mlsanityData to 7 Oct 2026

Alignment-Enhanced Decoding:Defending via Token-Level Adaptive Refining of Probability Distributions

arXiv 2408.07663 ↗First posted 14 Aug 2024cs.CL cs.AIcited by 2

On the map: LLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks

also in 1 more
Abstract (arXiv)

Large language models are susceptible to jailbreak attacks, which can result in the generation of harmful content. While prior defenses mitigate these risks by perturbing or inspecting inputs, they ignore competing objectives, the underlying cause of alignment failures. In this paper, we propose Alignment-Enhanced Decoding (AED), a novel defense that employs adaptive decoding to address the root causes of jailbreak issues. We first define the Competitive Index to quantify alignment failures and utilize feedback from self-evaluation to compute post-alignment logits. Then, AED adaptively combines AED and post-alignment logits with the original logits to obtain harmless and helpful distributions. Consequently, our method enhances safety alignment while maintaining helpfulness. We conduct experiments across five models and four common jailbreaks, with the results validating the effectiveness of our approach. Code is available at https://github.com/GIGABaozi/AED.git.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Safety alignment and jailbreak attacks, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 29 of its 42 references that are in the map. First posted on arXiv 14 Aug 2024.

Builds on

29 of 42 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States9 Jun
  2. 2023Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations10 Oct
  3. 2023AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models3 Oct
  4. 2023Baseline Defenses for Adversarial Attacks Against Aligned Language Models1 Sep
  5. 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul

Other references · 24

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  5. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  6. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  7. 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,326
  8. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
  9. 2024Gemma: Open Models Based on Gemini Research and Technologycited by 889
  10. 2023Gemini: A Family of Highly Capable Multimodal Modelscited by 810
  11. 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 760
  12. 2023The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Onlycited by 755
12 more
  1. 2020Aligning AI With Shared Human Valuescited by 706
  2. 2022Improving alignment of dialogue agents via targeted human judgementscited by 527
  3. 2023Jailbreaking ChatGPT via Prompt Engineering: An Empirical Studycited by 478
  4. 2023Catastrophic Jailbreak of Open-source LLMs via Exploiting Generationcited by 439
  5. 2023SmoothLLM: Defending Large Language Models Against Jailbreaking Attackscited by 434
  6. 2023Detecting Language Model Attacks with Perplexitycited by 411
  7. 2023A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPTcited by 364
  8. 2023Certifying LLM Safety against Adversarial Promptingcited by 248
  9. 2024SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decodingcited by 233
  10. 2023Fundamental Limitations of Alignment in Large Language Modelscited by 152
  11. 2024PARDEN, Can You Repeat That? Defending against Jailbreaks via Repetitioncited by 29
  12. 2024Protecting Your LLMs with Information Bottleneckcited by 26

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025On Almost Surely Safe Alignment of Large Language Models at Inference-Timecited by 13
  2. 2026JT-SAFE-V2: Safety-by-Design Foundation Model with World-Context Datacited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Jailbreaking LLMs via Calibration
  2. 2026Defending Large Language Models Against Jailbreak Attacks via In-Decoding Safety-Awareness Probing
  3. 2025SABER: Uncovering Vulnerabilities in Safety Alignment via Cross-Layer Residual Connection
  4. 2024Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment
  5. 2024SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance
  6. 2026Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code
  7. 2024Jailbreaking Large Language Models Through Alignment Vulnerabilities in Out-of-Distribution Settings
  8. 2025Decoding One Safety Trigger Token for Balancing Safety and Usability in Large Language Models