Image de couverture de livre

How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Pletenev, Sergey, Marina, Maria, Moskovskiy, Daniil, Konovalov, Vasily, Braslavski, Pavel, Panchenko, Alexander, Salnikov, Mikhail
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

Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval
par: Vazhentsev, Artem, et autres
Publié: (2026)

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

Konstruktor: A Strong Baseline for Simple Knowledge Graph Question Answering
par: Lysyuk, Maria, et autres
Publié: (2024)

LLM-Independent Adaptive RAG: Let the Question Speak for Itself
par: Marina, Maria, et autres
Publié: (2025)

SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators
par: Moskovskiy, Daniil, et autres
Publié: (2025)

Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA
par: Pletenev, Sergey, et autres
Publié: (2025)

Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home
par: Moskvoretskii, Viktor, et autres
Publié: (2025)

The Chronicles of RiDiC: Generating Datasets with Controlled Popularity Distribution for Long-form Factuality Evaluation
par: Braslavski, Pavel, et autres
Publié: (2026)

Beyond Detection: Rethinking Education in the Age of AI-writing
par: Marina, Maria, et autres
Publié: (2026)

S-LoRA: Serving Thousands of Concurrent LoRA Adapters
par: Sheng, Ying, et autres
Publié: (2023)

How Much is Too Much? Exploring LoRA Rank Trade-offs for Retaining Knowledge and Domain Robustness
par: Rathore, Darshita, et autres
Publié: (2025)

Spectral Geometry of LoRA Adapters Encodes Training Objective and Predicts Harmful Compliance
par: Paul, Roi
Publié: (2026)

LoRACode: LoRA Adapters for Code Embeddings
par: Chaturvedi, Saumya, et autres
Publié: (2025)

Kron-LoRA: Hybrid Kronecker-LoRA Adapters for Scalable, Sustainable Fine-tuning
par: Shen, Yixin
Publié: (2025)

Serving Heterogeneous LoRA Adapters in Distributed LLM Inference Systems
par: Jaiswal, Shashwat, et autres
Publié: (2025)

Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead
par: Brüel-Gabrielsson, Rickard, et autres
Publié: (2024)

Weight space Detection of Backdoors in LoRA Adapters
par: Merenciano, David Puertolas, et autres
Publié: (2026)

AutoRAG-LoRA: Hallucination-Triggered Knowledge Retuning via Lightweight Adapters
par: Dwivedi, Kaushik, et autres
Publié: (2025)

LoRA-Drop: Temporal LoRA Decoding for Efficient LLM Inference
par: Rajabzadeh, Hossein, et autres
Publié: (2026)

AuthenLoRA: Entangling Stylization with Imperceptible Watermarks for Copyright-Secure LoRA Adapters
par: Shi, Fangming, et autres
Publié: (2025)

LoRA-Pro: Are Low-Rank Adapters Properly Optimized?
par: Wang, Zhengbo, et autres
Publié: (2024)

Effective LoRA Adapter Routing using Task Representations
par: Dhasade, Akash, et autres
Publié: (2026)

SLAD : Shared LoRA Adapters for Task Specific Distillation
par: Bensaid, Reda, et autres
Publié: (2026)

POLAR: Online Learning for LoRA Adapter Caching and Routing in Edge LLM Serving
par: Li, Shaoang, et autres
Publié: (2026)

LoRA Is Slower Than You Think
par: Ko, Seokmin
Publié: (2025)

Enhancing Learned Knowledge in LoRA Adapters Through Efficient Contrastive Decoding on Ascend NPUs
par: Heisler, Morgan Lindsay, et autres
Publié: (2025)

LoREnc: Low-Rank Encryption for Securing Foundation Models and LoRA Adapters
par: Ahn, Beomjin, et autres
Publié: (2026)

HypeLoRA: Hyper-Network-Generated LoRA Adapters for Calibrated Language Model Fine-Tuning
par: Trojan, Bartosz, et autres
Publié: (2026)

DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion Model
par: Xia, Siwei, et autres
Publié: (2025)

KD-LoRA: A Hybrid Approach to Efficient Fine-Tuning with LoRA and Knowledge Distillation
par: Azimi, Rambod, et autres
Publié: (2024)

LoRA-Switch: Boosting the Efficiency of Dynamic LLM Adapters via System-Algorithm Co-design
par: Kong, Rui, et autres
Publié: (2024)

A Little Rank Goes a Long Way: Random Scaffolds with LoRA Adapters Are All You Need
par: Hazan, Hananel, et autres
Publié: (2026)

Parametric Retrieval-Augmented Generation using Latent Routing of LoRA Adapters
par: Su, Zhan, et autres
Publié: (2025)

mLoRA: Fine-Tuning LoRA Adapters via Highly-Efficient Pipeline Parallelism in Multiple GPUs
par: Ye, Zhengmao, et autres
Publié: (2023)

SC-LoRA: Balancing Efficient Fine-tuning and Knowledge Preservation via Subspace-Constrained LoRA
par: Luo, Minrui, et autres
Publié: (2025)

Run LoRA Run: Faster and Lighter LoRA Implementations
par: Cherniuk, Daria, et autres
Publié: (2023)

Dual LoRA: Enhancing LoRA with Magnitude and Direction Updates
par: Xu, Yixing, et autres
Publié: (2025)

Uni-LoRA: One Vector is All You Need
par: Li, Kaiyang, et autres
Publié: (2025)

LoRA as Oracle
par: Arazzi, Marco, et autres
Publié: (2026)

Vision as LoRA
par: Wang, Han, et autres
Publié: (2025)