Cover Image

Where Do Prompt Perturbations Break Generation? A Segment-Level View of Robustness in LoRA-Tuned Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Zhuoyun, Wang, Boxuan, Hu, Jinwei, Huang, Zhenglin, He, Qisong, Huang, Xinmiao, Cheng, Guangliang, Huang, Xiaowei, Dong, Yi
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models
by: Huang, Xinmiao, et al.
Published: (2025)

Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation
by: He, Qisong, et al.
Published: (2026)

Chain-of-Thought as a Lens: Evaluating Structured Reasoning Alignment between Human Preferences and Large Language Models
by: Wang, Boxuan, et al.
Published: (2025)

FragileFlow: Spectral Control of Correct-but-Fragile Predictions for Foundation Model Robustness
by: Li, Zhuoyun, et al.
Published: (2026)

Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts
by: Wang, Boxuan, et al.
Published: (2026)

Responsible Agentic AI Requires Explicit Provenance
by: Hu, Jinwei, et al.
Published: (2026)

Rethinking Multi-Agent Intelligence Through the Lens of Small-World Networks
by: Wang, Boxuan, et al.
Published: (2025)

FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model
by: Hu, Jinwei, et al.
Published: (2025)

Position: Towards a Responsible LLM-empowered Multi-Agent Systems
by: Hu, Jinwei, et al.
Published: (2025)

Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignment
by: Hu, Jinwei, et al.
Published: (2025)

Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs
by: Ao, Shuang, et al.
Published: (2025)

Multimodal Instruction Tuning with Conditional Mixture of LoRA
by: Shen, Ying, et al.
Published: (2024)

Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage
by: Hu, Jinwei, et al.
Published: (2026)

LoRA-PAR: A Flexible Dual-System LoRA Partitioning Approach to Efficient LLM Fine-Tuning
by: Huang, Yining, et al.
Published: (2025)

Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations
by: He, Qisong, et al.
Published: (2026)

Mixture of LoRA Experts
by: Wu, Xun, et al.
Published: (2024)

NP-LoRA: Null Space Projection for Subject-Style LoRA Fusion
by: Chen, Chuheng, et al.
Published: (2025)

LoRA-Edit: Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-Tuning
by: Gao, Chenjian, et al.
Published: (2025)

PeriodicLoRA: Breaking the Low-Rank Bottleneck in LoRA Optimization
by: Meng, Xiangdi, et al.
Published: (2024)

LoRA-Squeeze: Simple and Effective Post-Tuning and In-Tuning Compression of LoRA Modules
by: Vulić, Ivan, et al.
Published: (2026)

Vision as LoRA
by: Wang, Han, et al.
Published: (2025)

NaRA: Noise-Aware LoRA for Parameter-Efficient Fine-Tuning of Diffusion LLMs
by: Wang, Shuaidi, et al.
Published: (2026)

PrefixGuard: From LLM-Agent Traces to Online Failure-Warning Monitors
by: Huang, Xinmiao, et al.
Published: (2026)

AuroRA: Breaking Low-Rank Bottleneck of LoRA with Nonlinear Mapping
by: Dong, Haonan, et al.
Published: (2025)

ALTO: Adaptive LoRA Tuning and Orchestration for Heterogeneous LoRA Training Workloads
by: Zuo, Jingwei, et al.
Published: (2026)

LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinement
by: Bian, Jieming, et al.
Published: (2024)

CE-LoRA: Computation-Efficient LoRA Fine-Tuning for Language Models
by: Chen, Guanduo, et al.
Published: (2025)

SHE-LoRA: Selective Homomorphic Encryption for Federated Tuning with Heterogeneous LoRA
by: Liu, Jianmin, et al.
Published: (2025)

Bi-LoRA: Efficient Sharpness-Aware Minimization for Fine-Tuning Large-Scale Models
by: Liu, Yuhang, et al.
Published: (2025)

Robust LLM-based Column Type Annotation via Prompt Augmentation with LoRA Tuning
by: Meng, Hanze, et al.
Published: (2025)

Towards Multi-Level Transcript Segmentation: LoRA Fine-Tuning for Table-of-Contents Generation
by: Freisinger, Steffen, et al.
Published: (2026)

ALLoRA: Adaptive Learning Rate Mitigates LoRA Fatal Flaws
by: Huang, Hai, et al.
Published: (2024)

DR-LoRA: Dynamic Rank LoRA for Fine-Tuning Mixture-of-Experts Models
by: Deng, Guanzhi, et al.
Published: (2026)

Dual LoRA: Enhancing LoRA with Magnitude and Direction Updates
by: Xu, Yixing, et al.
Published: (2025)

LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization
by: Yen, Jui-Nan, et al.
Published: (2024)

SCALE-LoRA: Auditing Post-Retrieval LoRA Composition with Residual Merging and View Reliability
by: Zhou, Shuaipeng, et al.
Published: (2026)

CA-LoRA: Concept-Aware LoRA for Domain-Aligned Segmentation Dataset Generation
by: Park, Minho, et al.
Published: (2025)

pFedLoRA: Model-Heterogeneous Personalized Federated Learning with LoRA Tuning
by: Yi, Liping, et al.
Published: (2023)

SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model
by: Huang, Zhenglin, et al.
Published: (2024)

FDLoRA: Personalized Federated Learning of Large Language Model via Dual LoRA Tuning
by: QI, Jiaxing, et al.
Published: (2024)