Imagen de Portada

ELSPR: Evaluator LLM Training Data Self-Purification on Non-Transitive Preferences via Tournament Graph Reconstruction

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yu, Yan, Liu, Yilun, He, Minggui, Tao, Shimin, Meng, Weibin, Yang, Xinhua, Zhang, Li, Ma, Hongxia, Li, Dengye, Wei, Daimeng, Chen, Boxing, Li, Fuliang
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

MIDB: Multilingual Instruction Data Booster for Enhancing Cultural Equality in Multilingual Instruction Synthesis
por: Liu, Yilun, et al.
Publicado: (2025)

M-DaQ: Retrieving Samples with Multilingual Diversity and Quality for Instruction Fine-Tuning Datasets
por: Zhao, Chunguang, et al.
Publicado: (2025)

R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning
por: He, Minggui, et al.
Publicado: (2025)

C-Mining: Unsupervised Discovery of Seeds for Cultural Data Synthesis via Geometric Misalignment
por: Zeng, Pufan, et al.
Publicado: (2026)

RationAnomaly: Log Anomaly Detection with Rationality via Chain-of-Thought and Reinforcement Learning
por: Xu, Song, et al.
Publicado: (2025)

LogLM: From Task-based to Instruction-based Automated Log Analysis
por: Liu, Yilun, et al.
Publicado: (2024)

Adapting Large Language Models to Log Analysis with Interpretable Domain Knowledge
por: Ji, Yuhe, et al.
Publicado: (2024)

R-Log: Incentivizing Log Analysis Capability in LLMs via Reasoning-based Reinforcement Learning
por: Liu, Yilun, et al.
Publicado: (2025)

Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation
por: Ge, Yuan, et al.
Publicado: (2024)

The GaoYao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Models
por: Liu, Yilun, et al.
Publicado: (2026)

Taming Text-to-Image Synthesis for Novices: User-centric Prompt Generation via Multi-turn Guidance
por: Liu, Yilun, et al.
Publicado: (2024)

Cross-Preference Learning for Sentence-Level and Context-Aware Machine Translation
por: Li, Ying, et al.
Publicado: (2026)

Improving LLM-based Document-level Machine Translation with Multi-Knowledge Fusion
por: Liu, Bin, et al.
Publicado: (2025)

Chart Specification: Structural Representations for Incentivizing VLM Reasoning in Chart-to-Code Generation
por: He, Minggui, et al.
Publicado: (2026)

A Multitask Training Approach to Enhance Whisper with Contextual Biasing and Open-Vocabulary Keyword Spotting
por: Li, Yuang, et al.
Publicado: (2023)

Two Intermediate Translations Are Better Than One: Fine-tuning LLMs for Document-level Translation Refinement
por: Dong, Yichen, et al.
Publicado: (2025)

From Handcrafted Features to LLMs: A Brief Survey for Machine Translation Quality Estimation
por: Zhao, Haofei, et al.
Publicado: (2024)

Transitivity in Inhomogeneous Random Tournaments
por: Chatterjee, Sayak, et al.
Publicado: (2026)

CultureScope: A Dimensional Lens for Probing Cultural Understanding in LLMs
por: Zhang, Jinghao, et al.
Publicado: (2025)

DeMPT: Decoding-enhanced Multi-phase Prompt Tuning for Making LLMs Be Better Context-aware Translators
por: Lyu, Xinglin, et al.
Publicado: (2024)

Interpretable Online Log Analysis Using Large Language Models with Prompt Strategies
por: Liu, Yilun, et al.
Publicado: (2023)

Learning from Response not Preference: A Stackelberg Approach for LLM Detoxification using Non-parallel Data
por: Xie, Xinhong, et al.
Publicado: (2024)

Do Large Language Models Truly Understand Cross-cultural Differences?
por: Guo, Shiwei, et al.
Publicado: (2025)

On minimal k-factor-critical planar graphs
por: Li, Qiuli, et al.
Publicado: (2025)

Non‐Hamiltonian Cycles in Tournaments
por: Ayman El Zein
Publicado: (2025)

Pairwise Imitation and Tournament Graphs
por: Sung‐Ha Hwang, et al.
Publicado: (2026)

Immersions of Directed Graphs in Tournaments
por: António Girão, et al.
Publicado: (2024)

Wheel‐Like Bricks and Minimal Matching Covered Graphs
por: Xiaoling He, et al.
Publicado: (2025)

Enhancing mechanical properties of Er 2 O 3 –Al 2 O 3 –SiO 2 glass–ceramics for advanced substrate application
por: Daimeng Chen, et al.
Publicado: (2025)

Chain--collider--fork Decompositions of Transitive Tournament
por: Gunasekara, Ajani De Vas
Publicado: (2026)

CoachLM: Automatic Instruction Revisions Improve the Data Quality in LLM Instruction Tuning
por: Liu, Yilun, et al.
Publicado: (2023)

Skating System Unveiled: Exploring Preference Aggregation in Ballroom Tournaments
por: Horn, Laryssa, et al.
Publicado: (2025)

Loong: A Human-Like Long Document Translation Agent with Observe-and-Act Adaptive Context Selection
por: Wang, Yutong, et al.
Publicado: (2026)

TSO: Self-Training with Scaled Preference Optimization
por: Chen, Kaihui, et al.
Publicado: (2024)

M-Ped: Multi-Prompt Ensemble Decoding for Large Language Models
por: Guo, Jiaxin, et al.
Publicado: (2024)

Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning
por: Wang, Tianduo, et al.
Publicado: (2024)

PsychePass: Calibrating LLM Therapeutic Competence via Trajectory-Anchored Tournaments
por: Chen, Zhuang, et al.
Publicado: (2026)

Unicron: Economizing Self-Healing LLM Training at Scale
por: He, Tao, et al.
Publicado: (2023)

Unlocking Fine-Grained Translation Quality Estimation in LRMs through Synergistically Evolving Implicit and Explicit Reasoning
por: Dang, Renfei, et al.
Publicado: (2026)

Revisiting Energy-Based Model for Out-of-Distribution Detection
por: Wu, Yifan, et al.
Publicado: (2024)