Copertina

CTRL-RAG: Contrastive Likelihood Reward Based Reinforcement Learning for Context-Faithful RAG Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Tan, Zhehao, Jiao, Yihan, Yang, Dan, Wang, Junjie, Sun, Duolin, Feng, Jie, Wang, Xidong, Liu, Lei, Shen, Yue, Wang, Jian, Gu, Jinjie
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

PRGB Benchmark: A Robust Placeholder-Assisted Algorithm for Benchmarking Retrieval-Augmented Generation
di: Tan, Zhehao, et al.
Pubblicazione: (2025)

HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering
di: Sun, Duolin, et al.
Pubblicazione: (2025)

WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning
di: Wang, Junjie, et al.
Pubblicazione: (2026)

GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs
di: Long, Meixiu, et al.
Pubblicazione: (2025)

FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation
di: Zhang, Qinggang, et al.
Pubblicazione: (2025)

Faithfulness-QA: A Counterfactual Entity Substitution Dataset for Training Context-Faithful RAG Models
di: Ju, Li, et al.
Pubblicazione: (2026)

DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval
di: Sun, Duolin, et al.
Pubblicazione: (2025)

Reward-RAG: Enhancing RAG with Reward Driven Supervision
di: Nguyen, Thang, et al.
Pubblicazione: (2024)

UniDoc-RL: Coarse-to-Fine Visual RAG with Hierarchical Actions and Dense Rewards
di: Wang, Jun, et al.
Pubblicazione: (2026)

From RAG to Agentic RAG for Faithful Islamic Question Answering
di: Bhatia, Gagan, et al.
Pubblicazione: (2026)

Correctness is not Faithfulness in RAG Attributions
di: Wallat, Jonas, et al.
Pubblicazione: (2024)

LiveClin: A Live Clinical Benchmark without Leakage
di: Wang, Xidong, et al.
Pubblicazione: (2026)

ClinAlign: Scaling Healthcare Alignment from Clinician Preference
di: Lyu, Shiwei, et al.
Pubblicazione: (2026)

Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS
di: Xu, Shijia, et al.
Pubblicazione: (2026)

Know Your Needs Better: Towards Structured Understanding of Marketer Demands with Analogical Reasoning Augmented LLMs
di: Wang, Junjie, et al.
Pubblicazione: (2024)

Towards Faithful Industrial RAG: A Reinforced Co-adaptation Framework for Advertising QA
di: Li, Wenwei, et al.
Pubblicazione: (2026)

OpenRAG: Optimizing RAG End-to-End via In-Context Retrieval Learning
di: Zhou, Jiawei, et al.
Pubblicazione: (2025)

RAG-based Crowdsourcing Task Decomposition via Masked Contrastive Learning with Prompts
di: Yang, Jing, 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)

SFR-RAG: Towards Contextually Faithful LLMs
di: Nguyen, Xuan-Phi, et al.
Pubblicazione: (2024)

Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards
di: Tamber, Manveer Singh, et al.
Pubblicazione: (2025)

From Code Generation to Software Testing: AI Copilot with Context-Based RAG
di: Wang, Yuchen, et al.
Pubblicazione: (2025)

Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning
di: Zhang, Wenlin, et al.
Pubblicazione: (2025)

EmoRAG: Evaluating RAG Robustness to Symbolic Perturbations
di: Zhou, Xinyun, et al.
Pubblicazione: (2025)

Context Embeddings for Efficient Answer Generation in RAG
di: Rau, David, et al.
Pubblicazione: (2024)

RAG Makes Guardrails Unsafe? Investigating Robustness of Guardrails under RAG-style Contexts
di: She, Yining, et al.
Pubblicazione: (2025)

Optimizing Retrieval for RAG via Reinforcement Learning
di: Zhou, Jiawei, et al.
Pubblicazione: (2025)

HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems
di: Tan, Jiejun, et al.
Pubblicazione: (2024)

Self-Rewarding Rubric-Based Reinforcement Learning for Open-Ended Reasoning
di: Ye, Zhiling, et al.
Pubblicazione: (2025)

MacRAG: Compress, Slice, and Scale-up for Multi-Scale Adaptive Context RAG
di: Lim, Woosang, et al.
Pubblicazione: (2025)

In Defense of RAG in the Era of Long-Context Language Models
di: Yu, Tan, et al.
Pubblicazione: (2024)

ECoRAG: Evidentiality-guided Compression for Long Context RAG
di: Jeong, Yeonseok, et al.
Pubblicazione: (2025)

LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering
di: Zhao, Qingfei, et al.
Pubblicazione: (2024)

Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning
di: Wu, Yuhang, et al.
Pubblicazione: (2026)

PrLM: Learning Explicit Reasoning for Personalized RAG via Contrastive Reward Optimization
di: Zhang, Kepu, et al.
Pubblicazione: (2025)

Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworks
di: Gao, Yunfan, et al.
Pubblicazione: (2024)

FoRAG: Factuality-optimized Retrieval Augmented Generation for Web-enhanced Long-form Question Answering
di: Cai, Tianchi, et al.
Pubblicazione: (2024)

GeoRAG: A Question-Answering Approach from a Geographical Perspective
di: Wang, Jian, et al.
Pubblicazione: (2025)

FARSIQA: Faithful and Advanced RAG System for Islamic Question Answering
di: Asl, Mohammad Aghajani, et al.
Pubblicazione: (2025)

OCC-RAG: Optimal Cognitive Core for Faithful Question Answering
di: Savkin, Maksim, et al.
Pubblicazione: (2026)