Copertina

PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the Beginning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Langming, Lv, Kangtao, Chen, Haibin, Zhang, Weidong, Wang, Yejing, Liu, Shilei, Tong, Xin, Yuan, Yujin, Wang, Yongwei, Su, Wenbo, Zheng, Bo
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

How to inject knowledge efficiently? Knowledge Infusion Scaling Law for Pre-training Large Language Models
di: Lv, Kangtao, et al.
Pubblicazione: (2025)

Data Distribution Matters: A Data-Centric Perspective on Context Compression for Large Language Model
di: Lv, Kangtao, et al.
Pubblicazione: (2026)

ChineseEcomQA: A Scalable E-commerce Concept Evaluation Benchmark for Large Language Models
di: Chen, Haibin, et al.
Pubblicazione: (2025)

ECKGBench: Benchmarking Large Language Models in E-commerce Leveraging Knowledge Graph
di: Liu, Langming, et al.
Pubblicazione: (2025)

PoC: Performance-oriented Context Compression for Large Language Models via Performance Prediction
di: Zhao, Runsong, et al.
Pubblicazione: (2026)

Expert Divergence Learning for MoE-based Language Models
di: Li, Jiaang, et al.
Pubblicazione: (2026)

CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling
di: Zhao, Runsong, et al.
Pubblicazione: (2026)

Hyper Adversarial Tuning for Boosting Adversarial Robustness of Pretrained Large Vision Models
di: Lv, Kangtao, et al.
Pubblicazione: (2024)

Read As Human: Compressing Context via Parallelizable Close Reading and Skimming
di: Tang, Jiwei, et al.
Pubblicazione: (2026)

Unlocking Scaling Law in Industrial Recommendation Systems with a Three-step Paradigm based Large User Model
di: Yan, Bencheng, et al.
Pubblicazione: (2025)

NAN: A Training-Free Solution to Coefficient Estimation in Model Merging
di: Si, Chongjie, et al.
Pubblicazione: (2025)

UQABench: Evaluating User Embedding for Prompting LLMs in Personalized Question Answering
di: Liu, Langming, et al.
Pubblicazione: (2025)

COMI: Coarse-to-fine Context Compression via Marginal Information Gain
di: Tang, Jiwei, et al.
Pubblicazione: (2026)

HyperDet: Generalizable Detection of Synthesized Images by Generating and Merging A Mixture of Hyper LoRAs
di: Cao, Huangsen, et al.
Pubblicazione: (2024)

NEZHA: A Zero-sacrifice and Hyperspeed Decoding Architecture for Generative Recommendations
di: Wang, Yejing, et al.
Pubblicazione: (2025)

Mitigating Geospatial Knowledge Hallucination in Large Language Models: Benchmarking and Dynamic Factuality Aligning
di: Wang, Shengyuan, et al.
Pubblicazione: (2025)

Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems
di: Liu, Langming, et al.
Pubblicazione: (2025)

Tracing Multilingual Factual Knowledge Acquisition in Pretraining
di: Liu, Yihong, et al.
Pubblicazione: (2025)

Analysis of regularized federated learning
di: Liu, Langming, et al.
Pubblicazione: (2024)

Hallucination Begins Where Saliency Drops
di: Zhang, Xiaofeng, et al.
Pubblicazione: (2026)

Risk-Sensitive RL for Alleviating Exploration Dilemmas in Large Language Models
di: Jiang, Yuhua, et al.
Pubblicazione: (2025)

An Improved Quantum Private Set Intersection Protocol Based on Hadamard Gates
di: Liu, Wenjie, et al.
Pubblicazione: (2023)

NoiseBoost: Alleviating Hallucination with Noise Perturbation for Multimodal Large Language Models
di: Wu, Kai, et al.
Pubblicazione: (2024)

HAVE: Head-Adaptive Gating and ValuE Calibration for Hallucination Mitigation in Large Language Models
di: Tong, Xin, et al.
Pubblicazione: (2025)

Alleviating Hallucinations of Large Language Models through Induced Hallucinations
di: Zhang, Yue, et al.
Pubblicazione: (2023)

The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models
di: Li, Junyi, et al.
Pubblicazione: (2024)

Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels
di: Cen, Zhepeng, et al.
Pubblicazione: (2025)

Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Control
di: Huang, Weidong, et al.
Pubblicazione: (2026)

Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models
di: He, Yancheng, et al.
Pubblicazione: (2024)

"See the World, Discover Knowledge": A Chinese Factuality Evaluation for Large Vision Language Models
di: Gu, Jihao, et al.
Pubblicazione: (2025)

CodeSimpleQA: Scaling Factuality in Code Large Language Models
di: Yang, Jian, et al.
Pubblicazione: (2025)

Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models
di: Huo, Fushuo, et al.
Pubblicazione: (2024)

Towards Alleviating Text-to-Image Retrieval Hallucination for CLIP in Zero-shot Learning
di: Wang, Hanyao, et al.
Pubblicazione: (2024)

Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language Models
di: Tan, Yingshui, et al.
Pubblicazione: (2024)

Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced Optimization
di: Lyu, Xinyu, et al.
Pubblicazione: (2024)

AFTER: Mitigating the Object Hallucination of LVLM via Adaptive Factual-Guided Activation Editing
di: Wang, Tianbo, et al.
Pubblicazione: (2026)

Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization
di: Zhang, Siyuan, et al.
Pubblicazione: (2025)

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

Enhancement of Mechanical Properties of Low‐Density WC–TiC–Co Cemented Carbides
di: Shilei Xuan, et al.
Pubblicazione: (2025)

How Do Large Language Models Acquire Factual Knowledge During Pretraining?
di: Chang, Hoyeon, et al.
Pubblicazione: (2024)