Cover Image

Efficiency vs. Alignment: Investigating Safety and Fairness Risks in Parameter-Efficient Fine-Tuning of LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Taraghi, Mina, Pequignot, Yann, Nikanjam, Amin, Merzouk, Mohamed Amine, Khomh, Foutse
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Prism: Dynamic and Flexible Benchmarking of LLMs Code Generation with Monte Carlo Tree Search
by: Majdinasab, Vahid, et al.
Published: (2025)

DeepCodeProbe: Towards Understanding What Models Trained on Code Learn
by: Majdinasab, Vahid, et al.
Published: (2024)

ReCatcher: Towards LLMs Regression Testing for Code Generation
by: Abbassi, Altaf Allah, et al.
Published: (2025)

Common Challenges of Deep Reinforcement Learning Applications Development: An Empirical Study
by: Morovati, Mohammad Mehdi, et al.
Published: (2023)

TaskEval: Assessing Difficulty of Code Generation Tasks for Large Language Models
by: Tambon, Florian, et al.
Published: (2024)

Adversarial Moral Stress Testing of Large Language Models
by: Jamshidi, Saeid, et al.
Published: (2026)

Bugs in Large Language Models Generated Code: An Empirical Study
by: Tambon, Florian, et al.
Published: (2024)

Real Faults in Model Context Protocol (MCP) Software: a Comprehensive Taxonomy
by: Taraghi, Mina, et al.
Published: (2026)

Secure Tool Manifest and Digital Signing Solution for Verifiable MCP and LLM Pipelines
by: Jamshidi, Saeid, et al.
Published: (2026)

Trained Without My Consent: Detecting Code Inclusion In Language Models Trained on Code
by: Majdinasab, Vahid, et al.
Published: (2024)

Toward Debugging Deep Reinforcement Learning Programs with RLExplorer
by: Bouchoucha, Rached, et al.
Published: (2024)

An Efficient Model Maintenance Approach for MLOps
by: Majidi, Forough, et al.
Published: (2024)

LLMs and Stack Overflow Discussions: Reliability, Impact, and Challenges
by: Da Silva, Leuson, et al.
Published: (2024)

Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms
by: Le, Linh, et al.
Published: (2026)

Fault Localization in Deep Learning-based Software: A System-level Approach
by: Morovati, Mohammad Mehdi, et al.
Published: (2024)

Machine Learning Robustness: A Primer
by: Braiek, Houssem Ben, et al.
Published: (2024)

PathOCL: Path-Based Prompt Augmentation for OCL Generation with GPT-4
by: Abukhalaf, Seif, et al.
Published: (2024)

RefAgent: A Multi-agent LLM-based Framework for Automatic Software Refactoring
by: Oueslati, Khouloud, et al.
Published: (2025)

Chain of Targeted Verification Questions to Improve the Reliability of Code Generated by LLMs
by: Ngassom, Sylvain Kouemo, et al.
Published: (2024)

Deep Learning Model Reuse in the HuggingFace Community: Challenges, Benefit and Trends
by: Taraghi, Mina, et al.
Published: (2024)

Semantic Attacks on Tool-Augmented LLMs: Securing the Model Context Protocol Against Descriptor-Level Manipulation
by: Jamshidi, Saeid, et al.
Published: (2025)

What Information Contributes to Log-based Anomaly Detection? Insights from a Configurable Transformer-Based Approach
by: Wu, Xingfang, et al.
Published: (2024)

From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices
by: Slamanig, Georg, et al.
Published: (2025)

Leveraging Machine Learning Techniques in Intrusion Detection Systems for Internet of Things
by: Jamshidi, Saeid, et al.
Published: (2025)

Evaluating Machine Learning-Driven Intrusion Detection Systems in IoT: Performance and Energy Consumption
by: Jamshidi, Saeid, et al.
Published: (2025)

SDLog: A Deep Learning Framework for Detecting Sensitive Information in Software Logs
by: Aghili, Roozbeh, et al.
Published: (2025)

FairLLaVA: Fairness-Aware Parameter-Efficient Fine-Tuning for Large Vision-Language Assistants
by: Bhosale, Mahesh, et al.
Published: (2026)

Understanding and Preserving Safety in Fine-Tuned LLMs
by: Zhang, Jiawen, et al.
Published: (2026)

Defending MoE LLMs against Harmful Fine-Tuning via Safety Routing Alignment
by: Kim, Jaehan, et al.
Published: (2025)

Parameter-Efficient Fine-Tuning With Adapters
by: Chen, Keyu, et al.
Published: (2024)

Analysing Safety Risks in LLMs Fine-Tuned with Pseudo-Malicious Cyber Security Data
by: ElZemity, Adel, et al.
Published: (2025)

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

Re-Emergent Misalignment: How Narrow Fine-Tuning Erodes Safety Alignment in LLMs
by: Giordani, Jeremiah
Published: (2025)

NeuronTune: Fine-Grained Neuron Modulation for Balanced Safety-Utility Alignment in LLMs
by: Pan, Birong, et al.
Published: (2025)

Narrow Fine-Tuning Erodes Safety Alignment in Vision-Language Agents
by: Gulati, Idhant, et al.
Published: (2026)

Diffusion-based Adversarial Purification for Intrusion Detection
by: Merzouk, Mohamed Amine, et al.
Published: (2024)

Partial Order in Chaos: Consensus on Feature Attributions in the Rashomon Set
by: Laberge, Gabriel, et al.
Published: (2021)

Parameter Efficiency Is Not Memory Efficiency: Rethinking Fine-Tuning for On-Device LLM Adaptation
by: Tenison, Irene, et al.
Published: (2026)

The Geometry of Alignment Collapse: When Fine-Tuning Breaks Safety
by: Springer, Max, et al.
Published: (2026)

A Systematic Evaluation of Parameter-Efficient Fine-Tuning Methods for the Security of Code LLMs
by: Lee, Kiho, et al.
Published: (2025)