Image de couverture de livre

Out of Style: RAG's Fragility to Linguistic Variation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Cao, Tianyu, Bhandari, Neel, Yerukola, Akhila, Asai, Akari, Sap, Maarten
Format:	Preprint
Publié:	2025
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

Is the Pope Catholic? Yes, the Pope is Catholic. Generative Evaluation of Non-Literal Intent Resolution in LLMs
par: Yerukola, Akhila, et autres
Publié: (2024)

Mind the Gesture: Evaluating AI Sensitivity to Culturally Offensive Non-Verbal Gestures
par: Yerukola, Akhila, et autres
Publié: (2025)

NormAd: A Framework for Measuring the Cultural Adaptability of Large Language Models
par: Rao, Abhinav, et autres
Publié: (2024)

Words Like Knives: Backstory-Personalized Modeling and Detection of Violent Communication
par: Shen, Jocelyn, et autres
Publié: (2025)

PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages
par: Kumar, Priyanshu, et autres
Publié: (2025)

Mitigating Bias in RAG: Controlling the Embedder
par: Kim, Taeyoun, et autres
Publié: (2025)

Ambig-SWE: Interactive Agents to Overcome Underspecificity in Software Engineering
par: Vijayvargiya, Sanidhya, et autres
Publié: (2025)

Social World Models
par: Zhou, Xuhui, et autres
Publié: (2025)

HEART-felt Narratives: Tracing Empathy and Narrative Style in Personal Stories with LLMs
par: Shen, Jocelyn, et autres
Publié: (2024)

CodeRAG-Bench: Can Retrieval Augment Code Generation?
par: Wang, Zora Zhiruo, et autres
Publié: (2024)

Imperfectly Cooperative Human-AI Interactions: Comparing the Impacts of Human and AI Attributes in Simulated and User Studies
par: Cohen, Myke C., et autres
Publié: (2026)

Train for Truth, Keep the Skills: Binary Retrieval-Augmented Reward Mitigates Hallucinations
par: Chen, Tong, et autres
Publié: (2025)

AgentIR: Reasoning-Aware Retrieval for Deep Research Agents
par: Chen, Zijian, et autres
Publié: (2026)

From Dogwhistles to Bullhorns: Unveiling Coded Rhetoric with Language Models
par: Mendelsohn, Julia, et autres
Publié: (2023)

Stereotype or Personalization? User Identity Biases Chatbot Recommendations
par: Kantharuban, Anjali, et autres
Publié: (2024)

Where Do People Tell Stories Online? Story Detection Across Online Communities
par: Antoniak, Maria, et autres
Publié: (2023)

Fine-grained Hallucination Detection and Editing for Language Models
par: Mishra, Abhika, et autres
Publié: (2024)

Differentially-Private Text Rewriting reshapes Linguistic Style
par: Arnold, Stefan
Publié: (2026)

Martingale Score: An Unsupervised Metric for Bayesian Rationality in LLM Reasoning
par: He, Zhonghao, et autres
Publié: (2025)

Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertainty
par: Zhou, Kaitlyn, et autres
Publié: (2024)

Say It Differently: Linguistic Styles as Jailbreak Vectors
par: Panda, Srikant, et autres
Publié: (2025)

BabyLM Challenge: Exploring the Effect of Variation Sets on Language Model Training Efficiency
par: Haga, Akari, et autres
Publié: (2024)

Breaking mBad! Supervised Fine-tuning for Cross-Lingual Detoxification
par: Beniwal, Himanshu, et autres
Publié: (2025)

Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMs
par: Zhou, Xuhui, et autres
Publié: (2024)

GoodPoint: Learning Constructive Scientific Paper Feedback from Author Responses
par: Mun, Jimin, et autres
Publié: (2026)

Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversations
par: Zheng, Mingqian, et autres
Publié: (2026)

Curiosity-Driven LLM-as-a-judge for Personalized Creative Judgment
par: Kumar, Vanya Bannihatti, et autres
Publié: (2025)

PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models
par: Jain, Devansh, et autres
Publié: (2024)

BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data
par: Li, Wenkai, et autres
Publié: (2024)

Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAG
par: Ki, Dayeon, et autres
Publié: (2025)

Cognitive Chain-of-Thought (CoCoT): Structured Multimodal Reasoning about Social Situations
par: Park, Eunkyu, et autres
Publié: (2025)

Data Defenses Against Large Language Models
par: Agnew, William, et autres
Publié: (2024)

Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models
par: Baheti, Ashutosh, et autres
Publié: (2023)

StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis
par: Zhang, Yu, et autres
Publié: (2023)

Simple Mechanistic Explanations for Out-Of-Context Reasoning
par: Wang, Atticus, et autres
Publié: (2025)

Bilevel MCTS for Amortized O(1) Node Selection in Classical Planning
par: Asai, Masataro
Publié: (2025)

Style-agnostic evaluation of ASR using multiple reference transcripts
par: McNamara, Quinten, et autres
Publié: (2024)

Digital Linguistic Bias in Spanish: Evidence from Lexical Variation in LLMs
par: Kawasaki, Yoshifumi
Publié: (2026)

Rel-A.I.: An Interaction-Centered Approach To Measuring Human-LM Reliance
par: Zhou, Kaitlyn, et autres
Publié: (2024)

EVALUESTEER: Measuring Reward Model Steerability Towards Values and Preferences
par: Ghate, Kshitish, et autres
Publié: (2025)