{"list":"other","total":55,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"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":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"id":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"id":"1506.03340","title":"Teaching Machines to Read and Comprehend","created":"2015-06-10","cited_by_count":1049},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"2004.09095","title":"The State and Fate of Linguistic Diversity and Inclusion in the NLP World","created":"2020-04-20","cited_by_count":798},{"id":"1807.02811","title":"A Tutorial on Bayesian Optimization","created":"2018-07-08","cited_by_count":744},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"id":"2007.12626","title":"SummEval: Re-evaluating Summarization Evaluation","created":"2020-07-24","cited_by_count":674},{"id":"1712.07040","title":"The NarrativeQA Reading Comprehension Challenge","created":"2017-12-19","cited_by_count":597},{"id":"2403.13787","title":"RewardBench: Evaluating Reward Models for Language Modeling","created":"2024-03-20","cited_by_count":499},{"id":"2406.18495","title":"WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs","created":"2024-06-26","cited_by_count":496},{"id":"2001.09977","title":"Towards a Human-like Open-Domain Chatbot","created":"2020-01-27","cited_by_count":470},{"id":"2301.13848","title":"Benchmarking Large Language Models for News Summarization","created":"2023-01-31","cited_by_count":445},{"id":"1909.02622","title":"MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance","created":"2019-09-05","cited_by_count":418},{"id":"2403.17297","title":"InternLM2 Technical Report","created":"2024-03-26","cited_by_count":397},{"id":"2406.12845","title":"Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts","created":"2024-06-18","cited_by_count":376},{"id":"2406.08464","title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","created":"2024-06-12","cited_by_count":346},{"id":"2310.10482","title":"xCOMET: Transparent Machine Translation Evaluation through Fine-grained Error Detection","created":"2023-10-16","cited_by_count":265},{"id":"2210.07197","title":"Towards a Unified Multi-Dimensional Evaluator for Text Generation","created":"2022-10-13","cited_by_count":264},{"id":"2406.08673","title":"HelpSteer2: Open-source dataset for training top-performing reward models","created":"2024-06-12","cited_by_count":236},{"id":"1910.09753","title":"MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehension","created":"2019-10-22","cited_by_count":184},{"id":"2107.10821","title":"To Ship or Not to Ship: An Extensive Evaluation of Automatic Metrics for Machine Translation","created":"2021-07-22","cited_by_count":163},{"id":"2310.13988","title":"GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4","created":"2023-10-21","cited_by_count":146},{"id":"2407.06551","title":"OffsetBias: Leveraging Debiased Data for Tuning Evaluators","created":"2024-07-09","cited_by_count":94},{"id":"1909.01610","title":"Answers Unite! Unsupervised Metrics for Reinforced Summarization Models","created":"2019-09-04","cited_by_count":92},{"id":"2111.05040","title":"A survey on high-dimensional Gaussian process modeling with application to Bayesian optimization","created":"2021-11-09","cited_by_count":77},{"id":"1508.06034","title":"Better Summarization Evaluation with Word Embeddings for ROUGE","created":"2015-08-25","cited_by_count":66},{"id":"1909.02050","title":"TIGEr: Text-to-Image Grounding for Image Caption Evaluation","created":"2019-09-04","cited_by_count":58},{"id":"1909.08582","title":"Code-Switched Language Models Using Neural Based Synthetic Data from Parallel Sentences","created":"2019-09-18","cited_by_count":55},{"id":"2106.01229","title":"Lower Perplexity is Not Always Human-Like","created":"2021-06-02","cited_by_count":52},{"id":"2011.00483","title":"Deconstruct to Reconstruct a Configurable Evaluation Metric for Open-Domain Dialogue Systems","created":"2020-11-01","cited_by_count":47},{"id":"2111.08940","title":"Transparent Human Evaluation for Image Captioning","created":"2021-11-17","cited_by_count":40},{"id":"2402.01591","title":"BAT: Learning to Reason about Spatial Sounds with Large Language Models","created":"2024-02-02","cited_by_count":36},{"id":"2212.09660","title":"The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challenges","created":"2022-12-19","cited_by_count":35},{"id":"2305.12421","title":"Evaluating Open-QA Evaluation","created":"2023-05-21","cited_by_count":35},{"id":"2409.11564","title":"Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey","created":"2024-09-17","cited_by_count":23},{"id":"2406.09334","title":"ProxyLM: Predicting Language Model Performance on Multilingual Tasks via Proxy Models","created":"2024-06-13","cited_by_count":20}],"next_cursor":null}