| BanglaQuAD: A Bengali Open-domain Question Answering Dataset | Oct 14, 2024 | ArticlesOpen-Domain Question Answering | —Unverified | 0 |
| Jailbreak Instruction-Tuned LLMs via end-of-sentence MLP Re-weighting | Oct 14, 2024 | Sentence | —Unverified | 0 |
| Multilingual Controlled Generation And Gold-Standard-Agnostic Evaluation of Code-Mixed Sentences | Oct 14, 2024 | SentenceText Generation | —Unverified | 0 |
| LoRE: Logit-Ranked Retriever Ensemble for Enhancing Open-Domain Question Answering | Oct 13, 2024 | Answer GenerationLanguage Modeling | —Unverified | 0 |
| Empowering Dysarthric Speech: Leveraging Advanced LLMs for Accurate Speech Correction and Multimodal Emotion Analysis | Oct 13, 2024 | Emotion RecognitionSentence | —Unverified | 0 |
| Extended Japanese Commonsense Morality Dataset with Masked Token and Label Enhancement | Oct 12, 2024 | Language ModellingLarge Language Model | —Unverified | 0 |
| Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP | Oct 11, 2024 | Few-Shot Image Classificationimage-classification | —Unverified | 0 |
| Guidelines for Fine-grained Sentence-level Arabic Readability Annotation | Oct 11, 2024 | BenchmarkingSentence | —Unverified | 0 |
| Integrating Supertag Features into Neural Discontinuous Constituent Parsing | Oct 11, 2024 | ChunkingDependency Parsing | CodeCode Available | 0 |
| MELO: An Evaluation Benchmark for Multilingual Entity Linking of Occupations | Oct 10, 2024 | Entity LinkingSentence | CodeCode Available | 0 |
