mlsanityData to 14 Oct 2026

Reflections and New Directions for Human-Centered Large Language Models

arXiv 2605.06901 ↗First posted 7 May 2026cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) are increasingly shaping the private and professional lives of users, with numerous applications in business, education, finance, healthcare, law, and science. With this rise in global influence comes greater urgency to build, evaluate, and deploy these systems in a manner that prioritizes not only technical capabilities but also human priorities. This work presents a framework for developing Human-Centered Large Language Models (HCLLMs), which integrates perspectives from Natural Language Processing (NLP), Human-Computer Interaction (HCI), and responsible AI. Considering the ethics, economics, and technical objectives of language modeling, we argue that model developers need to address human concerns, preferences, values, and goals, not only during a cursory post-training stage, but rather with rigor and care at every stage of the pipeline. This paper offers human-centered insights and recommendations for developers at each stage, from system design to data sourcing, model training, evaluation, and responsible deployment. Then we conclude with a case study, applying these insights to understand the future of work with HCLLMs.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 245 of its 759 references that are in the map. First posted on arXiv 7 May 2026.

Builds on

245 of 759 references.

References · 245

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  4. 2020Scaling Laws for Neural Language Modelscited by 6,586
  5. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  6. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  7. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  8. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  9. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  10. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  11. 2022Training Compute-Optimal Large Language Modelscited by 3,019
  12. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
38 more
  1. 2020Learning to summarize from human feedbackcited by 2,588
  2. 2023A Survey of Large Language Modelscited by 2,576
  3. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,411
  4. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,998
  5. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,984
  6. 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,420
  7. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,336
  8. 2023A Survey on Evaluation of Large Language Modelscited by 1,242
  9. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,207
  10. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,202
  11. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,055
  12. 2021Ethical and social risks of harm from Language Modelscited by 966
  13. 2023Steering Language Models With Activation Engineeringcited by 922
  14. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 886
  15. 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 832
  16. 2023The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Onlycited by 763
  17. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 759
  18. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debatecited by 742
  19. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 729
  20. 2023Measuring Faithfulness in Chain-of-Thought Reasoningcited by 703
  21. 2023Instruction Tuning with GPT-4cited by 686
  22. 2024LLM Evaluators Recognize and Favor Their Own Generationscited by 686
  23. 2023Tree of Attacks: Jailbreaking Black-Box LLMs Automaticallycited by 672
  24. 2023Safe RLHF: Safe Reinforcement Learning from Human Feedbackcited by 656
  25. 2024How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMscited by 573
  26. 2023Textbooks Are All You Needcited by 569
  27. 2024Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingcited by 529
  28. 2024Large Language Models: A Surveycited by 525
  29. 2023Reinforced Self-Training (ReST) for Language Modelingcited by 500
  30. 2024Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Researchcited by 483
  31. 2024LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methodscited by 465
  32. 2023RRHF: Rank Responses to Align Language Models with Human Feedback without tearscited by 463
  33. 2023Catastrophic Jailbreak of Open-source LLMs via Exploiting Generationcited by 451
  34. 2018Scalable agent alignment via reward modeling: a research directioncited by 447
  35. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Modelscited by 437
  36. 2025HealthBench: Evaluating Large Language Models Towards Improved Human Healthcited by 429
  37. 2023Who's Harry Potter? Approximate Unlearning in LLMscited by 381
  38. 2022Self-critiquing models for assisting human evaluatorscited by 380

50 most cited of 245 All 245 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026LKValues: Aligning Large Language Models with Sri Lankan Societal Valuescited by 1
  2. 2026Talking with Language Modelscited by 0