{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1901.08746","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","created":"2019-01-25","cited_by_count":1947},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"1903.10676","title":"SciBERT: A Pretrained Language Model for Scientific Text","created":"2019-03-26","cited_by_count":1414},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"1612.03975","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","created":"2016-12-12","cited_by_count":1067},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"1810.00278","title":"MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling","created":"2018-09-29","cited_by_count":766},{"id":"2002.00388","title":"A Survey on Knowledge Graphs: Representation, Acquisition and Applications","created":"2020-02-02","cited_by_count":643},{"id":"2003.02320","title":"Knowledge Graphs","created":"2020-03-04","cited_by_count":621},{"id":"1705.08045","title":"Learning multiple visual domains with residual adapters","created":"2017-05-22","cited_by_count":557},{"id":"1911.00359","title":"CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data","created":"2019-11-01","cited_by_count":548},{"id":"1811.01241","title":"Wizard of Wikipedia: Knowledge-Powered Conversational agents","created":"2018-11-03","cited_by_count":530},{"id":"2007.07779","title":"AdapterHub: A Framework for Adapting Transformers","created":"2020-07-15","cited_by_count":444},{"id":"2002.01808","title":"K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters","created":"2020-02-05","cited_by_count":319},{"id":"1909.08478","title":"Simple, Scalable Adaptation for Neural Machine Translation","created":"2019-09-18","cited_by_count":242},{"id":"1808.06752","title":"Lessons from Natural Language Inference in the Clinical Domain","created":"2018-08-21","cited_by_count":151},{"id":"2106.03164","title":"On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation","created":"2021-06-06","cited_by_count":147},{"id":"2302.07027","title":"AdapterSoup: Weight Averaging to Improve Generalization of Pretrained Language Models","created":"2023-02-14","cited_by_count":84},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83},{"id":"2211.05994","title":"A Survey of Knowledge Enhanced Pre-trained Language Models","created":"2022-11-11","cited_by_count":76},{"id":"2005.11787","title":"Common Sense or World Knowledge? Investigating Adapter-Based Knowledge Injection into Pretrained Transformers","created":"2020-05-24","cited_by_count":57},{"id":"2007.00655","title":"Knowledge-Aware Language Model Pretraining","created":"2020-06-29","cited_by_count":52},{"id":"2210.00105","title":"A Decade of Knowledge Graphs in Natural Language Processing: A Survey","created":"2022-09-30","cited_by_count":40},{"id":"2010.03746","title":"Infusing Disease Knowledge into BERT for Health Question Answering, Medical Inference and Disease Name Recognition","created":"2020-10-08","cited_by_count":35},{"id":"2108.02340","title":"Robust Transfer Learning with Pretrained Language Models through Adapters","created":"2021-08-05","cited_by_count":35},{"id":"2306.05406","title":"Mixture-of-Domain-Adapters: Decoupling and Injecting Domain Knowledge to Pre-trained Language Models Memories","created":"2023-06-08","cited_by_count":34},{"id":"2110.08455","title":"Knowledge Enhanced Pretrained Language Models: A Compreshensive Survey","created":"2021-10-16","cited_by_count":33},{"id":"2112.08786","title":"Efficient Hierarchical Domain Adaptation for Pretrained Language Models","created":"2021-12-16","cited_by_count":32},{"id":"2006.09174","title":"Results of the seventh edition of the BioASQ Challenge","created":"2020-06-16","cited_by_count":28},{"id":"2101.12294","title":"Combining pre-trained language models and structured knowledge","created":"2021-01-28","cited_by_count":25},{"id":"2102.10233","title":"The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods","created":"2021-02-20","cited_by_count":24},{"id":"2105.06232","title":"Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters","created":"2021-05-13","cited_by_count":23},{"id":"2110.08395","title":"DS-TOD: Efficient Domain Specialization for Task Oriented Dialog","created":"2021-10-15","cited_by_count":21},{"id":"2402.13137","title":"The Hidden Space of Transformer Language Adapters","created":"2024-02-20","cited_by_count":17},{"id":"2109.04810","title":"Mixture-of-Partitions: Infusing Large Biomedical Knowledge Graphs into BERT","created":"2021-09-10","cited_by_count":14},{"id":"2302.01496","title":"Efficient Domain Adaptation for Speech Foundation Models","created":"2023-02-03","cited_by_count":13},{"id":"2204.09883","title":"Layer-wise Fast Adaptation for End-to-End Multi-Accent Speech Recognition","created":"2022-04-21","cited_by_count":12},{"id":"2310.00637","title":"Knowledge Engineering using Large Language Models","created":"2023-10-01","cited_by_count":9},{"id":"2309.15739","title":"Experience and Evidence are the eyes of an excellent summarizer! Towards Knowledge Infused Multi-modal Clinical Conversation Summarization","created":"2023-09-27","cited_by_count":8},{"id":"2306.13467","title":"Incorporating Graph Information in Transformer-based AMR Parsing","created":"2023-06-23","cited_by_count":7},{"id":"2109.06605","title":"MDAPT: Multilingual Domain Adaptive Pretraining in a Single Model","created":"2021-09-14","cited_by_count":6},{"id":"2212.08120","title":"Injecting Domain Knowledge in Language Models for Task-Oriented Dialogue Systems","created":"2022-12-15","cited_by_count":6},{"id":"2305.12717","title":"TADA: Efficient Task-Agnostic Domain Adaptation for Transformers","created":"2023-05-22","cited_by_count":6},{"id":"2012.15421","title":"Verb Knowledge Injection for Multilingual Event Processing","created":"2020-12-31","cited_by_count":3},{"id":"2210.00907","title":"The Effectiveness of Masked Language Modeling and Adapters for Factual Knowledge Injection","created":"2022-10-03","cited_by_count":2},{"id":"1409.5698","title":"The Scientific Competitiveness of Nations","created":"2014-09-19","cited_by_count":1},{"id":"2111.03715","title":"Leveraging Sentiment Analysis Knowledge to Solve Emotion Detection Tasks","created":"2021-11-05","cited_by_count":1}],"next_cursor":null}