{"total":18,"rows":[{"id":"2410.23771","title":"What is Wrong with Perplexity for Long-context Language Modeling?","created":"2024-10-31","cited_by_count":69,"area":null},{"id":"2403.14541","title":"EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Sampling","created":"2024-03-21","cited_by_count":45,"area":null},{"id":"2106.00941","title":"Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translation","created":"2021-06-02","cited_by_count":17,"area":null},{"id":"2203.09053","title":"Reducing Position Bias in Simultaneous Machine Translation with Length-Aware Framework","created":"2022-03-17","cited_by_count":16,"area":null},{"id":"2305.08706","title":"Understanding and Bridging the Modality Gap for Speech Translation","created":"2023-05-15","cited_by_count":15,"area":null},{"id":"2109.00165","title":"An Unsupervised Method for Building Sentence Simplification Corpora in Multiple Languages","created":"2021-09-01","cited_by_count":14,"area":null},{"id":"2205.12593","title":"Less Learn Shortcut: Analyzing and Mitigating Learning of Spurious Feature-Label Correlation","created":"2022-05-25","cited_by_count":13,"area":null},{"id":"2112.14484","title":"Frequency-Aware Contrastive Learning for Neural Machine Translation","created":"2021-12-29","cited_by_count":11,"area":null},{"id":"2109.03402","title":"Mixup Decoding for Diverse Machine Translation","created":"2021-09-08","cited_by_count":10,"area":null},{"id":"2508.15390","title":"Exploiting Vocabulary Frequency Imbalance in Language Model Pre-training","created":"2025-08-21","cited_by_count":7,"area":null},{"id":"2203.02951","title":"Conditional Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation","created":"2022-03-06","cited_by_count":6,"area":null},{"id":"2105.12523","title":"Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation","created":"2021-05-26","cited_by_count":5,"area":null},{"id":"2212.03230","title":"Switching to Discriminative Image Captioning by Relieving a Bottleneck of Reinforcement Learning","created":"2022-12-06","cited_by_count":4,"area":null},{"id":"2310.15689","title":"Creating a silver standard for patent simplification","created":"2023-10-24","cited_by_count":3,"area":null},{"id":"2506.15021","title":"SFT-GO: Supervised Fine-Tuning with Group Optimization for Large Language Models","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2307.15286","title":"Multilingual Lexical Simplification via Paraphrase Generation","created":"2023-07-28","cited_by_count":1,"area":null},{"id":"2505.07783","title":"Relative Overfitting and Accept-Reject Framework","created":"2025-05-12","cited_by_count":1,"area":null},{"id":"2305.19754","title":"Sentence Simplification Using Paraphrase Corpus for Initialization","created":"2023-05-31","cited_by_count":0,"area":null}],"next_cursor":null}