mlsanityData to 7 Oct 2026

A Roadmap for Robust End-to-End Alignment

arXiv 1809.01036 ↗First posted 4 Sep 2018cs.AIcited by 0

On the map: LLM alignment / RLHF / preference optimisation → LLM preference optimization methods

Abstract (arXiv)

This paper discussed the it robust alignment problem, that is, the problem of aligning the goals of algorithms with human preferences. It presented a general roadmap to tackle this issue. Interestingly, this roadmap identifies 5 critical steps, as well as many relevant aspects of these 5 steps. In other words, we have presented a large number of hopefully more tractable subproblems that readers are highly encouraged to tackle. Hopefully, this combination allows to better highlight the most pressing problems, how every expertise can be best used to, and how combining the solutions to subproblems might add up to solve robust alignment.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 27 of its 112 references that are in the map. First posted on arXiv 4 Sep 2018.

Builds on

27 of 112 references.

References · 27

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  4. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  5. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  6. 2016Concrete Problems in AI Safetycited by 1,582
  7. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  8. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  9. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
  10. 2017One pixel attack for fooling deep neural networkscited by 579
  11. 2018The Hidden Vulnerability of Distributed Learning in Byzantiumcited by 324
  12. 2016Cooperative Inverse Reinforcement Learningcited by 298
15 more
  1. 2016Safety Verification of Deep Neural Networkscited by 262
  2. 2018Categorizing Variants of Goodhart's Lawcited by 132
  3. 2018A Dual Approach to Scalable Verification of Deep Networkscited by 125
  4. 2017AI Safety Gridworldscited by 108
  5. 2016The Off-Switch Gamecited by 97
  6. 2016Research Priorities for Robust and Beneficial Artificial Intelligencecited by 74
  7. 2017A Voting-Based System for Ethical Decision Makingcited by 55
  8. 2015Learning the Preferences of Ignorant, Inconsistent Agentscited by 45
  9. 2017When Will AI Exceed Human Performance? Evidence from AI Expertscited by 41
  10. 2017Pragmatic-Pedagogic Value Alignmentcited by 36
  11. 2018A Game-Based Approximate Verification of Deep Neural Networks with Provable Guaranteescited by 33
  12. 2017Context-Aware Generative Adversarial Privacycited by 27
  13. 2016Death and Suicide in Universal Artificial Intelligencecited by 9
  14. 2018Asynchronous Byzantine Machine Learning (the case of SGD)cited by 7
  15. 2017Dynamic Safe Interruptibility for Decentralized Multi-Agent Reinforcement Learningcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025The Differences Between Direct Alignment Algorithms are a Blur
  2. 2024A Practical Analysis of Human Alignment with *PO
  3. 2024On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models
  4. 2024MAP: Multi-Human-Value Alignment Palette
  5. 2025OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment
  6. 2026Revisiting Robustness for LLM Safety Alignment via Selective Geometry Control
  7. 2024Systematic Evaluation of LLM-as-a-Judge in LLM Alignment Tasks: Explainable Metrics and Diverse Prompt Templates
  8. 2025Alignment Data Map for Efficient Preference Data Selection and Diagnosis