Elamur Research⌕
☰
home / shelves / Social Sciences / Safety Research / page 3

🤝 Safety Research

168 papers · page 3 of 3 · 126–168 · the most cited first · all shelves

Safety Research is a subfield of Social Sciences in the OpenAlex classification of science. The topics most of its papers here are on: «Ethics and Social Impacts of AI», «Academic integrity and plagiarism», «Disability Rights and Representation».

 Papers

1 2 3

  1. French CrowS-Pairs: Extending a challenge dataset for measuring social bias in masked language models to a language other than EnglishAurélie Névéol, Yoann Dupont, Julien Bezançon, et al.2022 · 107 citations
  2. End-to-End Bias Mitigation by Modelling Biases in CorporaRabeeh Karimi Mahabadi, Yonatan Belinkov, James Henderson2020 · 107 citations
  3. GPT detectors are biased against non-native English writersWeixin Liang, Mert Yuksekgonul, Yining Mao, et al.2023 · 106 citations
  4. Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine TranslationShahar Levy, Koren Lazar, Gabriel Stanovsky2021 · 82 citations
  5. Toward Gender-Inclusive Coreference Resolution: An Analysis of Gender and Bias Throughout the Machine Learning Lifecycle*Yang Trista Cao, Hal Daumé III2021 · 71 citations
  6. FAME: Fictional Actors for Multilingual ErasureClaudio Savelli, Moreno La Quatra, Alkis Koudounas, et al.2026 · 7 citations
  7. A Survey of Plagiarism Detection Systems: Case of Use with English, French and Arabic LanguagesMehdi Abdelhamid, Faical Azouaou, Sofiane Batata2022 · 4 citations
  8. Gender Disambiguation in Machine Translation: Diagnostic Evaluation in Decoder-Only ArchitecturesChiara Manna, Hosein Mohebbi, Afra Alishahi, et al.2026 · 3 citations
  9. Adapting Psycholinguistic Research for LLMs: Gender-inclusive Language in a Coreference ContextMarion Bartl, Thomas Brendan Murphy, Susan Leavy2025 · 3 citations
  10. KZ-SafetyPrompts: A Kazakh Safety Evaluation Prompt Dataset for Large Language ModelsWajdi Zaghouani, Shimaa Amer Ibrahim, Aruzhan Muratbek, et al.2026 · 2 citations
  11. AI Text Detectors and the Misclassification of Slightly Polished Arabic TextSaleh Almohaimeed, Saad Almohaimeed, Mousa Jari, et al.2025 · 2 citations
  12. Roadblocks in Gender Bias Measurement for Diachronic CorporaSaied Alshahrani, Esma Wali, Abdullah R Alshamsan, et al.2022 · 2 citations
  13. AlbanianLLMSafety: A Safety Evaluation Dataset for Large Language Models in AlbanianWajdi Zaghouani, Kholoud Khalil Aldous, Isra Fejzullaj2026 · 1 citation
  14. German General Social Survey Personas: A Survey-Derived Persona Prompt Collection for Population-Aligned LLM StudiesJens Rupprecht, Leon Froehling, Claudia Wagner, et al.2026 · 1 citation
  15. Uncertainty Quantification for Evaluating Gender Bias in Machine TranslationIeva Staliunaite, Julius Cheng, Andreas Vlachos2026 · 1 citation
  16. A Sociophonetic Analysis of Racial Bias in Commercial ASR Systems Using the Pacific Northwest English CorpusMichael Scott, Siyu Liang, Alicia Wassink, et al.2026
  17. ACID: On the Perception of Online ClassismArianna Muti, Elisa Bassignana, Amanda Cercas Curry, et al.2026
  18. AI Safety Lost in Translation: Evaluating the Effectiveness of English-Italian Cross-Lingual LLM Safety AlignmentAlessio Wu, Martim Brandao2026
  19. Annotating Indian Regional Biases using Large Language Models: Evaluation and AnalysisDebasmita Panda, Akash Anil, Neelesh Kumar Shukla2026
  20. AnswerCarefully: Creating a Dataset for LLM Safety in JapaneseHisami Suzuki, Satoru Katsumata, Takashi Kodama, et al.2026
  21. Arabic Safety Alignment as Selective Refusal: An Empirical Study of SFT, DPO, and Guard CalibrationMohamad Zbib, Ammar Mohanna2026
  22. Are Social Biases in LLMs Consistent across Generative Tasks? A Case Study for BasqueMuitze Zulaika, Xabier Saralegi, Julia Shershneva, et al.2026
  23. Auditing Discovery Claims: A Two-Sided Criterion for Agentic Science, with the Negative Side DecidableWenhui Chen, Jianlin Chen, Ziyao Lin, et al.2026
  24. Automating FAIRness: A FAIRification Tool within the Language Resources InfrastructureDaniele Melaccio, Monica Monachini2026
  25. Beyond Cultural Knowledge: Evaluating Arabic Cultural Appropriateness of Large Language ModelsEnes Altinisik, Hamdy Mubarak, Masoomali Fatehkia, et al.2026
  26. Breaking the Benchmark: Revealing LLM Bias via Minimal Contextual AugmentationKaveh Eskandari Miandoab, Mahammed Kamruzzaman, Arshia Gharooni, et al.2026
  27. CANVAS: A Multimodal Dataset of Chinese Textbook Images for Bias and Representation AnalysisHaotian Zhu, Kefan Yu, Min Li2026
  28. Common Sense vs. Morality: The Curious Case of Narrative Focus Bias in LLMsSaugata Purkayastha, Pranav Kushare, Pragya Paramita Pal, et al.2026
  29. Evaluation Drift in LLM Personality Induction: Are We Moving the Goalpost?Prateek Kumar Rajput, Yewei Song, Iyiola Emmanuel Olatunji, et al.2026
  30. Explainable AI for Ethical Counter Speech Generation in Hate Speech MitigationAshiful Islam Ridoy, Mohammed Faisal, Yogesh Kumar, et al.2026
  31. How Far Can Bias Go? Tracing Bias from Pre-Training Data to AlignmentMarion Thaler, Abdullatif Köksal, Alina Leidinger, et al.2026
  32. IndigiEval: Evaluating LLMs in North American Indigenous LanguagesJulia Mainzinger, Jacqueline Brixey2026
  33. Investigating How LLMs Propagate Female Stereotypes: Comparing What Models Say via Prompts with What They Represent in Their EmbeddingsAndrea Valderrey Nuñez, Jelke Bloem2026
  34. Mind the Language Gap: Assessing LLM Safety in ItalianElena Marafatto, Roberto Navigli2026
  35. Persona-Aware Evaluation of Cognitive Bias in LLMs: From Benchmark to Applied Decision-MakingKatsumasa Yoshikawa, Junya Takayama, Takato Yamazaki2026
  36. Quantifying Metric and Model Agreement in Bias Evaluation of Large Language ModelsArash Asgari, Huan Wu, Amirreza Naziri, et al.2026
  37. SalamahBench: Dialect and Category Level Safety Evaluation of Arabic Language ModelsOmar Abdelnasser, Fatemah Alharbi, Khaled Khasawneh, et al.2026
  38. SciCiteVal: A Multi-Domain Dataset for Scientific Citation VerificationQinyue Liu, Yongxin Zhou, Cyril Labbe2026
  39. Towards Reliable AI Fairness: Challenges in Steering Features within Bias-Implicated NeuronsIsmael Garrido-Munoz, Arturo Montejo-Raez, Fernando Martínez-Santiago2026
  40. TryggLLM: A Benchmark for Evaluating LLM Safety in NorwegianSamia Touileb, Truls Pedersen, Isabell Stinessen Haugen2026
  41. Uncovering Hidden Violent Tendencies in LLMs: A Demographic Analysis via Behavioral VignettesQuintin Myers, Yanjun Gao2026
  42. Uncovering Ideological Bias in RAG with Lexical Multidimensional Analysis: A Case Study on COVID-19Elmira Salari, Maria Claudia Nunes Delfino, Hazem Amamou, et al.2026
  43. Whose Pragmatics? Cultural Grounding as a Bottleneck for Stereotype Detection in Egyptian Arabic Social MediaSamar A. Assem2026

1 2 3

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/page/3/