mlsanityData to 7 Oct 2026

Ethical and social risks of harm from Language Models

arXiv 2112.04359 ↗First posted 8 Dec 2021cs.CL cs.AI cs.CYcited by 957

Not on the map. Why?

Cited by 131 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

This paper aims to help structure the risk landscape associated with large-scale Language Models (LMs). In order to foster advances in responsible innovation, an in-depth understanding of the potential risks posed by these models is needed. A wide range of established and anticipated risks are analysed in detail, drawing on multidisciplinary expertise and literature from computer science, linguistics, and social sciences. We outline six specific risk areas: I. Discrimination, Exclusion and Toxicity, II. Information Hazards, III. Misinformation Harms, V. Malicious Uses, V. Human-Computer Interaction Harms, VI. Automation, Access, and Environmental Harms. The first area concerns the perpetuation of stereotypes, unfair discrimination, exclusionary norms, toxic language, and lower performance by social group for LMs. The second focuses on risks from private data leaks or LMs correctly inferring sensitive information. The third addresses risks arising from poor, false or misleading information including in sensitive domains, and knock-on risks such as the erosion of trust in shared information. The fourth considers risks from actors who try to use LMs to cause harm. The fifth focuses on risks specific to LLMs used to underpin conversational agents that interact with human users, including unsafe use, manipulation or deception. The sixth discusses the risk of environmental harm, job automation, and other challenges that may have a disparate effect on different social groups or communities. In total, we review 21 risks in-depth. We discuss the points of origin of different risks and point to potential mitigation approaches. Lastly, we discuss organisational responsibilities in implementing mitigations, and the role of collaboration and participation. We highlight directions for further research, particularly on expanding the toolkit for assessing and evaluating the outlined risks in LMs.

Key facts. Cited by 957 papers in the map (data through 7 Oct 2026). Builds on 70 of its 279 references that are in the map. First posted on arXiv 8 Dec 2021.

Builds on

70 of 279 references.

References · 70

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  5. 2016Deep Learning with Differential Privacycited by 2,682
  6. 2020Extracting Training Data from Large Language Modelscited by 2,144
  7. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  8. 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,718
  9. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  10. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,242
  11. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  12. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 951
38 more
  1. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 911
  2. 2016Semantics derived automatically from language corpora contain human-like biasescited by 894
  3. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  4. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 789
  5. 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Modelscited by 703
  6. 2021Carbon Emissions and Large Neural Network Trainingcited by 561
  7. 2019Defending Against Neural Fake Newscited by 553
  8. 2019Release Strategies and the Social Impacts of Language Modelscited by 505
  9. 2021Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpuscited by 481
  10. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
  11. 2020Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditingcited by 380
  12. 2018Analysis Methods in Neural Language Processing: A Surveycited by 276
  13. 2019Measuring Bias in Contextualized Word Representationscited by 275
  14. 2021ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generationcited by 258
  15. 2016A Network-based End-to-End Trainable Task-oriented Dialogue Systemcited by 252
  16. 2021Quality at a Glance: An Audit of Web-Crawled Multilingual Datasetscited by 241
  17. 2019Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Flycited by 240
  18. 2019Gender Bias in Contextualized Word Embeddingscited by 203
  19. 2017Deal or No Deal? End-to-End Learning for Negotiation Dialoguescited by 202
  20. 2021Societal Biases in Language Generation: Progress and Challengescited by 201
  21. 2016Demographic Dialectal Variation in Social Media: A Case Study of African-American Englishcited by 194
  22. 2021Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasetscited by 179
  23. 2021Challenges in Detoxifying Language Modelscited by 169
  24. 2020Automatic Detection of Machine Generated Text: A Critical Surveycited by 160
  25. 2021Understanding the Capabilities, Limitations, and Societal Impact of Large Language Modelscited by 159
  26. 2018The Frontiers of Fairness in Machine Learningcited by 139
  27. 2020Towards Accountability for Machine Learning Datasets: Practices from Software Engineering and Infrastructurecited by 138
  28. 2019Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overviewcited by 137
  29. 2020Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasetscited by 137
  30. 2020A Distributional Approach to Controlled Text Generationcited by 117
  31. 2019Lessons from Archives: Strategies for Collecting Sociocultural Data in Machine Learningcited by 116
  32. 2021Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learnerscited by 115
  33. 2020UNKs Everywhere: Adapting Multilingual Language Models to New Scriptscited by 113
  34. 2020Participation is not a Design Fix for Machine Learningcited by 110
  35. 2021Detoxifying Language Models Risks Marginalizing Minority Voicescited by 106
  36. 2021Re-imagining Algorithmic Fairness in India and Beyondcited by 102
  37. 2020Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligencecited by 100
  38. 2021Language Models are Few-shot Multilingual Learnerscited by 92

50 most cited of 70 All 70 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 105; 2023: 215; 2024: 268; 2025: 209; 2026: 159.

957 papers.

Sort:

By area:

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  4. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  5. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  6. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  7. 2022Emergent Abilities of Large Language Modelscited by 2,483
  8. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,928
  9. 2022Large Language Models Encode Clinical Knowledgecited by 1,807
  10. 2025Gemma 3 Technical Reportcited by 1,686
  11. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  12. 2022Competition-Level Code Generation with AlphaCodecited by 1,427
38 more
  1. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  2. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,339
  3. 2022LaMDA: Language Models for Dialog Applicationscited by 1,218
  4. 2023PaLM 2 Technical Reportcited by 1,154
  5. 2022Red Teaming Language Models with Language Modelscited by 983
  6. 2023BloombergGPT: A Large Language Model for Financecited by 923
  7. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 837
  8. 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Datasetcited by 828
  9. 2022A Generalist Agentcited by 802
  10. 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 760
  11. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 743
  12. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 733
  13. 2023OpenAssistant Conversations -- Democratizing Large Language Model Alignmentcited by 712
  14. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 702
  15. 2023Safe RLHF: Safe Reinforcement Learning from Human Feedbackcited by 630
  16. 2022Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Modelcited by 557
  17. 2022Improving alignment of dialogue agents via targeted human judgementscited by 527
  18. 2024WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMscited by 460
  19. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Modelscited by 424
  20. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 394
  21. 2023Scaling Data-Constrained Language Modelscited by 391
  22. 2023Towards Expert-Level Medical Question Answering with Large Language Modelscited by 382
  23. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 380
  24. 2023Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructionscited by 377
  25. 2023SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compressioncited by 359
  26. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 351
  27. 2022A Holistic Approach to Undesired Content Detection in the Real Worldcited by 337
  28. 2023Explainability for Large Language Models: A Surveycited by 331
  29. 2022Teaching language models to support answers with verified quotescited by 290
  30. 2023Low-Resource Languages Jailbreak GPT-4cited by 290
  31. 2023Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystackcited by 278
  32. 2024A Survey on Knowledge Distillation of Large Language Modelscited by 276
  33. 2024Knowledge Conflicts for LLMs: A Surveycited by 274
  34. 2023ToolQA: A Dataset for LLM Question Answering with External Toolscited by 273
  35. 2023Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attackscited by 268
  36. 2022Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scalecited by 262
  37. 2023Provable Robust Watermarking for AI-Generated Textcited by 259
  38. 2022Prompting GPT-3 To Be Reliablecited by 258

50 most cited of 957 All 957 (JSON)