mlsanityData to 7 Oct 2026

The Empty Signifier Problem: Towards Clearer Paradigms for Operationalising "Alignment" in Large Language Models

arXiv 2310.02457 ↗First posted 3 Oct 2023cs.CL cs.CYcited by 7

Not on the map. Why?

Abstract (arXiv)

In this paper, we address the concept of "alignment" in large language models (LLMs) through the lens of post-structuralist socio-political theory, specifically examining its parallels to empty signifiers. To establish a shared vocabulary around how abstract concepts of alignment are operationalised in empirical datasets, we propose a framework that demarcates: 1) which dimensions of model behaviour are considered important, then 2) how meanings and definitions are ascribed to these dimensions, and by whom. We situate existing empirical literature and provide guidance on deciding which paradigm to follow. Through this framework, we aim to foster a culture of transparency and critical evaluation, aiding the community in navigating the complexities of aligning LLMs with human populations.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 48 of its 70 references that are in the map. First posted on arXiv 3 Oct 2023.

Builds on

48 of 70 references.

References · 48

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  3. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  4. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  5. 2020Learning to summarize from human feedbackcited by 2,562
  6. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  7. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
  8. 2018Datasheets for Datasetscited by 1,371
  9. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  10. 2023LIMA: Less Is More for Alignmentcited by 1,080
  11. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,023
  12. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 702
36 more
  1. 2018Annotation Artifacts in Natural Language Inference Datacited by 656
  2. 2022Improving alignment of dialogue agents via targeted human judgementscited by 527
  3. 2023LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Datasetcited by 449
  4. 2020Artificial Intelligence, Values and Alignmentcited by 443
  5. 2018Scalable agent alignment via reward modeling: a research directioncited by 438
  6. 2023LaMP: When Large Language Models Meet Personalizationcited by 425
  7. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Modelscited by 424
  8. 2023Fine-Grained Human Feedback Gives Better Rewards for Language Model Trainingcited by 399
  9. 2018AI safety via debatecited by 384
  10. 2021Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotationscited by 306
  11. 2022Teaching language models to support answers with verified quotescited by 290
  12. 2021Recursively Summarizing Books with Human Feedbackcited by 287
  13. 2021Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detectioncited by 258
  14. 2023Pretraining Language Models with Human Preferencescited by 245
  15. 2022Measuring Progress on Scalable Oversight for Large Language Modelscited by 212
  16. 2022Fine-tuning language models to find agreement among humans with diverse preferencescited by 189
  17. 2021Alignment of Language Agentscited by 167
  18. 2020What Can We Learn from Collective Human Opinions on Natural Language Inference Data?cited by 148
  19. 2021MultiVerS: Improving scientific claim verification with weak supervision and full-document contextcited by 140
  20. 2021On Releasing Annotator-Level Labels and Information in Datasetscited by 123
  21. 2022Jury Learning: Integrating Dissenting Voices into Machine Learning Modelscited by 115
  22. 2020Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligencecited by 100
  23. 2023Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedbackcited by 86
  24. 2023DICES Dataset: Diversity in Conversational AI Evaluation for Safetycited by 86
  25. 2022In conversation with Artificial Intelligence: aligning language models with human valuescited by 61
  26. 2022Training Language Models with Language Feedbackcited by 48
  27. 2022Eliciting and Learning with Soft Labels from Every Annotatorcited by 43
  28. 2022Is one annotation enough? A data-centric image classification benchmark for noisy and ambiguous label estimationcited by 43
  29. 2023Everyone Deserves A Reward: Learning Customized Human Preferencescited by 42
  30. 2023OpinionGPT: Modelling Explicit Biases in Instruction-Tuned LLMscited by 29
  31. 2023Second Thoughts are Best: Learning to Re-Align With Human Values from Text Editscited by 27
  32. 2023Reinforcement Learning from Diverse Human Preferencescited by 24
  33. 2023Learning Personalized Decision Support Policiescited by 13
  34. 2022Towards Boosting the Open-Domain Chatbot with Human Feedbackcited by 11
  35. 2023"Is a picture of a bird a bird": Policy recommendations for dealing with ambiguity in machine vision modelscited by 5
  36. 2018Mimetic vs Anchored Value Alignment in Artificial Intelligencecited by 3

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 3; 2025: 2.

7 papers.

  1. 2024The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Modelscited by 136
  2. 2023The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Valuescited by 53
  3. 2024AI Alignment with Changing and Influenceable Reward Functionscited by 33
  4. 2024Beyond the Binary: Capturing Diverse Preferences With Reward Regularizationcited by 11
  5. 2025SPRI: Aligning Large Language Models with Context-Situated Principlescited by 5
  6. 2023Foundational Moral Values for AI Alignmentcited by 1
  7. 2025From Seed to Harvest: Augmenting Human Creativity with AI for Red-teaming Text-to-Image Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Societal Alignment Frameworks Can Improve LLM Alignment
  2. 2024One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity
  3. 2023The Problem of Alignment
  4. 2025Randomness, Not Representation: The Unreliability of Evaluating Cultural Alignment in LLMs
  5. 2023From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models
  6. 2024From Distributional to Overton Pluralism: Investigating Large Language Model Alignment
  7. 2025Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes
  8. 2026Pressure Reveals Character: Behavioural Alignment Evaluation at Depth