Image de couverture de livre

Representation Surgery: Theory and Practice of Affine Steering

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Singh, Shashwat, Ravfogel, Shauli, Herzig, Jonathan, Aharoni, Roee, Cotterell, Ryan, Kumaraguru, Ponnurangam
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Computation and Language Computers and Society
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A Practical Method for Generating String Counterfactuals
par: Avitan, Matan, et autres
Publié: (2024)

Log-linear Guardedness and its Implications
par: Ravfogel, Shauli, et autres
Publié: (2022)

LEACE: Perfect linear concept erasure in closed form
par: Belrose, Nora, et autres
Publié: (2023)

Kernelized Concept Erasure
par: Ravfogel, Shauli, et autres
Publié: (2022)

Linear Adversarial Concept Erasure
par: Ravfogel, Shauli, et autres
Publié: (2022)

Gumbel Counterfactual Generation From Language Models
par: Ravfogel, Shauli, et autres
Publié: (2024)

On Affine Homotopy between Language Encoders
par: Chan, Robin SM, et autres
Publié: (2024)

Exploring the Linear Subspace Hypothesis in Gender Bias Mitigation
par: Vargas, Francisco, et autres
Publié: (2020)

What if I ask in \textit{alia lingua}? Measuring Functional Similarity Across Languages
par: Mishra, Debangan, et autres
Publié: (2025)

BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models
par: Ben-Zaken, Elad, et autres
Publié: (2021)

Multilingual Instruction Tuning With Just a Pinch of Multilinguality
par: Shaham, Uri, et autres
Publié: (2024)

Diversity Over Quantity: A Lesson From Few Shot Relation Classification
par: Cohen, Amir DN, et autres
Publié: (2024)

CAFIN: Centrality Aware Fairness inducing IN-processing for Unsupervised Representation Learning on Graphs
par: Arun, Arvindh, et autres
Publié: (2023)

Rethinking Thinking Tokens: Understanding Why They Underperform in Practice
par: Vennam, Sreeram, et autres
Publié: (2024)

Measuring Moral Inconsistencies in Large Language Models
par: Bonagiri, Vamshi Krishna, et autres
Publié: (2024)

Sometimes the Model doth Preach: Quantifying Religious Bias in Open LLMs through Demographic Analysis in Asian Nations
par: Shankar, Hari, et autres
Publié: (2025)

Unintended Impacts of LLM Alignment on Global Representation
par: Ryan, Michael J., et autres
Publié: (2024)

The Role of Language Imbalance in Cross-lingual Generalisation: Insights from Cloned Language Experiments
par: Schäfer, Anton, et autres
Publié: (2024)

Description-Based Text Similarity
par: Ravfogel, Shauli, et autres
Publié: (2023)

DRAGged into Conflicts: Detecting and Addressing Conflicting Sources in Search-Augmented LLMs
par: Cattan, Arie, et autres
Publié: (2025)

DSO: Direct Steering Optimization for Bias Mitigation
par: Paes, Lucas Monteiro, et autres
Publié: (2025)

White-Box Sensitivity Auditing with Steering Vectors
par: Cyberey, Hannah, et autres
Publié: (2026)

Causal Reasoning Favors Encoders: On The Limits of Decoder-Only Models
par: Roy, Amartya, et autres
Publié: (2025)

LLM Vocabulary Compression for Low-Compute Environments
par: Vennam, Sreeram, et autres
Publié: (2024)

On the Representational Capacity of Recurrent Neural Language Models
par: Nowak, Franz, et autres
Publié: (2023)

Wu's Method can Boost Symbolic AI to Rival Silver Medalists and AlphaGeometry to Outperform Gold Medalists at IMO Geometry
par: Sinha, Shiven, et autres
Publié: (2024)

Mind the Gap: Pitfalls of LLM Alignment with Asian Public Opinion
par: Shankar, Hari, et autres
Publié: (2026)

Enhancing AI Safety Through the Fusion of Low Rank Adapters
par: Gudipudi, Satya Swaroop, et autres
Publié: (2024)

Great Models Think Alike and this Undermines AI Oversight
par: Goel, Shashwat, et autres
Publié: (2025)

Activation Steering via Generative Causal Mediation
par: Sankaranarayanan, Aruna, et autres
Publié: (2026)

Multilingual Non-Factoid Question Answering with Answer Paragraph Selection
par: Mishra, Ritwik, et autres
Publié: (2024)

Are Models Trained on Indian Legal Data Fair?
par: Girhepuje, Sahil, et autres
Publié: (2023)

Just KIDDIN: Knowledge Infusion and Distillation for Detection of INdecent Memes
par: Garg, Rahul, et autres
Publié: (2024)

Extending Activation Steering to Broad Skills and Multiple Behaviours
par: van der Weij, Teun, et autres
Publié: (2024)

Flying Pigs, FaR and Beyond: Evaluating LLM Reasoning in Counterfactual Worlds
par: Joishy, Anish R, et autres
Publié: (2025)

Interpreting Latent Student Knowledge Representations in Programming Assignments
par: Fernandez, Nigel, et autres
Publié: (2024)

Fair Representation in Parliamentary Summaries: Measuring and Mitigating Inclusion Bias
par: Cunningham, Eoghan, et autres
Publié: (2025)

Exploring Knowledge Tracing in Tutor-Student Dialogues using LLMs
par: Scarlatos, Alexander, et autres
Publié: (2024)

SoK: Machine Learning for Misinformation Detection
par: Xiao, Madelyne, et autres
Publié: (2023)

Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information
par: Iskander, Shadi, et autres
Publié: (2024)