Image de couverture de livre

Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yang, Shiping, Wu, Jie, Ding, Wenbiao, Wu, Ning, Liang, Shining, Gong, Ming, Li, Hongzhi, Zhang, Hengyuan, Chang, Angel X., Zhang, Dongmei
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MuDAF: Long-Context Multi-Document Attention Focusing through Contrastive Learning on Attention Heads
par: Liu, Weihao, et autres
Publié: (2025)

Selected Languages are All You Need for Cross-lingual Truthfulness Transfer
par: Liu, Weihao, et autres
Publié: (2024)

Is Bigger and Deeper Always Better? Probing LLaMA Across Scales and Layers
par: Chen, Nuo, et autres
Publié: (2023)

ASPIRE: Language-Guided Data Augmentation for Improving Robustness Against Spurious Correlations
par: Ghosh, Sreyan, et autres
Publié: (2023)

PIKA: Expert-Level Synthetic Datasets for Post-Training Alignment from Scratch
par: Yin, Shangjian, et autres
Publié: (2025)

Spurious Feature Diversification Improves Out-of-distribution Generalization
par: Lin, Yong, et autres
Publié: (2023)

Beyond Rejection Sampling: Trajectory Fusion for Scaling Mathematical Reasoning
par: Deng, Jie, et autres
Publié: (2026)

A Sober Look at the Robustness of CLIPs to Spurious Features
par: Wang, Qizhou, et autres
Publié: (2024)

ViGiL3D: A Linguistically Diverse Dataset for 3D Visual Grounding
par: Wang, Austin T., et autres
Publié: (2025)

${M^2D}$NeRF: Multi-Modal Decomposition NeRF with 3D Feature Fields
par: Wang, Ning, et autres
Publié: (2024)

Out of Spuriousity: Improving Robustness to Spurious Correlations without Group Annotations
par: Le, Phuong Quynh, et autres
Publié: (2024)

Improving Group Robustness on Spurious Correlation via Evidential Alignment
par: Ye, Wenqian, et autres
Publié: (2025)

How Does Chunking Affect Retrieval-Augmented Code Completion? A Controlled Empirical Study
par: Wu, Xinjian, et autres
Publié: (2026)

Ploutos: Towards interpretable stock movement prediction with financial large language model
par: Tong, Hanshuang, et autres
Publié: (2024)

Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations
par: Zhang, Michael, et autres
Publié: (2022)

Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations
par: Chen, Nuo, et autres
Publié: (2023)

Your Attention Matters: to Improve Model Robustness to Noise and Spurious Correlations
par: Tamayo-Rousseau, Camilo, et autres
Publié: (2025)

ConPress: Learning Efficient Reasoning from Multi-Question Contextual Pressure
par: Deng, Jie, et autres
Publié: (2026)

TagRAG: Tag-guided Hierarchical Knowledge Graph Retrieval-Augmented Generation
par: Tao, Wenbiao, et autres
Publié: (2025)

QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation
par: Min, Dehai, et autres
Publié: (2025)

Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model
par: Ma, Huan, et autres
Publié: (2024)

ReFilter: Improving Robustness of Retrieval-Augmented Generation via Gated Filter
par: Chen, Yixin, et autres
Publié: (2026)

Quantifying the non-Abelian property of Andreev bound states in inhomogeneous Majorana nanowires
par: Zhang, Yu, et autres
Publié: (2024)

Grounding Language Models for Visual Entity Recognition
par: Xiao, Zilin, et autres
Publié: (2024)

Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning
par: Shi, Yaorui, et autres
Publié: (2025)

Improving Robustness to Multiple Spurious Correlations by Multi-Objective Optimization
par: Kim, Nayeong, et autres
Publié: (2024)

Weakly Supervised Contrastive Adversarial Training for Learning Robust Features from Semi-supervised Data
par: Zhang, Lilin, et autres
Publié: (2025)

Privacy Policy Enforcement Guardrails for Data-Sensitive Retrieval-Augmented Generation
par: Zafar, Osama, et autres
Publié: (2026)

Challenges and Opportunities in Improving Worst-Group Generalization in Presence of Spurious Features
par: Joshi, Siddharth, et autres
Publié: (2023)

PRISM: Exposing and Resolving Spurious Isolation in Federated Multimodal Continual Learning
par: Wu, Beining, et autres
Publié: (2026)

Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation
par: Xia, Sirui, et autres
Publié: (2024)

Multi-modal Semantic Understanding with Contrastive Cross-modal Feature Alignment
par: Zhang, Ming, et autres
Publié: (2024)

Retrieval-Augmented Purifier for Robust LLM-Empowered Recommendation
par: Ning, Liangbo, et autres
Publié: (2025)

Spuriousness-Aware Meta-Learning for Learning Robust Classifiers
par: Zheng, Guangtao, et autres
Publié: (2024)

Tuning Strong Metal‐Support Interactions for Enhancing Direct Deoxygenation of Biomass‐Lignin Derived Phenolics
par: Shining Ding, et autres
Publié: (2024)

Generalizing Single-View 3D Shape Retrieval to Occlusions and Unseen Objects
par: Wu, Qirui, et autres
Publié: (2023)

Elastic Representation: Mitigating Spurious Correlations for Group Robustness
par: Wen, Tao, et autres
Publié: (2025)

Improving Group Robustness on Spurious Correlation Requires Preciser Group Inference
par: Han, Yujin, et autres
Publié: (2024)

Policy-Invisible Violations in LLM-Based Agents
par: Wu, Jie, et autres
Publié: (2026)

Beyond Single-Agent Alignment: Preventing Context-Fragmented Violations in Multi-Agent Systems
par: Wu, Jie, et autres
Publié: (2026)