| Internal and External Impacts of Natural Language Processing Papers | May 21, 2025 | ArticlesEthics | —Unverified | 0 |
| Cultural Value Alignment in Large Language Models: A Prompt-based Analysis of Schwartz Values in Gemini, ChatGPT, and DeepSeek | May 21, 2025 | Fairness | —Unverified | 0 |
| Evaluate Bias without Manual Test Sets: A Concept Representation Perspective for LLMs | May 21, 2025 | DiagnosticFairness | —Unverified | 0 |
| Are the confidence scores of reviewers consistent with the review content? Evidence from top conference proceedings in AI | May 21, 2025 | Deep LearningFairness | CodeCode Available | 0 |
| Mitigating Subgroup Disparities in Multi-Label Speech Emotion Recognition: A Pseudo-Labeling and Unsupervised Learning Approach | May 20, 2025 | Emotion RecognitionFairness | —Unverified | 0 |
| Enforcing Hard Linear Constraints in Deep Learning Models with Decision Rules | May 20, 2025 | Fairness | —Unverified | 0 |
| Explaining Neural Networks with Reasons | May 20, 2025 | Fairness | CodeCode Available | 0 |
| DECASTE: Unveiling Caste Stereotypes in Large Language Models through Multi-Dimensional Bias Analysis | May 20, 2025 | BenchmarkingFairness | —Unverified | 0 |
| Unlearning Algorithmic Biases over Graphs | May 20, 2025 | FairnessNode Classification | —Unverified | 0 |
| Algorithmic Hiring and Diversity: Reducing Human-Algorithm Similarity for Better Outcomes | May 20, 2025 | DiversityFairness | —Unverified | 0 |
