{"list":"other","total":84,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1704.04368","title":"Get To The Point: Summarization with Pointer-Generator Networks","created":"2017-04-14","cited_by_count":1292},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"1508.04025","title":"Effective Approaches to Attention-based Neural Machine Translation","created":"2015-08-17","cited_by_count":1026},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"2308.10144","title":"ExpeL: LLM Agents Are Experiential Learners","created":"2023-08-20","cited_by_count":876},{"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":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"id":"2002.08910","title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","created":"2020-02-10","cited_by_count":719},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"1303.5778","title":"Speech Recognition with Deep Recurrent Neural Networks","created":"2013-03-22","cited_by_count":669},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623},{"id":"1909.02622","title":"MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance","created":"2019-09-05","cited_by_count":418},{"id":"2104.14478","title":"Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation","created":"2021-04-29","cited_by_count":338},{"id":"2211.02001","title":"Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model","created":"2022-11-03","cited_by_count":265},{"id":"1706.09254","title":"The E2E Dataset: New Challenges For End-to-End Generation","created":"2017-06-28","cited_by_count":253},{"id":"1511.06391","title":"Order Matters: Sequence to sequence for sets","created":"2015-11-19","cited_by_count":237},{"id":"1707.08052","title":"Challenges in Data-to-Document Generation","created":"2017-07-25","cited_by_count":226},{"id":"1703.09902","title":"Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation","created":"2017-03-29","cited_by_count":206},{"id":"2304.04370","title":"OpenAGI: When LLM Meets Domain Experts","created":"2023-04-10","cited_by_count":197},{"id":"2007.02871","title":"DART: Open-Domain Structured Data Record to Text Generation","created":"2020-07-06","cited_by_count":145},{"id":"1508.01745","title":"Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems","created":"2015-08-07","cited_by_count":134},{"id":"1503.02364","title":"Neural Responding Machine for Short-Text Conversation","created":"2015-03-09","cited_by_count":124},{"id":"1805.06087","title":"Learning to Write with Cooperative Discriminators","created":"2018-05-16","cited_by_count":119},{"id":"1906.01081","title":"Handling Divergent Reference Texts when Evaluating Table-to-Text Generation","created":"2019-06-03","cited_by_count":119},{"id":"2306.04723","title":"Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts","created":"2023-06-07","cited_by_count":112},{"id":"2008.09036","title":"Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queries","created":"2020-08-20","cited_by_count":107},{"id":"1809.00582","title":"Data-to-Text Generation with Content Selection and Planning","created":"2018-09-03","cited_by_count":106},{"id":"2305.13144","title":"Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline","created":"2023-05-22","cited_by_count":86},{"id":"2309.14393","title":"LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models","created":"2023-09-25","cited_by_count":72},{"id":"2307.03025","title":"Style Over Substance: Evaluation Biases for Large Language Models","created":"2023-07-06","cited_by_count":70},{"id":"1910.08684","title":"Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation","created":"2019-10-19","cited_by_count":62},{"id":"2305.00955","title":"Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation","created":"2023-05-01","cited_by_count":55},{"id":"1711.09724","title":"Table-to-text Generation by Structure-aware Seq2seq Learning","created":"2017-11-27","cited_by_count":54},{"id":"2108.13740","title":"Plan-then-Generate: Controlled Data-to-Text Generation via Planning","created":"2021-08-31","cited_by_count":52},{"id":"2005.00969","title":"Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraints","created":"2020-05-03","cited_by_count":48},{"id":"2004.14579","title":"Logic2Text: High-Fidelity Natural Language Generation from Logical Forms","created":"2020-04-30","cited_by_count":45},{"id":"1805.11234","title":"Table-to-Text: Describing Table Region with Natural Language","created":"2018-05-29","cited_by_count":41},{"id":"2403.09162","title":"Unveiling the Generalization Power of Fine-Tuned Large Language Models","created":"2024-03-14","cited_by_count":36},{"id":"2102.02723","title":"Data-to-text Generation with Macro Planning","created":"2021-02-04","cited_by_count":34},{"id":"1904.01301","title":"Pragmatically Informative Text Generation","created":"2019-04-02","cited_by_count":32},{"id":"1509.00838","title":"What to talk about and how? Selective Generation using LSTMs with Coarse-to-Fine Alignment","created":"2015-09-02","cited_by_count":31},{"id":"1910.12129","title":"ViGGO: A Video Game Corpus for Data-To-Text Generation in Open-Domain Conversation","created":"2019-10-26","cited_by_count":31},{"id":"1810.01170","title":"Findings of the E2E NLG Challenge","created":"2018-10-02","cited_by_count":28},{"id":"2203.05227","title":"Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods","created":"2022-03-10","cited_by_count":27},{"id":"1709.00155","title":"Order-Planning Neural Text Generation From Structured Data","created":"2017-09-01","cited_by_count":20},{"id":"1805.06553","title":"A Deep Ensemble Model with Slot Alignment for Sequence-to-Sequence Natural Language Generation","created":"2018-05-16","cited_by_count":20},{"id":"2002.01127","title":"Variational Template Machine for Data-to-Text Generation","created":"2020-02-04","cited_by_count":19},{"id":"1909.02304","title":"Table-to-Text Generation with Effective Hierarchical Encoder on Three Dimensions (Row, Column and Time)","created":"2019-09-05","cited_by_count":18},{"id":"2310.07328","title":"An Empirical Study of Instruction-tuning Large Language Models in Chinese","created":"2023-10-11","cited_by_count":17},{"id":"2401.01183","title":"Unifying Structured Data as Graph for Data-to-Text Pre-Training","created":"2024-01-02","cited_by_count":13},{"id":"2403.12900","title":"Toward Sustainable GenAI using Generation Directives for Carbon-Friendly Large Language Model Inference","created":"2024-03-19","cited_by_count":13},{"id":"1804.07789","title":"Generating Descriptions from Structured Data Using a Bifocal Attention Mechanism and Gated Orthogonalization","created":"2018-04-20","cited_by_count":12},{"id":"2305.03256","title":"Stylized Data-to-Text Generation: A Case Study in the E-Commerce Domain","created":"2023-05-05","cited_by_count":11},{"id":"1808.03507","title":"Making effective use of healthcare data using data-to-text technology","created":"2018-08-10","cited_by_count":9},{"id":"2109.01518","title":"Biomedical Data-to-Text Generation via Fine-Tuning Transformers","created":"2021-09-03","cited_by_count":9},{"id":"2302.14169","title":"TabGenie: A Toolkit for Table-to-Text Generation","created":"2023-02-27","cited_by_count":7},{"id":"2312.07763","title":"Can LLM find the green circle? Investigation and Human-guided tool manipulation for compositional generalization","created":"2023-12-12","cited_by_count":7},{"id":"2308.00399","title":"Tackling Hallucinations in Neural Chart Summarization","created":"2023-08-01","cited_by_count":6},{"id":"1705.03802","title":"Analysing Data-To-Text Generation Benchmarks","created":"2017-05-10","cited_by_count":5},{"id":"2402.12267","title":"High-quality Data-to-Text Generation for Severely Under-Resourced Languages with Out-of-the-box Large Language Models","created":"2024-02-19","cited_by_count":5},{"id":"1610.08375","title":"Content Selection in Data-to-Text Systems: A Survey","created":"2016-10-26","cited_by_count":3}],"next_cursor":null}