mlsanityData to 7 Oct 2026

Adversarial Representation Engineering: A General Model Editing Framework for Large Language Models

arXiv 2404.13752 ↗First posted 21 Apr 2024cs.LG cs.AI cs.CLcited by 12

Not on the map. Why?

Abstract (arXiv)

Since the rapid development of Large Language Models (LLMs) has achieved remarkable success, understanding and rectifying their internal complex mechanisms has become an urgent issue. Recent research has attempted to interpret their behaviors through the lens of inner representation. However, developing practical and efficient methods for applying these representations for general and flexible model editing remains challenging. In this work, we explore how to leverage insights from representation engineering to guide the editing of LLMs by deploying a representation sensor as an editing oracle. We first identify the importance of a robust and reliable sensor during editing, then propose an Adversarial Representation Engineering (ARE) framework to provide a unified and interpretable approach for conceptual model editing without compromising baseline performance. Experiments on multiple tasks demonstrate the effectiveness of ARE in various model editing scenarios. Our code and data are available at https://github.com/Zhang-Yihao/Adversarial-Representation-Engineering.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 46 of its 63 references that are in the map. First posted on arXiv 21 Apr 2024.

Builds on

46 of 63 references.

References · 46

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  6. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  7. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  8. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  9. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  10. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  11. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  12. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,259
34 more
  1. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,106
  2. 2024DoRA: Weight-Decomposed Low-Rank Adaptationcited by 740
  3. 2023AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Modelscited by 738
  4. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  5. 2023The Internal State of an LLM Knows When It's Lyingcited by 644
  6. 2018Texygen: A Benchmarking Platform for Text Generation Modelscited by 484
  7. 2020MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfercited by 443
  8. 2023Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrationscited by 401
  9. 2023DeepInception: Hypnotize Large Language Model to Be Jailbreakercited by 337
  10. 2023Explainability for Large Language Models: A Surveycited by 331
  11. 2023Finding Neurons in a Haystack: Case Studies with Sparse Probingcited by 328
  12. 2023Shadow Alignment: The Ease of Subverting Safely-Aligned Language Modelscited by 284
  13. 2023Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessmentcited by 227
  14. 2024Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modificationscited by 220
  15. 2023Evaluating the Performance of Large Language Models on GAOKAO Benchmarkcited by 182
  16. 2023How Robust is Google's Bard to Adversarial Image Attacks?cited by 177
  17. 2020Compositional Explanations of Neuronscited by 172
  18. 2020Robust Pre-Training by Adversarial Contrastive Learningcited by 144
  19. 2020Feature Purification: How Adversarial Training Performs Robust Deep Learningcited by 107
  20. 2022Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generationcited by 90
  21. 2023Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanationscited by 90
  22. 2023Rethinking Model Ensemble in Transfer-based Adversarial Attackscited by 88
  23. 2023Alleviating Hallucinations of Large Language Models through Induced Hallucinationscited by 78
  24. 2023Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimismcited by 69
  25. 2024Fight Back Against Jailbreaking via Prompt Adversarial Tuningcited by 63
  26. 2024Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapescited by 63
  27. 2023CFA: Class-wise Calibrated Fair Adversarial Trainingcited by 53
  28. 2023Sequential Integrated Gradients: a simple but effective method for explaining language modelscited by 52
  29. 2018Domain Adversarial Training for Accented Speech Recognitioncited by 40
  30. 2022Robust Models are less Over-Confidentcited by 25
  31. 2024On the Duality Between Sharpness-Aware Minimization and Adversarial Trainingcited by 24
  32. 2023Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustnesscited by 20
  33. 2021Straight to the Gradient: Learning to Use Novel Tokens for Neural Text Generationcited by 19
  34. 2023ArCL: Enhancing Contrastive Learning with Augmentation-Robust Representationscited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 6; 2026: 3.

12 papers.

  1. 2024Can Knowledge Editing Really Correct Hallucinations?cited by 28
  2. 2025Advancing LLM Safe Alignment with Safety Representation Rankingcited by 15
  3. 2025Unveiling the Basin-Like Loss Landscape in Large Language Modelscited by 13
  4. 2025Towards the Worst-case Robustness of Large Language Modelscited by 7
  5. 2025Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Promptscited by 5
  6. 2024Investigating Representation Universality: Case Study on Genealogical Representationscited by 4
  7. 2025Efficient LLM Moderation with Multi-Layer Latent Prototypescited by 4
  8. 2024Iter-AHMCL: Alleviate Hallucination for Large Language Model via Iterative Model-level Contrastive Learningcited by 2
  9. 2025Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinationscited by 2
  10. 2026To Defend Against Cyber Attacks, We Must Teach AI Agents to Hackcited by 1
  11. 2026The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systemscited by 1
  12. 2026Epistemic-Probabilistic Model for Guarded Multi-Agent LLM Coordinationcited by 0