| 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 |
| Chinese Toxic Language Mitigation via Sentiment Polarity Consistent Rewrites | May 21, 2025 | Sentence | —Unverified | 0 |
| Adapting Pretrained Language Models for Citation Classification via Self-Supervised Contrastive Learning | May 20, 2025 | Contrastive LearningDecoder | CodeCode Available | 0 |
| SlangDIT: Benchmarking LLMs in Interpretative Slang Translation | May 20, 2025 | BenchmarkingSentence | —Unverified | 0 |
| S2SBench: A Benchmark for Quantifying Intelligence Degradation in Speech-to-Speech Large Language Models | May 20, 2025 | DiagnosticSentence | CodeCode Available | 0 |
| Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation | May 19, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
| Cross-Lingual Representation Alignment Through Contrastive Image-Caption Tuning | May 19, 2025 | Natural Language UnderstandingRetrieval | CodeCode Available | 0 |
| CMLFormer: A Dual Decoder Transformer with Switching Point Learning for Code-Mixed Language Modeling | May 19, 2025 | DecoderLanguage Modeling | —Unverified | 0 |
| Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations | May 19, 2025 | Sentence | —Unverified | 0 |
| To Bias or Not to Bias: Detecting bias in News with bias-detector | May 19, 2025 | Bias DetectionSentence | CodeCode Available | 0 |
