated Guidance in Agentic Optimization
por: Wu, Jinyang, et al.
Publicado: (2026)

BLSP-Emo: Towards Empathetic Large Speech-Language Models
por: Wang, Chen, et al.
Publicado: (2024)

Can LLMs Think Like Consumers? Benchmarking Crowd-Level Reaction Reconstruction with ConsumerSimBench
por: Wang, Tianyu, et al.
Publicado: (2026)

Finding the Sweet Spot: Preference Data Construction for Scaling Preference Optimization
por: Xiao, Yao, et al.
Publicado: (2025)

Language Imbalance Driven Rewarding for Multilingual Self-improving
por: Yang, Wen, et al.
Publicado: (2024)

Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models
por: Jian, Pu, et al.
Publicado: (2025)

DOCE: Finding the Sweet Spot for Execution-Based Code Generation
por: Li, Haau-Sing, et al.
Publicado: (2024)

Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models
por: Lu, Jinliang, et al.
Publicado: (2024)

Strategies for Span Labeling with Large Language Models
por: Semin, Danil, et al.
Publicado: (2026)

Spotting AI's Touch: Identifying LLM-Paraphrased Spans in Text
por: Li, Yafu, et al.
Publicado: (2024)

Temporal Blind Spots in Large Language Models
por: Wallat, Jonas, et al.
Publicado: (2024)

ELPO: Ensemble Learning Based Prompt Optimization for Large Language Models
por: Zhang, Qing, et al.
Publicado: (2025)

Rethinking Personalization in Large Language Models at the Token Level
por: Zhang, Chenheng, et al.
Publicado: (2026)

Architectural Sweet Spots for Modeling Human Label Variation by the Example of Argument Quality: It's Best to Relate Perspectives!
por: Heinisch, Philipp, et al.
Publicado: (2023)

SRA: Span Representation Alignment for Large Language Model Distillation
por: Dao, Quoc Phong, et al.
Publicado: (2026)

Self-Selected Attention Span for Accelerating Large Language Model Inference
por: Jin, Tian, et al.
Publicado: (2024)

ACE-RL: Adaptive Constraint-Enhanced Reward for Long-form Generation Reinforcement Learning
por: Chen, Jianghao, et al.
Publicado: (2025)

PERL: Pinyin Enhanced Rephrasing Language Model for Chinese ASR N-best Error Correction
por: Liang, Junhong, et al.
Publicado: (2024)

Vision Language Models Are Not (Yet) Spelling Correctors
por: Liang, Junhong, et al.
Publicado: (2025)

Span Modeling for Idiomaticity and Figurative Language Detection with Span Contrastive Loss
por: Matheny, Blake, et al.
Publicado: (2026)

Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment
por: Yang, Wen, et al.
Publicado: (2025)

Ensemble Watermarks for Large Language Models
por: Niess, Georg, et al.
Publicado: (2024)

Knowledge Editing for Large Language Model with Knowledge Neuronal Ensemble
por: Li, Yongchang, et al.
Publicado: (2024)

Enhancing Knowledge Distillation of Large Language Models through Efficient Multi-Modal Distribution Alignment
por: Peng, Tianyu, et al.
Publicado: (2024)

Large Language Models Make Sample-Efficient Recommender Systems
por: Lin, Jianghao, et al.
Publicado: (2024)

Blind Spot Navigation in Large Language Model Reasoning with Thought Space Explorer
por: Zhang, Jinghan, et al.
Publicado: (2024)

An Analysis of Language Frequency and Error Correction for Esperanto
por: Liang, Junhong
Publicado: (2024)

ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Models
por: Lin, Zihan, et al.
Publicado: (2025)

Collection Development: Hitting the Sweet Spot (Baking)
por: Charles, John
Publicado: (2010)

Lost in the Source Language: How Large Language Models Evaluate the Quality of Machine Translation
por: Huang, Xu, et al.
Publicado: (2024)

Chinese-SkillSpan: A Span-Level Dataset for ESCO-Aligned Competency Extraction from Chinese Job Ads
por: Li, Guojing, et al.
Publicado: (2026)

Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model Ensembling
por: Yao, Yuxuan, et al.
Publicado: (2024)

DPPA: Pruning Method for Large Language Model to Model Merging
por: Zhu, Yaochen, et al.
Publicado: (2024)

Linguistic Blind Spots of Large Language Models
por: Cheng, Jiali, et al.
Publicado: (2025)

Exploring the Performance of Large Language Models on Subjective Span Identification Tasks
por: Dmonte, Alphaeus, et al.
Publicado: (2026)