{"list":"other","total":62,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"1809.05053","title":"XNLI: Evaluating Cross-lingual Sentence Representations","created":"2018-09-13","cited_by_count":915},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"2007.01852","title":"Language-agnostic BERT Sentence Embedding","created":"2020-07-03","cited_by_count":627},{"id":"2210.03057","title":"Language Models are Multilingual Chain-of-Thought Reasoners","created":"2022-10-06","cited_by_count":530},{"id":"2102.01454","title":"MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers","created":"2021-02-02","cited_by_count":470},{"id":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454},{"id":"2207.00032","title":"DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale","created":"2022-06-30","cited_by_count":407},{"id":"2310.18018","title":"NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark","created":"2023-10-27","cited_by_count":348},{"id":"2005.00333","title":"XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning","created":"2020-05-01","cited_by_count":333},{"id":"2308.16884","title":"The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants","created":"2023-08-31","cited_by_count":311},{"id":"2304.08177","title":"Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca","created":"2023-04-17","cited_by_count":305},{"id":"2112.10668","title":"Few-shot Learning with Multilingual Language Models","created":"2021-12-20","cited_by_count":278},{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263},{"id":"2303.10420","title":"A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models","created":"2023-03-18","cited_by_count":246},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229},{"id":"2312.11514","title":"LLM in a flash: Efficient Large Language Model Inference with Limited Memory","created":"2023-12-12","cited_by_count":177},{"id":"2104.07412","title":"XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation","created":"2021-04-15","cited_by_count":168},{"id":"2110.07814","title":"Meta-learning via Language Model In-context Tuning","created":"2021-10-15","cited_by_count":164},{"id":"2103.11811","title":"MasakhaNER: Named Entity Recognition for African Languages","created":"2021-03-22","cited_by_count":155},{"id":"2204.07580","title":"mGPT: Few-Shot Learners Go Multilingual","created":"2022-04-15","cited_by_count":142},{"id":"2305.12182","title":"Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages","created":"2023-05-20","cited_by_count":116},{"id":"2401.01055","title":"LLaMA Beyond English: An Empirical Study on Language Capability Transfer","created":"2024-01-02","cited_by_count":95},{"id":"2109.07684","title":"Language Models are Few-shot Multilingual Learners","created":"2021-09-16","cited_by_count":92},{"id":"2204.08110","title":"Language Contamination Helps Explain the Cross-lingual Capabilities of English Pretrained Models","created":"2022-04-17","cited_by_count":92},{"id":"2305.15011","title":"Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank Adaptation","created":"2023-05-24","cited_by_count":81},{"id":"2401.01854","title":"Multilingual Instruction Tuning With Just a Pinch of Multilinguality","created":"2024-01-03","cited_by_count":73},{"id":"2305.05940","title":"Multilingual LLMs are Better Cross-lingual In-context Learners with Alignment","created":"2023-05-10","cited_by_count":71},{"id":"2307.06018","title":"PolyLM: An Open Source Polyglot Large Language Model","created":"2023-07-12","cited_by_count":64},{"id":"2305.10266","title":"Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM's Translation Capability","created":"2023-05-17","cited_by_count":62},{"id":"2303.08119","title":"How Many Demonstrations Do You Need for In-context Learning?","created":"2023-03-14","cited_by_count":52},{"id":"2107.00676","title":"A Primer on Pretrained Multilingual Language Models","created":"2021-07-01","cited_by_count":49},{"id":"2311.07978","title":"AfroBench: How Good are Large Language Models on African Languages?","created":"2023-11-14","cited_by_count":43},{"id":"2306.15091","title":"Understanding In-Context Learning via Supportive Pretraining Data","created":"2023-06-26","cited_by_count":41},{"id":"2310.16248","title":"GlotLID: Language Identification for Low-Resource Languages","created":"2023-10-24","cited_by_count":39},{"id":"2312.12683","title":"Turning English-centric LLMs Into Polyglots: How Much Multilinguality Is Needed?","created":"2023-12-20","cited_by_count":39},{"id":"2305.11938","title":"XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages","created":"2023-05-19","cited_by_count":34},{"id":"2211.03831","title":"Multi-Head Adapter Routing for Cross-Task Generalization","created":"2022-11-07","cited_by_count":33},{"id":"2401.13303","title":"MaLA-500: Massive Language Adaptation of Large Language Models","created":"2024-01-24","cited_by_count":28},{"id":"2306.13421","title":"Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrieval","created":"2023-06-23","cited_by_count":20},{"id":"2307.14031","title":"Multi3WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems","created":"2023-07-26","cited_by_count":16},{"id":"2212.10455","title":"MULTI3NLU++: A Multilingual, Multi-Intent, Multi-Domain Dataset for Natural Language Understanding in Task-Oriented Dialogue","created":"2022-12-20","cited_by_count":15},{"id":"2204.02123","title":"Improved and Efficient Conversational Slot Labeling through Question Answering","created":"2022-04-05","cited_by_count":10},{"id":"2204.13021","title":"NLU++: A Multi-Label, Slot-Rich, Generalisable Dataset for Natural Language Understanding in Task-Oriented Dialogue","created":"2022-04-27","cited_by_count":8},{"id":"2310.12892","title":"A Systematic Study of Performance Disparities in Multilingual Task-Oriented Dialogue Systems","created":"2023-10-19","cited_by_count":4},{"id":"2311.09502","title":"SQATIN: Supervised Instruction Tuning Meets Question Answering for Improved Dialogue NLU","created":"2023-11-16","cited_by_count":3}],"next_cursor":null}