Cover Image

Alignment-Constrained Dynamic Pruning for LLMs: Identifying and Preserving Alignment-Critical Circuits

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Patel, Dev, Gervacio, Gabrielle, Raimi, Diekola, Zhu, Kevin, Lagasse, Ryan, Grand, Gabriel, Panda, Ashwinee, Chaudhary, Maheep
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Amortized Latent Steering: Low-Cost Alternative to Test-Time Optimization
by: Egbuna, Nathan, et al.
Published: (2025)

Evaluation Awareness Scales Predictably in Open-Weights Large Language Models
by: Chaudhary, Maheep, et al.
Published: (2025)

Hydra: A Modular Architecture for Efficient Long-Context Reasoning
by: Chaudhary, Siddharth, et al.
Published: (2025)

SALT: Steering Activations towards Leakage-free Thinking in Chain of Thought
by: Batra, Shourya, et al.
Published: (2025)

FRIT: Using Causal Importance to Improve Chain-of-Thought Faithfulness
by: Swaroop, Anand, et al.
Published: (2025)

A Few Bad Neurons: Isolating and Surgically Correcting Sycophancy
by: O'Brien, Claire, et al.
Published: (2026)

In-Context Environments Induce Evaluation-Awareness in Language Models
by: Chaudhary, Maheep
Published: (2026)

SafetyNet: Detecting Harmful Outputs in LLMs by Modeling and Monitoring Deceptive Behaviors
by: Chaudhary, Maheep, et al.
Published: (2025)

Discovering Transformer Circuits via a Hybrid Attribution and Pruning Framework
by: Gu, Hao, et al.
Published: (2025)

Broken Chains: The Cost of Incomplete Reasoning in LLMs
by: Su, Ian, et al.
Published: (2026)

Evaluating Open-Source Sparse Autoencoders on Disentangling Factual Knowledge in GPT-2 Small
by: Chaudhary, Maheep, et al.
Published: (2024)

MANATEE: Inference-Time Lightweight Diffusion Based Safety Defense for LLMs
by: Kan, Chun Yan Ryan, et al.
Published: (2026)

Identifying and Evaluating Inactive Heads in Pretrained LLMs
by: Sandoval-Segura, Pedro, et al.
Published: (2025)

Urgent Need for Entrepreneurship in the Health Professional Education Curriculum: A Path to Sustainable Healthcare Systems
by: Lukman Raimi
Published: (2025)

PALADIN: Self-Correcting Language Model Agents to Cure Tool-Failure Cases
by: Vuddanti, Sri Vatsa, et al.
Published: (2025)

Modeling and Predicting Multi-Turn Answer Instability in Large Language Models
by: He, Jiahang, et al.
Published: (2025)

Safety Alignment Should Be Made More Than Just a Few Tokens Deep
by: Qi, Xiangyu, et al.
Published: (2024)

Weight space Detection of Backdoors in LoRA Adapters
by: Merenciano, David Puertolas, et al.
Published: (2026)

Beyond Loss Values: Robust Dynamic Pruning via Loss Trajectory Alignment
by: Qin, Huaiyuan, et al.
Published: (2026)

Chopping Trees: Semantic Similarity Based Dynamic Pruning for Tree-of-Thought Reasoning
by: Kim, Joongho, et al.
Published: (2025)

Peek-a-Boo Reasoning: Contrastive Region Masking in MLLMs
by: Chaturvedi, Isha, et al.
Published: (2025)

HiPO: Hierarchical Preference Optimization for Adaptive Reasoning in LLMs
by: Kachroo, Darsh, et al.
Published: (2026)

Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs
by: Afonin, Nikita, 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)

Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs
by: Yun, Vincent-Daniel, et al.
Published: (2026)

Finite-Time Analysis of Three-Timescale Constrained Actor-Critic and Constrained Natural Actor-Critic Algorithms
by: Panda, Prashansa, et al.
Published: (2023)

Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs
by: Panda, Ashwinee, et al.
Published: (2024)

Constrain Alignment with Sparse Autoencoders
by: Yin, Qingyu, et al.
Published: (2024)

Teach LLMs to Phish: Stealing Private Information from Language Models
by: Panda, Ashwinee, et al.
Published: (2024)

Optimizing Chain-of-Thought Confidence via Topological and Dirichlet Risk Analysis
by: More, Abhishek, et al.
Published: (2025)

FedSODA: Federated Fine-tuning of LLMs via Similarity Group Pruning and Orchestrated Distillation Alignment
by: Zhu, Manning, et al.
Published: (2025)

On identity Seidel switches
by: Gervacio, Severino V.
Published: (2026)

Score sequences of bitournaments
by: Gervacio, Severino V.
Published: (2021)

A Fundamental Theorem on Graph Operators
by: Gervacio, Severino V.
Published: (2024)

LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation
by: Zhang, Juzheng, et al.
Published: (2025)

EACO: Enhancing Alignment in Multimodal LLMs via Critical Observation
by: Wang, Yongxin, et al.
Published: (2024)

MemeCLIP: Leveraging CLIP Representations for Multimodal Meme Classification
by: Shah, Siddhant Bikram, et al.
Published: (2024)

Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging
by: Liu, Deyuan, et al.
Published: (2024)

Shared Parameter Subspaces and Cross-Task Linearity in Emergently Misaligned Behavior
by: Arturi, Daniel Aarao Reis, et al.
Published: (2025)

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs
by: Liang, Juhao, et al.
Published: (2024)