Image de couverture de livre

Does the Generator Mind its Contexts? An Analysis of Generative Model Faithfulness under Context Transfer

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hu, Xinshuo, Hu, Baotian, Li, Dongfang, Li, Xiaoguang, Shang, Lifeng
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

In-Context Learning State Vector with Inner and Momentum Optimization
par: Li, Dongfang, et autres
Publié: (2024)

Take Off the Training Wheels Progressive In-Context Learning for Effective Alignment
par: Liu, Zhenyu, et autres
Publié: (2025)

CMT: A Memory Compression Method for Continual Knowledge Learning of Large Language Models
par: Li, Dongfang, et autres
Publié: (2024)

Improving Attributed Text Generation of Large Language Models via Preference Learning
par: Li, Dongfang, et autres
Publié: (2024)

Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation
par: Hu, Xinshuo, et autres
Publié: (2023)

Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training
par: Li, Dongfang, et autres
Publié: (2023)

Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning
par: Chen, Zhuoen, et autres
Publié: (2026)

LycheeCluster: Efficient Long-Context Inference with Structure-Aware Chunking and Hierarchical KV Indexing
par: Li, Dongfang, et autres
Publié: (2026)

FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG
par: Zhao, Xinping, et autres
Publié: (2024)

Learning to Extract Rational Evidence via Reinforcement Learning for Retrieval-Augmented Generation
par: Zhao, Xinping, et autres
Publié: (2025)

LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding
par: Lin, Gang, et autres
Publié: (2026)

SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation
par: Zhao, Xinping, et autres
Publié: (2024)

A Multimodal In-Context Tuning Approach for E-Commerce Product Description Generation
par: Li, Yunxin, et autres
Publié: (2024)

FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation
par: Zhang, Qinggang, et autres
Publié: (2025)

Improving Value-based Process Verifier via Low-Cost Variance Reduction
par: Sun, Zetian, et autres
Publié: (2025)

KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model
par: Hu, Xinshuo, et autres
Publié: (2025)

Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding
par: Zhang, Weixu, et autres
Publié: (2026)

Is On-Policy Data always the Best Choice for Direct Preference Optimization-based LM Alignment?
par: Sun, Zetian, et autres
Publié: (2025)

VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems in Visual Context
par: Li, Yunxin, et autres
Publié: (2024)

Context-DPO: Aligning Language Models for Context-Faithfulness
par: Bi, Baolong, et autres
Publié: (2024)

Structured Episodic Event Memory
par: Lu, Zhengxuan, et autres
Publié: (2026)

Stabilizing Long-term Multi-turn Reinforcement Learning with Gated Rewards
par: Sun, Zetian, et autres
Publié: (2025)

Improving Value-based Process Verifier via Structural Prior Injection
par: Sun, Zetian, et autres
Publié: (2025)

Generative Multimodal Entity Linking
par: Shi, Senbao, et autres
Publié: (2023)

Temporal Knowledge Question Answering via Abstract Reasoning Induction
par: Chen, Ziyang, et autres
Publié: (2023)

Generate, Discriminate, Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-Evolution
par: Li, Kun, et autres
Publié: (2025)

Faithfulness-QA: A Counterfactual Entity Substitution Dataset for Training Context-Faithful RAG Models
par: Ju, Li, et autres
Publié: (2026)

Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models
par: Huang, Yanwen, et autres
Publié: (2025)

KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model
par: Zhao, Xinping, et autres
Publié: (2025)

LongFaith: Enhancing Long-Context Reasoning in LLMs with Faithful Synthetic Data
par: Yang, Cehao, et autres
Publié: (2025)

Every Token Counts: Generalizing 16M Ultra-Long Context in Large Language Models
par: Hu, Xiang, et autres
Publié: (2025)

On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey
par: Zhang, Meishan, et autres
Publié: (2025)

Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style
par: Li, Yuepei, et autres
Publié: (2024)

Assessing LLMs in Art Contexts: Critique Generation and Theory of Mind Evaluation
par: Arita, Takaya, et autres
Publié: (2025)

ContextCite: Attributing Model Generation to Context
par: Cohen-Wang, Benjamin, et autres
Publié: (2024)

ContextLens: Modeling Imperfect Privacy and Safety Context for Legal Compliance
par: Li, Haoran, et autres
Publié: (2026)

Listen to the Context: Towards Faithful Large Language Models for Retrieval Augmented Generation on Climate Questions
par: Thulke, David, et autres
Publié: (2025)

InfMem: Learning System-2 Memory Control for Long-Context Agent
par: Wang, Xinyu, et autres
Publié: (2026)

Where Does Long-Context Supervision Actually Go? Effective-Context Exposure Balancing
par: Zhu, Jinchang, et autres
Publié: (2026)

SSFO: Self-Supervised Faithfulness Optimization for Retrieval-Augmented Generation
par: Tang, Xiaqiang, et autres
Publié: (2025)