Image de couverture de livre

Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kim, San, Kim, Jonghwi, Jeon, Yejin, Lee, Gary Geunbae
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models
par: Kim, San, et autres
Publié: (2026)

Multi-Facet Blending for Faceted Query-by-Example Retrieval
par: Do, Heejin, et autres
Publié: (2024)

Adversarial DPO: Harnessing Harmful Data for Reducing Toxicity with Minimal Impact on Coherence and Evasiveness in Dialogue Agents
par: Kim, San, et autres
Publié: (2024)

An Investigation Into Explainable Audio Hate Speech Detection
par: An, Jinmyeong, et autres
Publié: (2024)

Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognition
par: Lee, Wonjun, et autres
Publié: (2026)

Learning When to Translate for Multilingual Reasoning
par: Kang, Deokhyung, et autres
Publié: (2026)

Autoregressive Score Generation for Multi-trait Essay Scoring
par: Do, Heejin, et autres
Publié: (2024)

Retrieval-Augmented Fine-Tuning With Preference Optimization For Visual Program Generation
par: Kang, Deokhyung, et autres
Publié: (2025)

Key-Element-Informed sLLM Tuning for Document Summarization
par: Ryu, Sangwon, et autres
Publié: (2024)

Multimodal Cognitive Reframing Therapy via Multi-hop Psychotherapeutic Reasoning
par: Kim, Subin, et autres
Publié: (2025)

MIRROR: Multimodal Cognitive Reframing Therapy for Rolling with Resistance
par: Kim, Subin, et autres
Publié: (2025)

TPA: Next Token Probability Attribution for Detecting Hallucinations in RAG
par: Lu, Pengqian, et autres
Publié: (2025)

Denoising Table-Text Retrieval for Open-Domain Question Answering
par: Kang, Deokhyung, et autres
Publié: (2024)

Cross-lingual Back-Parsing: Utterance Synthesis from Meaning Representation for Zero-Resource Semantic Parsing
par: Kang, Deokhyung, et autres
Publié: (2024)

Ontology-Free General-Domain Knowledge Graph-to-Text Generation Dataset Synthesis using Large Language Model
par: Kim, Daehee, et autres
Publié: (2024)

Leveraging the Interplay Between Syntactic and Acoustic Cues for Optimizing Korean TTS Pause Formation
par: Jeon, Yejin, et autres
Publié: (2024)

K-COMP: Retrieval-Augmented Medical Domain Question Answering With Knowledge-Injected Compressor
par: Cho, Jeonghun, et autres
Publié: (2025)

PanicToCalm: A Proactive Counseling Agent for Panic Attacks
par: Lee, Jihyun, et autres
Publié: (2025)

GuRE:Generative Query REwriter for Legal Passage Retrieval
par: Kim, Daehee, et autres
Publié: (2025)

HybridRAG: A Practical LLM-based ChatBot Framework based on Pre-Generated Q&A over Raw Unstructured Documents
par: Kim, Sungmoon, et autres
Publié: (2025)

Adaptive Planning for Multi-Attribute Controllable Summarization with Monte Carlo Tree Search
par: Ryu, Sangwon, et autres
Publié: (2025)

Behavior-Aware Item Modeling via Dynamic Procedural Solution Representations for Knowledge Tracing
par: Seo, Jun, et autres
Publié: (2026)

Multi-Dimensional Optimization for Text Summarization via Reinforcement Learning
par: Ryu, Sangwon, et autres
Publié: (2024)

Revisiting Early Detection of Sexual Predators via Turn-level Optimization
par: An, Jinmyeong, et autres
Publié: (2025)

Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?
par: Kang, Deokhyung, et autres
Publié: (2025)

First Token Probability Guided RAG for Telecom Question Answering
par: Chen, Tingwei, et autres
Publié: (2025)

Leveraging What's Overfixed: Post-Correction via LLM Grammatical Error Overcorrection
par: Park, Taehee, et autres
Publié: (2025)

Teach-to-Reason with Scoring: Self-Explainable Rationale-Driven Multi-Trait Essay Scoring
par: Do, Heejin, et autres
Publié: (2025)

Autoregressive Multi-trait Essay Scoring via Reinforcement Learning with Scoring-aware Multiple Rewards
par: Do, Heejin, et autres
Publié: (2024)

Speak & Spell: LLM-Driven Controllable Phonetic Error Augmentation for Robust Dialogue State Tracking
par: Lee, Jihyun, et autres
Publié: (2024)

Exploring Iterative Controllable Summarization with Large Language Models
par: Ryu, Sangwon, et autres
Publié: (2024)

STACK: Adversarial Attacks on LLM Safeguard Pipelines
par: McKenzie, Ian R., et autres
Publié: (2025)

PSY-STEP: Structuring Therapeutic Targets and Action Sequences for Proactive Counseling Dialogue Systems
par: Lee, Jihyun, et autres
Publié: (2026)

A Theoretical Analysis of Why Masked Diffusion Models Mitigate the Reversal Curse
par: Jeon, Moongyu, et autres
Publié: (2026)

Towards Prompt Generalization: Grammar-aware Cross-Prompt Automated Essay Scoring
par: Do, Heejin, et autres
Publié: (2025)

Understanding LLM Behavior in Multi-Target Cross-Lingual Summarization
par: Ryu, Sangwon, et autres
Publié: (2026)

Focus on the Core: Efficient Attention via Pruned Token Compression for Document Classification
par: Yun, Jungmin, et autres
Publié: (2024)

PicPersona-TOD : A Dataset for Personalizing Utterance Style in Task-Oriented Dialogue with Image Persona
par: Lee, Jihyun, et autres
Publié: (2025)

Latent Preference Modeling for Cross-Session Personalized Tool Calling
par: Yoon, Yejin, et autres
Publié: (2026)

LP Data Pipeline: Lightweight, Purpose-driven Data Pipeline for Large Language Models
par: Kim, Yungi, et autres
Publié: (2024)