Knowing You Don't Know: Learning When to Continue Search in Multi-round RAG through Self-Practicing

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yang, Diji, Zeng, Linda, Rao, Jinmeng, Zhang, Yi
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence Computation and Language Information Retrieval
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

IM-RAG: Multi-Round Retrieval-Augmented Generation Through Learning Inner Monologues
di: Yang, Diji, et al.
Pubblicazione: (2024)

"Knowing When You Don't Know": A Multilingual Relevance Assessment Dataset for Robust Retrieval-Augmented Generation
di: Thakur, Nandan, et al.
Pubblicazione: (2023)

Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals
di: Zeng, Linda, et al.
Pubblicazione: (2025)

"I Don't Know" -- Towards Appropriate Trust with Certainty-Aware Retrieval Augmented Generation
di: Di Scala, Daan, et al.
Pubblicazione: (2026)

Knowing When Not to Answer: Lightweight KB-Aligned OOD Detection for Safe RAG
di: Triantafyllopoulos, Ilias, et al.
Pubblicazione: (2025)

NanoKnow: How to Know What Your Language Model Knows
di: Gu, Lingwei, et al.
Pubblicazione: (2026)

WeKnow-RAG: An Adaptive Approach for Retrieval-Augmented Generation Integrating Web Search and Knowledge Graphs
di: Xie, Weijian, et al.
Pubblicazione: (2024)

Don't Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG
di: Sun, Yiqun, et al.
Pubblicazione: (2026)

Knowing When to Ask -- Bridging Large Language Models and Data
di: Radhakrishnan, Prashanth, et al.
Pubblicazione: (2024)

RAG-R1: Incentivizing the Search and Reasoning Capabilities of LLMs through Multi-query Parallelism
di: Tan, Zhiwen, et al.
Pubblicazione: (2025)

Know When to Fuse: Investigating Non-English Hybrid Retrieval in the Legal Domain
di: Louis, Antoine, et al.
Pubblicazione: (2024)

Do Retrieval Augmented Language Models Know When They Don't Know?
di: Zhou, Youchao, et al.
Pubblicazione: (2025)

Don't Measure Once: Measuring Visibility in AI Search (GEO)
di: Schulte, Julius, et al.
Pubblicazione: (2026)

Don't "Overthink" Passage Reranking: Is Reasoning Truly Necessary?
di: Jedidi, Nour, et al.
Pubblicazione: (2025)

Don't Reinvent the Wheel: Efficient Instruction-Following Text Embedding based on Guided Space Transformation
di: Feng, Yingchaojie, et al.
Pubblicazione: (2025)

SearchRAG: Can Search Engines Be Helpful for LLM-based Medical Question Answering?
di: Shi, Yucheng, et al.
Pubblicazione: (2025)

RAG-KG-IL: A Multi-Agent Hybrid Framework for Reducing Hallucinations and Enhancing LLM Reasoning through RAG and Incremental Knowledge Graph Learning Integration
di: Yu, Hong Qing, et al.
Pubblicazione: (2025)

When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering
di: Astaraki, Mahdi, et al.
Pubblicazione: (2026)

You Don't Bring Me Flowers: Mitigating Unwanted Recommendations Through Conformal Risk Control
di: De Toni, Giovanni, et al.
Pubblicazione: (2025)

Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?
di: Mei, Zhiting, et al.
Pubblicazione: (2025)

Multi-Head RAG: Solving Multi-Aspect Problems with LLMs
di: Besta, Maciej, et al.
Pubblicazione: (2024)

Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers
di: Sawarkar, Kunal, et al.
Pubblicazione: (2024)

MES-RAG: Bringing Multi-modal, Entity-Storage, and Secure Enhancements to RAG
di: Wu, Pingyu, et al.
Pubblicazione: (2025)

Think Before You Retrieve: Learning Test-Time Adaptive Search with Small Language Models
di: Vijay, Supriti, et al.
Pubblicazione: (2025)

Don't Waste It: Guiding Generative Recommenders with Structured Human Priors via Multi-Head Decoding
di: Zhang, Yunkai, et al.
Pubblicazione: (2025)

SmartRAG: Jointly Learn RAG-Related Tasks From the Environment Feedback
di: Gao, Jingsheng, et al.
Pubblicazione: (2024)

CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Search
di: Zeng, Hansi, et al.
Pubblicazione: (2026)

Can AI Assistants Know What They Don't Know?
di: Cheng, Qinyuan, et al.
Pubblicazione: (2024)

Sustainable Digitalization of Business with Multi-Agent RAG and LLM
di: Arslan, Muhammad, et al.
Pubblicazione: (2025)

What Models Know, How Well They Know It: Knowledge-Weighted Fine-Tuning for Learning When to Say "I Don't Know"
di: Lee, Joosung, et al.
Pubblicazione: (2026)

Search-E1: Self-Distillation Drives Self-Evolution in Search-Augmented Reasoning
di: Liang, Zihan, et al.
Pubblicazione: (2026)

IndexRAG: Bridging Facts for Cross-Document Reasoning at Index Time
di: Bao, Zhenghua, et al.
Pubblicazione: (2026)

Multi-Stage Verification-Centric Framework for Mitigating Hallucination in Multi-Modal RAG
di: Chen, Baiyu, et al.
Pubblicazione: (2025)

Don't Start Over: A Cost-Effective Framework for Migrating Personalized Prompts Between LLMs
di: Zhao, Ziyi, et al.
Pubblicazione: (2026)

Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
di: Jin, Bowen, et al.
Pubblicazione: (2025)

Don't Retrieve, Generate: Prompting LLMs for Synthetic Training Data in Dense Retrieval
di: Sinha, Aarush
Pubblicazione: (2025)

RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering
di: Zhang, Rongyang, et al.
Pubblicazione: (2025)

OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework
di: Chen, Ben, et al.
Pubblicazione: (2026)

DoTA-RAG: Dynamic of Thought Aggregation RAG
di: Ruangtanusak, Saksorn, et al.
Pubblicazione: (2025)

SD-Search: On-Policy Hindsight Self-Distillation for Search-Augmented Reasoning
di: Ma, Yufei, et al.
Pubblicazione: (2026)