Copertina

Detecting Overflow in Compressed Token Representations for Retrieval-Augmented Generation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Belikova, Julia, Rozhevskii, Danila, Svirin, Dennis, Polev, Konstantin, Panchenko, Alexander
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Data-efficient Meta-models for Evaluation of Context-based Questions and Answers in LLMs
di: Belikova, Julia, et al.
Pubblicazione: (2025)

When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA
di: Rykov, Elisei, et al.
Pubblicazione: (2025)

Hallucination Detection in LLMs with Topological Divergence on Attention Graphs
di: Bazarova, Alexandra, et al.
Pubblicazione: (2025)

Probabilistic distances-based hallucination detection in LLMs with RAG
di: Oblovatny, Rodion, et al.
Pubblicazione: (2025)

Semantic Tokens in Retrieval Augmented Generation
di: Suro, Joel
Pubblicazione: (2024)

Beyond Detection: Rethinking Education in the Age of AI-writing
di: Marina, Maria, et al.
Pubblicazione: (2026)

BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models
di: Cao, Qingqing, et al.
Pubblicazione: (2023)

Efficient Dynamic Clustering-Based Document Compression for Retrieval-Augmented-Generation
di: Li, Weitao, et al.
Pubblicazione: (2025)

Context-Adaptive Synthesis and Compression for Enhanced Retrieval-Augmented Generation in Complex Domains
di: Zhou, Peiran, et al.
Pubblicazione: (2025)

AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation
di: Luo, Lvzhou, et al.
Pubblicazione: (2025)

PISCO: Pretty Simple Compression for Retrieval-Augmented Generation
di: Louis, Maxime, et al.
Pubblicazione: (2025)

Structured Knowledge Representation through Contextual Pages for Retrieval-Augmented Generation
di: Li, Xinze, et al.
Pubblicazione: (2026)

A Theory for Token-Level Harmonization in Retrieval-Augmented Generation
di: Xu, Shicheng, et al.
Pubblicazione: (2024)

Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models
di: Vazhentsev, Artem, et al.
Pubblicazione: (2025)

InterpDetect: Interpretable Signals for Detecting Hallucinations in Retrieval-Augmented Generation
di: Tan, Likun, et al.
Pubblicazione: (2025)

Breaking Token Into Concepts: Exploring Extreme Compression in Token Representation Via Compositional Shared Semantics
di: R V, Kavin, et al.
Pubblicazione: (2025)

CompressKV: Semantic Retrieval Heads Know What Tokens are Not Important Before Generation
di: Lin, Xiaolin, et al.
Pubblicazione: (2025)

HyperbolicRAG: Enhancing Retrieval-Augmented Generation with Hyperbolic Representations
di: Cao, Linxiao, et al.
Pubblicazione: (2025)

Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation
di: Jung, Dongwon, et al.
Pubblicazione: (2024)

xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token
di: Cheng, Xin, et al.
Pubblicazione: (2024)

Contextual Compression in Retrieval-Augmented Generation for Large Language Models: A Survey
di: Verma, Sourav
Pubblicazione: (2024)

Unified Active Retrieval for Retrieval Augmented Generation
di: Cheng, Qinyuan, et al.
Pubblicazione: (2024)

DioR: Adaptive Cognitive Detection and Contextual Retrieval Optimization for Dynamic Retrieval-Augmented Generation
di: Guo, Hanghui, et al.
Pubblicazione: (2025)

Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics
di: Chang, Tyler A., et al.
Pubblicazione: (2024)

Explainable Depression Detection in Clinical Interviews with Personalized Retrieval-Augmented Generation
di: Zhang, Linhai, et al.
Pubblicazione: (2025)

EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation
di: Hwang, Taeho, et al.
Pubblicazione: (2024)

One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language Models
di: Zhu, Yutao, et al.
Pubblicazione: (2024)

Corrective Retrieval Augmented Generation
di: Yan, Shi-Qi, et al.
Pubblicazione: (2024)

MultiParaDetox: Extending Text Detoxification with Parallel Data to New Languages
di: Dementieva, Daryna, et al.
Pubblicazione: (2024)

<think> So let's replace this phrase with insult... </think> Lessons learned from generation of toxic texts with LLMs
di: Pletenev, Sergey, et al.
Pubblicazione: (2025)

S3: A Simple Strong Sample-effective Multimodal Dialog System
di: Rykov, Elisei, et al.
Pubblicazione: (2024)

Enhancing Frame Detection with Retrieval Augmented Generation
di: Diallo, Papa Abdou Karim Karou, et al.
Pubblicazione: (2025)

CoRoVA: Compressed Representations for Vector-Augmented Code Completion
di: Cherniuk, Daria, et al.
Pubblicazione: (2025)

Bi'an: A Bilingual Benchmark and Model for Hallucination Detection in Retrieval-Augmented Generation
di: Jiang, Zhouyu, et al.
Pubblicazione: (2025)

Anatomy of Unlearning: The Dual Impact of Fact Salience and Model Fine-Tuning
di: Borisiuk, Anna, et al.
Pubblicazione: (2026)

Evaluating Text Style Transfer: A Nine-Language Benchmark for Text Detoxification
di: Protasov, Vitaly, et al.
Pubblicazione: (2025)

Konstruktor: A Strong Baseline for Simple Knowledge Graph Question Answering
di: Lysyuk, Maria, et al.
Pubblicazione: (2024)

BenchOverflow: Measuring Overflow in Large Language Models via Plain-Text Prompts
di: Feiglin, Erin, et al.
Pubblicazione: (2026)

Noise-Robust Abstractive Compression in Retrieval-Augmented Language Models
di: Kim, Singon
Pubblicazione: (2025)

Feedback Adaptation for Retrieval-Augmented Generation
di: Bang, Jihwan, et al.
Pubblicazione: (2026)