Cover Image

Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Deshpande, Vijeta, Giyahchi, Tootiya, Padmanabhan, Veena, Akoglu, Leman, Rumshisky, Anna
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Rethinking Evaluation for LLM Hallucination Detection: A Desiderata, A New RAG-based Benchmark, New Insights
by: Chen, Wenbo, et al.
Published: (2026)

Emergent Abilities in Reduced-Scale Generative Language Models
by: Muckatira, Sherin, et al.
Published: (2024)

Beyond Perplexity: A Geometric and Spectral Study of Low-Rank Pre-Training
by: Shivagunde, Namrata, et al.
Published: (2026)

Diverse, not Short: A Length-Controlled Data Selection Strategy for Improving Response Diversity of Language Models
by: Deshpande, Vijeta, et al.
Published: (2025)

A Pre-Training Analogue of Grokking in Language Models: Tracing Delayed Grammatical Generalization
by: Muckatira, Sherin, et al.
Published: (2026)

A Penalty Goes a Long Way: Measuring Lexical Diversity in Synthetic Texts Under Prompt-Influenced Length Variations
by: Deshpande, Vijeta, et al.
Published: (2025)

Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning
by: Lialin, Vladislav, et al.
Published: (2023)

Outlier Detection Bias Busted: Understanding Sources of Algorithmic Bias through Data-centric Factors
by: Ding, Xueying, et al.
Published: (2024)

Self-Tuning Self-Supervised Image Anomaly Detection
by: Yoo, Jaemin, et al.
Published: (2023)

LocalTweets to LocalHealth: A Mental Health Surveillance Framework Based on Twitter Data
by: Deshpande, Vijeta, et al.
Published: (2024)

Hierarchical Token Prepending: Enhancing Information Flow in Decoder-based LLM Embeddings
by: Ding, Xueying, et al.
Published: (2025)

Structured Prompt Optimization Meets Reinforcement Learning for Global and Local Interpretability over Complex Text
by: Zhou, Tianyang, et al.
Published: (2026)

Toward Privileged Foundation Models:LUPI for Accelerated and Improved Learning
by: Ding, Xueying, et al.
Published: (2026)

Pard: Permutation-Invariant Autoregressive Diffusion for Graph Generation
by: Zhao, Lingxiao, et al.
Published: (2024)

Adapting Decoder-Based Language Models for Diverse Encoder Downstream Tasks
by: Suganthan, Paul, et al.
Published: (2025)

Steering Language Models With Activation Engineering
by: Turner, Alexander Matt, et al.
Published: (2023)

Synthetic vs. Gold: The Role of LLM Generated Labels and Data in Cyberbullying Detection
by: Kazemi, Arefeh, et al.
Published: (2025)

Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention
by: Jin, Zehao, et al.
Published: (2026)

HyperSteer: Activation Steering at Scale with Hypernetworks
by: Sun, Jiuding, et al.
Published: (2025)

FoMo-0D: A Foundation Model for Zero-shot Tabular Outlier Detection
by: Shen, Yuchen, et al.
Published: (2024)

Playing with Words, Improving with Rewards: Training Language Models for Creative Association
by: Deshpande, Vijeta, et al.
Published: (2026)

Activation Steering via Generative Causal Mediation
by: Sankaranarayanan, Aruna, et al.
Published: (2026)

SteeringSafety: A Systematic Safety Evaluation Framework of Representation Steering in LLMs
by: Siu, Vincent, et al.
Published: (2025)

Steer Like the LLM: Activation Steering that Mimics Prompting
by: Heyman, Geert, et al.
Published: (2026)

ROAST: Rollout-based On-distribution Activation Steering Technique
by: Su, Xuanbo, et al.
Published: (2026)

Unified Discrete Diffusion for Categorical Data
by: Zhao, Lingxiao, et al.
Published: (2024)

CoBAD: Modeling Collective Behaviors for Human Mobility Anomaly Detection
by: Wen, Haomin, et al.
Published: (2025)

The Power of LLM-Generated Synthetic Data for Stance Detection in Online Political Discussions
by: Wagner, Stefan Sylvius, et al.
Published: (2024)

Spherical Steering: Geometry-Aware Activation Rotation for Language Models
by: You, Zejia, et al.
Published: (2026)

Guiding Giants: Lightweight Controllers for Weighted Activation Steering in LLMs
by: Hegazy, Amr, et al.
Published: (2025)

Steering MoE LLMs via Expert (De)Activation
by: Fayyaz, Mohsen, et al.
Published: (2025)

VIP-COP: Context Optimization for Tabular Foundation Models
by: Chen, Yilong, et al.
Published: (2026)

Prompt Perturbation Consistency Learning for Robust Language Models
by: Qiang, Yao, et al.
Published: (2024)

From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier Detection
by: Ding, Xueying, et al.
Published: (2026)

Programming Refusal with Conditional Activation Steering
by: Lee, Bruce W., et al.
Published: (2024)

SAKE: Steering Activations for Knowledge Editing
by: Scialanga, Marco, et al.
Published: (2025)

Understanding How CodeLLMs (Mis)Predict Types with Activation Steering
by: Lucchetti, Francesca, et al.
Published: (2024)

Exploring the Impact of a Transformer's Latent Space Geometry on Downstream Task Performance
by: Marbut, Anna C., et al.
Published: (2024)

Out-of-Distribution Detection using Synthetic Data Generation
by: Abbas, Momin, et al.
Published: (2025)

FishBack: Pullback Fisher Geometry for Optimal Activation Steering in Transformers
by: Wang, Sihan, et al.
Published: (2026)