---
title: "Safety Research — papers, page 3"
description: "Safety Research: 168 papers of the Elamur Research library · page 3 of 3 · 126–168, the most cited first — our summary of each, its ideas, references and…"
canonical: "https://research.elamur.ai/free/en/shelves/social-sciences/safety-research/page/3/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/shelves/social-sciences/safety-research/page/3/)

[home](https://md.research.elamur.ai/free/en/) / [shelves](https://md.research.elamur.ai/free/en/shelves/) / [Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) / [Safety Research](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/) / page 3

# 🤝 Safety Research

168 papers · page 3 of 3 · 126–168 · the most cited first · [all shelves](https://md.research.elamur.ai/free/en/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

[← prev](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/page/2/) [1](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/) [2](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/page/2/) **3**

126. [**French CrowS-Pairs: Extending a challenge dataset for measuring social bias in masked language models to a language other than English**Aurélie Névéol, Yoann Dupont, Julien Bezançon, et al.*2022 · 107 citations*](https://md.research.elamur.ai/free/en/papers/neveol-2022-french-crows-pairs-extending-challenge/)
127. [**End-to-End Bias Mitigation by Modelling Biases in Corpora**Rabeeh Karimi Mahabadi, Yonatan Belinkov, James Henderson*2020 · 107 citations*](https://md.research.elamur.ai/free/en/papers/mahabadi-2020-end-end-bias-mitigation-modelling/)
128. [**GPT detectors are biased against non-native English writers**Weixin Liang, Mert Yuksekgonul, Yining Mao, et al.*2023 · 106 citations*](https://md.research.elamur.ai/free/en/papers/liang-2023-gpt-detectors-biased-against-non/)
129. [**Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation**Shahar Levy, Koren Lazar, Gabriel Stanovsky*2021 · 82 citations*](https://md.research.elamur.ai/free/en/papers/levy-2021-collecting-large-scale-gender-bias/)
130. [**Toward Gender-Inclusive Coreference Resolution: An Analysis of Gender and Bias Throughout the Machine Learning Lifecycle***Yang Trista Cao, Hal Daumé III*2021 · 71 citations*](https://md.research.elamur.ai/free/en/papers/cao-2021-gender-inclusive-coreference-resolution-analysis/)
131. [**FAME: Fictional Actors for Multilingual Erasure**Claudio Savelli, Moreno La Quatra, Alkis Koudounas, et al.*2026 · 7 citations*](https://md.research.elamur.ai/free/en/papers/savelli-2026-fame-fictional-actors-multilingual-erasure/)
132. [**A Survey of Plagiarism Detection Systems: Case of Use with English, French and Arabic Languages**Mehdi Abdelhamid, Faical Azouaou, Sofiane Batata*2022 · 4 citations*](https://md.research.elamur.ai/free/en/papers/abdelhamid-2022-survey-plagiarism-detection-systems-case/)
133. [**Gender Disambiguation in Machine Translation: Diagnostic Evaluation in Decoder-Only Architectures**Chiara Manna, Hosein Mohebbi, Afra Alishahi, et al.*2026 · 3 citations*](https://md.research.elamur.ai/free/en/papers/manna-2026-gender-disambiguation-machine-translation-diagnostic/)
134. [**Adapting Psycholinguistic Research for LLMs: Gender-inclusive Language in a Coreference Context**Marion Bartl, Thomas Brendan Murphy, Susan Leavy*2025 · 3 citations*](https://md.research.elamur.ai/free/en/papers/bartl-2025-adapting-psycholinguistic-research-llms-gender/)
135. [**KZ-SafetyPrompts: A Kazakh Safety Evaluation Prompt Dataset for Large Language Models**Wajdi Zaghouani, Shimaa Amer Ibrahim, Aruzhan Muratbek, et al.*2026 · 2 citations*](https://md.research.elamur.ai/free/en/papers/zaghouani-2026-kz-safetyprompts-kazakh-safety-evaluation/)
136. [**AI Text Detectors and the Misclassification of Slightly Polished Arabic Text**Saleh Almohaimeed, Saad Almohaimeed, Mousa Jari, et al.*2025 · 2 citations*](https://md.research.elamur.ai/free/en/papers/almohaimeed-2025-ai-text-detectors-misclassification-slightly/)
137. [**Roadblocks in Gender Bias Measurement for Diachronic Corpora**Saied Alshahrani, Esma Wali, Abdullah R Alshamsan, et al.*2022 · 2 citations*](https://md.research.elamur.ai/free/en/papers/alshahrani-2022-roadblocks-gender-bias-measurement-diachronic/)
138. [**AlbanianLLMSafety: A Safety Evaluation Dataset for Large Language Models in Albanian**Wajdi Zaghouani, Kholoud Khalil Aldous, Isra Fejzullaj*2026 · 1 citation*](https://md.research.elamur.ai/free/en/papers/zaghouani-2026-albanianllmsafety-safety-evaluation-dataset-large/)
139. [**German General Social Survey Personas: A Survey-Derived Persona Prompt Collection for Population-Aligned LLM Studies**Jens Rupprecht, Leon Froehling, Claudia Wagner, et al.*2026 · 1 citation*](https://md.research.elamur.ai/free/en/papers/rupprecht-2026-german-general-social-survey-personas/)
140. [**Uncertainty Quantification for Evaluating Gender Bias in Machine Translation**Ieva Staliunaite, Julius Cheng, Andreas Vlachos*2026 · 1 citation*](https://md.research.elamur.ai/free/en/papers/staliunaite-2026-uncertainty-quantification-evaluating-gender-bias/)
141. [**A Sociophonetic Analysis of Racial Bias in Commercial ASR Systems Using the Pacific Northwest English Corpus**Michael Scott, Siyu Liang, Alicia Wassink, et al.*2026*](https://md.research.elamur.ai/free/en/papers/scott-2026-sociophonetic-analysis-racial-bias-commercial/)
142. [**ACID: On the Perception of Online Classism**Arianna Muti, Elisa Bassignana, Amanda Cercas Curry, et al.*2026*](https://md.research.elamur.ai/free/en/papers/muti-2026-acid-perception-online-classism/)
143. [**AI Safety Lost in Translation: Evaluating the Effectiveness of English-Italian Cross-Lingual LLM Safety Alignment**Alessio Wu, Martim Brandao*2026*](https://md.research.elamur.ai/free/en/papers/wu-2026-ai-safety-lost-translation-evaluating/)
144. [**Annotating Indian Regional Biases using Large Language Models: Evaluation and Analysis**Debasmita Panda, Akash Anil, Neelesh Kumar Shukla*2026*](https://md.research.elamur.ai/free/en/papers/panda-2026-annotating-indian-regional-biases-large/)
145. [**AnswerCarefully: Creating a Dataset for LLM Safety in Japanese**Hisami Suzuki, Satoru Katsumata, Takashi Kodama, et al.*2026*](https://md.research.elamur.ai/free/en/papers/suzuki-2026-answercarefully-creating-dataset-llm-safety/)
146. [**Arabic Safety Alignment as Selective Refusal: An Empirical Study of SFT, DPO, and Guard Calibration**Mohamad Zbib, Ammar Mohanna*2026*](https://md.research.elamur.ai/free/en/papers/zbib-2026-arabic-safety-alignment-selective-refusal/)
147. [**Are Social Biases in LLMs Consistent across Generative Tasks? A Case Study for Basque**Muitze Zulaika, Xabier Saralegi, Julia Shershneva, et al.*2026*](https://md.research.elamur.ai/free/en/papers/zulaika-2026-are-social-biases-llms-consistent/)
148. [**Auditing Discovery Claims: A Two-Sided Criterion for Agentic Science, with the Negative Side Decidable**Wenhui Chen, Jianlin Chen, Ziyao Lin, et al.*2026*](https://md.research.elamur.ai/free/en/papers/chen-2026-auditing-discovery-claims-two/)
149. [**Automating FAIRness: A FAIRification Tool within the Language Resources Infrastructure**Daniele Melaccio, Monica Monachini*2026*](https://md.research.elamur.ai/free/en/papers/melaccio-2026-automating-fairness-fairification-tool-within/)
150. [**Beyond Cultural Knowledge: Evaluating Arabic Cultural Appropriateness of Large Language Models**Enes Altinisik, Hamdy Mubarak, Masoomali Fatehkia, et al.*2026*](https://md.research.elamur.ai/free/en/papers/altinisik-2026-cultural-knowledge-evaluating-arabic-cultural/)
151. [**Breaking the Benchmark: Revealing LLM Bias via Minimal Contextual Augmentation**Kaveh Eskandari Miandoab, Mahammed Kamruzzaman, Arshia Gharooni, et al.*2026*](https://md.research.elamur.ai/free/en/papers/miandoab-2026-breaking-benchmark-revealing-llm-bias/)
152. [**CANVAS: A Multimodal Dataset of Chinese Textbook Images for Bias and Representation Analysis**Haotian Zhu, Kefan Yu, Min Li*2026*](https://md.research.elamur.ai/free/en/papers/zhu-2026-canvas-multimodal-dataset-chinese-textbook/)
153. [**Common Sense vs. Morality: The Curious Case of Narrative Focus Bias in LLMs**Saugata Purkayastha, Pranav Kushare, Pragya Paramita Pal, et al.*2026*](https://md.research.elamur.ai/free/en/papers/purkayastha-2026-common-sense-vs-morality-curious/)
154. [**Evaluation Drift in LLM Personality Induction: Are We Moving the Goalpost?**Prateek Kumar Rajput, Yewei Song, Iyiola Emmanuel Olatunji, et al.*2026*](https://md.research.elamur.ai/free/en/papers/rajput-2026-evaluation-drift-llm-personality-induction/)
155. [**Explainable AI for Ethical Counter Speech Generation in Hate Speech Mitigation**Ashiful Islam Ridoy, Mohammed Faisal, Yogesh Kumar, et al.*2026*](https://md.research.elamur.ai/free/en/papers/ridoy-2026-explainable-ai-ethical-counter-speech/)
156. [**How Far Can Bias Go? Tracing Bias from Pre-Training Data to Alignment**Marion Thaler, Abdullatif Köksal, Alina Leidinger, et al.*2026*](https://md.research.elamur.ai/free/en/papers/thaler-2026-how-far-can-bias-go/)
157. [**IndigiEval: Evaluating LLMs in North American Indigenous Languages**Julia Mainzinger, Jacqueline Brixey*2026*](https://md.research.elamur.ai/free/en/papers/mainzinger-2026-indigieval-evaluating-llms-north-american/)
158. [**Investigating How LLMs Propagate Female Stereotypes: Comparing What Models Say via Prompts with What They Represent in Their Embeddings**Andrea Valderrey Nuñez, Jelke Bloem*2026*](https://md.research.elamur.ai/free/en/papers/nunez-2026-investigating-how-llms-propagate-female/)
159. [**Mind the Language Gap: Assessing LLM Safety in Italian**Elena Marafatto, Roberto Navigli*2026*](https://md.research.elamur.ai/free/en/papers/marafatto-2026-mind-language-gap-assessing-llm/)
160. [**Persona-Aware Evaluation of Cognitive Bias in LLMs: From Benchmark to Applied Decision-Making**Katsumasa Yoshikawa, Junya Takayama, Takato Yamazaki*2026*](https://md.research.elamur.ai/free/en/papers/yoshikawa-2026-persona-aware-evaluation-cognitive-bias/)
161. [**Quantifying Metric and Model Agreement in Bias Evaluation of Large Language Models**Arash Asgari, Huan Wu, Amirreza Naziri, et al.*2026*](https://md.research.elamur.ai/free/en/papers/asgari-2026-quantifying-metric-model-agreement-bias/)
162. [**SalamahBench: Dialect and Category Level Safety Evaluation of Arabic Language Models**Omar Abdelnasser, Fatemah Alharbi, Khaled Khasawneh, et al.*2026*](https://md.research.elamur.ai/free/en/papers/abdelnasser-2026-salamahbench-dialect-category-level-safety/)
163. [**SciCiteVal: A Multi-Domain Dataset for Scientific Citation Verification**Qinyue Liu, Yongxin Zhou, Cyril Labbe*2026*](https://md.research.elamur.ai/free/en/papers/liu-2026-sciciteval-multi-domain-dataset-scientific/)
164. [**Towards Reliable AI Fairness: Challenges in Steering Features within Bias-Implicated Neurons**Ismael Garrido-Munoz, Arturo Montejo-Raez, Fernando Martínez-Santiago*2026*](https://md.research.elamur.ai/free/en/papers/munoz-2026-reliable-ai-fairness-challenges-steering/)
165. [**TryggLLM: A Benchmark for Evaluating LLM Safety in Norwegian**Samia Touileb, Truls Pedersen, Isabell Stinessen Haugen*2026*](https://md.research.elamur.ai/free/en/papers/touileb-2026-tryggllm-benchmark-evaluating-llm-safety/)
166. [**Uncovering Hidden Violent Tendencies in LLMs: A Demographic Analysis via Behavioral Vignettes**Quintin Myers, Yanjun Gao*2026*](https://md.research.elamur.ai/free/en/papers/myers-2026-uncovering-hidden-violent-tendencies-llms/)
167. [**Uncovering Ideological Bias in RAG with Lexical Multidimensional Analysis: A Case Study on COVID-19**Elmira Salari, Maria Claudia Nunes Delfino, Hazem Amamou, et al.*2026*](https://md.research.elamur.ai/free/en/papers/salari-2026-uncovering-ideological-bias-rag-lexical/)
168. [**Whose Pragmatics? Cultural Grounding as a Bottleneck for Stereotype Detection in Egyptian Arabic Social Media**Samar A. Assem*2026*](https://md.research.elamur.ai/free/en/papers/assem-2026-whose-pragmatics-cultural-grounding-as/)

[← prev](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/page/2/) [1](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/) [2](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/page/2/) **3**