{"total":28,"rows":[{"id":"2411.00860","title":"Survey of Cultural Awareness in Language Models: Text and Beyond","created":"2024-10-30","cited_by_count":103,"area":null},{"id":"2407.03129","title":"Social Bias Evaluation for Large Language Models Requires Prompt Variations","created":"2024-07-03","cited_by_count":40,"area":null},{"id":"2503.06987","title":"Social Bias Benchmark for Generation: A Comparison of Generation and QA-Based Evaluations","created":"2025-03-10","cited_by_count":16,"area":null},{"id":"2508.15830","title":"DAIQ: Auditing Demographic Attribute Inference from Question in LLMs","created":"2025-08-18","cited_by_count":10,"area":null},{"id":"2502.19965","title":"Deterministic or probabilistic? The psychology of LLMs as random number generators","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2508.07090","title":"BharatBBQ: A Multilingual Bias Benchmark for Question Answering in the Indian Context","created":"2025-08-09","cited_by_count":6,"area":null},{"id":"2412.14050","title":"Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2503.06011","title":"Intent-Aware Self-Correction for Mitigating Social Biases in Large Language Models","created":"2025-03-08","cited_by_count":5,"area":null},{"id":"2508.10186","title":"PakBBQ: A Culturally Adapted Bias Benchmark for QA","created":"2025-08-13","cited_by_count":4,"area":null},{"id":"2511.13368","title":"Donors and Recipients: On Asymmetric Transfer Across Tasks and Languages with Parameter-Efficient Fine-Tuning","created":"2025-11-17","cited_by_count":4,"area":null},{"id":"2510.05678","title":"Gradual Code-Switching as Inference-Time Cross-Lingual Representational Alignment for LLMs","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2509.24468","title":"Bias Mitigation or Cultural Commonsense? Evaluating LLMs with a Japanese Dataset","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2603.08182","title":"TildeOpen LLM: Leveraging Curriculum Learning to Achieve Equitable Language Representation","created":"2026-03-09","cited_by_count":2,"area":null},{"id":"2507.11216","title":"EsBBQ and CaBBQ: The Spanish and Catalan Bias Benchmarks for Question Answering","created":"2025-07-15","cited_by_count":1,"area":null},{"id":"2507.16410","title":"GG-BBQ: German Gender Bias Benchmark for Question Answering","created":"2025-07-22","cited_by_count":1,"area":null},{"id":"2510.04641","title":"Evaluating LLMs for Demographic-Targeted Social Bias Detection: A Comprehensive Benchmark Study","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2512.16029","title":"Cross-Language Bias Examination in Large Language Models","created":"2025-12-17","cited_by_count":1,"area":null},{"id":"2601.12033","title":"Preserving Fairness and Safety in Quantized LLMs Through Critical Weight Protection","created":"2026-01-17","cited_by_count":1,"area":null},{"id":"2607.07895","title":"Scalable and Culturally Specific Stereotype Dataset Construction via Human-LLM Collaboration","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2607.21063","title":"QuantiBias: Benchmarking Quantization-Induced Bias in LLMs","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2607.28801","title":"Benchmarks Are Not Monolithic: Sample-Level Auditing and Orchestration for LLM Evaluation","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2601.16803","title":"SoS: Analysis of Surface over Semantics in Multilingual Text-To-Image Generation","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2605.10442","title":"StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2606.00596","title":"Toward Responsible and Epistemically Grounded Multilingual LLMs for Computational Social Science and Humanities","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2608.09925","title":"From Values to Benchmarks: Evaluating Large Language Models for Governmental Use in Dutch","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.02651","title":"WinoQueer-NL: Assessing Bias in Dutch Language Models toward LGBTQ+ Identities","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.18649","title":"DyMT-ESB: Dynamic Multi-Turn Evaluation of Social Bias in User-LLM Interactions","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.25298","title":"FineWeb-CLaR: Culture, Language, and Region Annotations for Benchmark-Aligned Corpus Auditing","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}