{"total":41,"rows":[{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401,"area":null},{"id":"2303.03915","title":"The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset","created":"2023-03-07","cited_by_count":148,"area":null},{"id":"2102.05766","title":"Fused Acoustic and Text Encoding for Multimodal Bilingual Pretraining and Speech Translation","created":"2021-02-10","cited_by_count":47,"area":null},{"id":"2110.05841","title":"Relative Molecule Self-Attention Transformer","created":"2021-10-12","cited_by_count":21,"area":null},{"id":"2106.03720","title":"Person Re-Identification with a Locally Aware Transformer","created":"2021-06-07","cited_by_count":19,"area":null},{"id":"2104.08942","title":"Attention-based Clinical Note Summarization","created":"2021-04-18","cited_by_count":16,"area":null},{"id":"2112.14869","title":"Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity","created":"2021-12-30","cited_by_count":11,"area":null},{"id":"2104.08110","title":"LU-BZU at SemEval-2021 Task 2: Word2Vec and Lemma2Vec performance in Arabic Word-in-Context disambiguation","created":"2021-04-16","cited_by_count":9,"area":null},{"id":"2106.05903","title":"Deciphering Implicit Hate: Evaluating Automated Detection Algorithms for Multimodal Hate","created":"2021-06-10","cited_by_count":8,"area":null},{"id":"2502.11269","title":"Unlocking the Potential of Generative AI through Neuro-Symbolic Architectures: Benefits and Limitations","created":"2025-02-16","cited_by_count":6,"area":null},{"id":"2102.00238","title":"ShufText: A Simple Black Box Approach to Evaluate the Fragility of Text Classification Models","created":"2021-01-30","cited_by_count":5,"area":null},{"id":"2207.02724","title":"Pre-training Transformers for Molecular Property Prediction Using Reaction Prediction","created":"2022-07-06","cited_by_count":5,"area":null},{"id":"2412.01233","title":"Best Practices for Large Language Models in Radiology","created":"2024-12-02","cited_by_count":5,"area":null},{"id":"2305.13297","title":"Investigating the Role of Feed-Forward Networks in Transformers Using Parallel Attention and Feed-Forward Net Design","created":"2023-05-22","cited_by_count":4,"area":null},{"id":"2404.01317","title":"Intelligent Learning Rate Distribution to reduce Catastrophic Forgetting in Transformers","created":"2024-03-27","cited_by_count":4,"area":null},{"id":"2404.01492","title":"Modality Translation for Object Detection Adaptation Without Forgetting Prior Knowledge","created":"2024-04-01","cited_by_count":4,"area":null},{"id":"2110.09393","title":"Ceasing hate withMoH: Hate Speech Detection in Hindi-English Code-Switched Language","created":"2021-10-18","cited_by_count":3,"area":null},{"id":"2411.16694","title":"Reaction-conditioned De Novo Enzyme Design with GENzyme","created":"2024-11-10","cited_by_count":3,"area":null},{"id":"2412.13478","title":"Efficient Fine-Tuning of Single-Cell Foundation Models Enables Zero-Shot Molecular Perturbation Prediction","created":"2024-12-18","cited_by_count":3,"area":null},{"id":"2412.20357","title":"HindiLLM: Large Language Model for Hindi","created":"2024-12-29","cited_by_count":3,"area":null},{"id":"2103.11792","title":"Comparing the Performance of NLP Toolkits and Evaluation measures in Legal Tech","created":"2021-03-12","cited_by_count":2,"area":null},{"id":"2108.10127","title":"Legal Search in Case Law and Statute Law","created":"2021-08-23","cited_by_count":2,"area":null},{"id":"2310.02790","title":"Low Resource Summarization using Pre-trained Language Models","created":"2023-10-04","cited_by_count":2,"area":null},{"id":"2104.06439","title":"Zhestyatsky at SemEval-2021 Task 2: ReLU over Cosine Similarity for BERT Fine-tuning","created":"2021-04-13","cited_by_count":1,"area":null},{"id":"2104.09644","title":"Neural Language Models with Distant Supervision to Identify Major Depressive Disorder from Clinical Notes","created":"2021-04-19","cited_by_count":1,"area":null},{"id":"2109.06436","title":"YES SIR!Optimizing Semantic Space of Negatives with Self-Involvement Ranker","created":"2021-09-14","cited_by_count":1,"area":null},{"id":"2110.02852","title":"Pretrained Transformers for Offensive Language Identification in Tanglish","created":"2021-10-06","cited_by_count":1,"area":null},{"id":"2308.08807","title":"Linguistically-Informed Neural Architectures for Lexical, Syntactic and Semantic Tasks in Sanskrit","created":"2023-08-17","cited_by_count":1,"area":null},{"id":"2410.19184","title":"No Argument Left Behind: Overlapping Chunks for Faster Processing of Arbitrarily Long Legal Texts","created":"2024-10-24","cited_by_count":1,"area":null},{"id":"2603.26671","title":"Mitigating Forgetting in Continual Learning with Selective Gradient Projection","created":"2026-02-08","cited_by_count":1,"area":null},{"id":"2606.00340","title":"Balancing Learning Rates Across Layers: Exact Two-Step Dynamics and Optimal Scaling in Linear Neural Networks","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2608.18279","title":"A Comprehensive Review of Large Language Models for Nanophotonics: From Surrogate Modeling to Autonomous Design","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2205.03153","title":"Bridging the Domain Gap for Stance Detection for the Zulu language","created":"2022-05-06","cited_by_count":0,"area":null},{"id":"2209.04041","title":"Multilingual Transformer Language Model for Speech Recognition in Low-resource Languages","created":"2022-09-08","cited_by_count":0,"area":null},{"id":"2212.14206","title":"Maximizing Use-Case Specificity through Precision Model Tuning","created":"2022-12-29","cited_by_count":0,"area":null},{"id":"2411.08563","title":"Leveraging LLMs for Predictive Insights in Food Policy and Behavioral Interventions","created":"2024-11-13","cited_by_count":0,"area":null},{"id":"2501.00608","title":"Optimizing Speech-Input Length for Speaker-Independent Depression Classification","created":"2024-12-31","cited_by_count":0,"area":null},{"id":"2505.17704","title":"SemSketches-2021: experimenting with the machine processing of the pilot semantic sketches corpus","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2510.16604","title":"Fine-tuning of Large Language Models for Constituency Parsing Using a Sequence to Sequence Approach","created":"2025-10-18","cited_by_count":0,"area":null},{"id":"2605.14055","title":"PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2607.23925","title":"Greedy dynamical meta-learning","created":"2026-07-27","cited_by_count":0,"area":null}],"next_cursor":null}