mlsanityData to 7 Oct 2026

"You are grounded!": Latent Name Artifacts in Pre-trained Language Models

arXiv 2004.03012 ↗First posted 6 Apr 2020cs.CLcited by 39

Not on the map. Why?

Abstract (arXiv)

Pre-trained language models (LMs) may perpetuate biases originating in their training corpus to downstream models. We focus on artifacts associated with the representation of given names (e.g., Donald), which, depending on the corpus, may be associated with specific entities, as indicated by next token prediction (e.g., Trump). While helpful in some contexts, grounding happens also in under-specified or inappropriate contexts. For example, endings generated for `Donald is a' substantially differ from those of other names, and often have more-than-average negative sentiment. We demonstrate the potential effect on downstream tasks with reading comprehension probes where name perturbation changes the model answers. As a silver lining, our experiments suggest that additional pre-training on different corpora may mitigate this bias.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 10; 2023: 8; 2024: 5; 2025: 3; 2026: 2.

39 papers.

Sort:

By area:

  1. 2021Entity-Based Knowledge Conflicts in Question Answeringcited by 349
  2. 2021Societal Biases in Language Generation: Progress and Challengescited by 201
  3. 2021Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Basescited by 107
  4. 2023Language Model Behavior: A Comprehensive Surveycited by 92
  5. 2022Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?cited by 89
  6. 2021On Measures of Biases and Harms in NLPcited by 81
  7. 2022Prompted Opinion Summarization with GPT-3.5cited by 44
  8. 2021Uncovering Implicit Gender Bias in Narratives through Commonsense Inferencecited by 32
  9. 2021Detecting Cross-Geographic Biases in Toxicity Modeling on Social Mediacited by 31
  10. 2021Evaluating Entity Disambiguation and the Role of Popularity in Retrieval-Based NLPcited by 30
  11. 2024Do Large Language Models Discriminate in Hiring Decisions on the Basis of Race, Ethnicity, and Gender?cited by 24
  12. 2022SODAPOP: Open-Ended Discovery of Social Biases in Social Commonsense Reasoning Modelscited by 22
27 more
  1. 2024Stop! In the Name of Flaws: Disentangling Personal Names and Sociodemographic Attributes in NLPcited by 22
  2. 2021Rewire-then-Probe: A Contrastive Recipe for Probing Biomedical Knowledge of Pre-trained Language Modelscited by 21
  3. 2025Presumed Cultural Identity: How Names Shape LLM Responsescited by 21
  4. 2021On the Robustness of Reading Comprehension Models to Entity Renamingcited by 17
  5. 2021Quantifying Gender Bias Towards Politicians in Cross-Lingual Language Modelscited by 15
  6. 2023Nichelle and Nancy: The Influence of Demographic Attributes and Tokenization Length on First Name Biasescited by 12
  7. 2025The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societiescited by 12
  8. 2022JASMINE: Arabic GPT Models for Few-Shot Learningcited by 11
  9. 2023"One-Size-Fits-All"? Examining Expectations around What Constitute "Fair" or "Good" NLG System Behaviorscited by 11
  10. 2024What makes a good metric? Evaluating automatic metrics for text-to-image consistencycited by 11
  11. 2021Probing Pre-trained Auto-regressive Language Models for Named Entity Typing and Recognitioncited by 10
  12. 2022Challenges and Opportunities in Information Manipulation Detection: An Examination of Wartime Russian Mediacited by 10
  13. 2024WinoPron: Revisiting English Winogender Schemas for Consistency, Coverage, and Grammatical Casecited by 9
  14. 2023Examining the Causal Effect of First Names on Language Models: The Case of Social Commonsense Reasoningcited by 8
  15. 2022Richer Countries and Richer Representationscited by 7
  16. 2022An Analysis of the Effects of Decoding Algorithms on Fairness in Open-Ended Language Generationcited by 7
  17. 2023Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyondcited by 7
  18. 2023Counter-GAP: Counterfactual Bias Evaluation through Gendered Ambiguous Pronounscited by 5
  19. 2023"Im not Racist but...": Discovering Bias in the Internal Knowledge of Large Language Modelscited by 5
  20. 2022Identifying and Measuring Token-Level Sentiment Bias in Pre-trained Language Models with Promptscited by 4
  21. 2025On the Mutual Influence of Gender and Occupation in LLM Representationscited by 4
  22. 2022Does Entity Abstraction Help Generative Transformers Reason?cited by 3
  23. 2022Multilingual Coreference Resolution in Multiparty Dialoguecited by 2
  24. 2023Reducing Sensitivity on Speaker Names for Text Generation from Dialoguescited by 1
  25. 2026Quantifying Gender Bias in Large Language Models: When ChatGPT Becomes a Hiring Managercited by 1
  26. 2024On the Influence of Gender and Race in Romantic Relationship Prediction from Large Language Modelscited by 0
  27. 2026Who Gets a Token, and What Does It Carry? Unequal Name Support and Concept Access in Large Language Modelscited by 0