| Scaling up COMETKIWI: Unbabel-IST 2023 Submission for the Quality Estimation Shared Task | Sep 21, 2023 | AllSentence | —Unverified | 0 |
| Constraints First: A New MDD-based Model to Generate Sentences Under Constraints | Sep 21, 2023 | Combinatorial OptimizationLanguage Modelling | —Unverified | 0 |
| The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" | Sep 21, 2023 | Data AugmentationSentence | CodeCode Available | 2 |
| SQUARE: Automatic Question Answering Evaluation using Multiple Positive and Negative References | Sep 21, 2023 | Answer SelectionQuestion Answering | —Unverified | 0 |
| A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance | Sep 21, 2023 | Domain GeneralizationKnowledge Distillation | CodeCode Available | 1 |
| Semi-supervised News Discourse Profiling with Contrastive Learning | Sep 20, 2023 | Contrastive LearningSentence | —Unverified | 0 |
| Sentence Attention Blocks for Answer Grounding | Sep 20, 2023 | Question AnsweringSentence | —Unverified | 0 |
| CoT-BERT: Enhancing Unsupervised Sentence Representation through Chain-of-Thought | Sep 20, 2023 | Contrastive LearningDenoising | CodeCode Available | 1 |
| A Hierarchical Neural Framework for Classification and its Explanation in Large Unstructured Legal Documents | Sep 19, 2023 | ClusteringLanguage Modelling | —Unverified | 0 |
| RedPenNet for Grammatical Error Correction: Outputs to Tokens, Attentions to Spans | Sep 19, 2023 | Grammatical Error CorrectionMachine Translation | CodeCode Available | 0 |
