Imagen de Portada

Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Junliang, Wang, Yucheng, Chen, Yan, Ran, Yu, Zhang, Ruiqing, Liu, Jing, Wu, Hua, Wang, Haifeng
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Reinforced Informativeness Optimization for Long-Form Retrieval-Augmented Generation
por: Wang, Yuhao, et al.
Publicado: (2025)

VeriFact: Enhancing Long-Form Factuality Evaluation with Refined Fact Extraction and Reference Facts
por: Liu, Xin, et al.
Publicado: (2025)

MAD-Fact: A Multi-Agent Debate Framework for Long-Form Factuality Evaluation in LLMs
por: Ning, Yucheng, et al.
Publicado: (2025)

FactAlign: Long-form Factuality Alignment of Large Language Models
por: Huang, Chao-Wei, et al.
Publicado: (2024)

Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation
por: Ren, Ruiyang, et al.
Publicado: (2023)

Unveiling Knowledge Utilization Mechanisms in LLM-based Retrieval-Augmented Generation
por: Wang, Yuhao, et al.
Publicado: (2025)

InFact: Informativeness Alignment for Improved LLM Factuality
por: Cohen, Roi, et al.
Publicado: (2025)

FactReasoner: A Probabilistic Approach to Long-Form Factuality Assessment for Large Language Models
por: Marinescu, Radu, et al.
Publicado: (2025)

Merging Facts, Crafting Fallacies: Evaluating the Contradictory Nature of Aggregated Factual Claims in Long-Form Generations
por: Chiang, Cheng-Han, et al.
Publicado: (2024)

FactNet: A Billion-Scale Knowledge Graph for Multilingual Factual Grounding
por: Shen, Yingli, et al.
Publicado: (2026)

FactCorrector: A Graph-Inspired Approach to Long-Form Factuality Correction of Large Language Models
por: Carnerero-Cano, Javier, et al.
Publicado: (2026)

Think Through Uncertainty: Improving Long-Form Generation Factuality via Reasoning Calibration
por: Liu, Xin, et al.
Publicado: (2026)

Long-Form Information Alignment Evaluation Beyond Atomic Facts
por: Zheng, Danna, et al.
Publicado: (2025)

On the Entity-Level Alignment in Crosslingual Consistency
por: Liu, Yihong, et al.
Publicado: (2025)

The Curious Case of Factual (Mis)Alignment between LLMs' Short- and Long-Form Answers
por: Islam, Saad Obaid ul, et al.
Publicado: (2025)

FAITH: Factuality Alignment through Integrating Trustworthiness and Honestness
por: Dong, Xiaoning, et al.
Publicado: (2026)

Curiosity-Driven Reinforcement Learning from Human Feedback
por: Sun, Haoran, et al.
Publicado: (2025)

LEAF: Learning and Evaluation Augmented by Fact-Checking to Improve Factualness in Large Language Models
por: Tran, Hieu, et al.
Publicado: (2024)

Safety Alignment via Constrained Knowledge Unlearning
por: Shi, Zesheng, et al.
Publicado: (2025)

CLR-Fact: Evaluating the Complex Logical Reasoning Capability of Large Language Models over Factual Knowledge
por: Zheng, Tianshi, et al.
Publicado: (2024)

BEE-RAG: Balanced Entropy Engineering for Retrieval-Augmented Generation
por: Wang, Yuhao, et al.
Publicado: (2025)

Only Say What You Know: Calibration-Aware Generation for Long-Form Factuality
por: Luo, Wen, et al.
Publicado: (2026)

How Does Response Length Affect Long-Form Factuality
por: Zhao, James Xu, et al.
Publicado: (2025)

OpenFactCheck: Building, Benchmarking Customized Fact-Checking Systems and Evaluating the Factuality of Claims and LLMs
por: Wang, Yuxia, et al.
Publicado: (2024)

UniArk: Improving Generalisation and Consistency for Factual Knowledge Extraction through Debiasing
por: Yang, Yijun, et al.
Publicado: (2024)

Atomic Consistency Preference Optimization for Long-Form Question Answering
por: Chen, Jingfeng, et al.
Publicado: (2025)

FACTORY: A Challenging Human-Verified Prompt Set for Long-Form Factuality
por: Chen, Mingda, et al.
Publicado: (2025)

KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality
por: Ren, Baochang, et al.
Publicado: (2025)

Evaluating the Factuality of Large Language Models using Large-Scale Knowledge Graphs
por: Liu, Xiaoze, et al.
Publicado: (2024)

MAVEN-Fact: A Large-scale Event Factuality Detection Dataset
por: Li, Chunyang, et al.
Publicado: (2024)

Knowledgeable In-Context Tuning: Exploring and Exploiting Factual Knowledge for In-Context Learning
por: Wang, Jianing, et al.
Publicado: (2023)

GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment
por: Lv, Minxuan, et al.
Publicado: (2026)

FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation
por: Bayat, Farima Fatahi, et al.
Publicado: (2024)

Exploring the Factual Consistency in Dialogue Comprehension of Large Language Models
por: She, Shuaijie, et al.
Publicado: (2023)

UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models
por: Xue, Boyang, et al.
Publicado: (2024)

Retrieval Head Mechanistically Explains Long-Context Factuality
por: Wu, Wenhao, et al.
Publicado: (2024)

DnDScore: Decontextualization and Decomposition for Factuality Verification in Long-Form Text Generation
por: Wanner, Miriam, et al.
Publicado: (2024)

Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations
por: Luo, Haozheng, et al.
Publicado: (2026)

Improving Factual Consistency of News Summarization by Contrastive Preference Optimization
por: Feng, Huawen, et al.
Publicado: (2023)

OpenFactCheck: A Unified Framework for Factuality Evaluation of LLMs
por: Iqbal, Hasan, et al.
Publicado: (2024)