{"list":"other","total":59,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"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":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"2211.01910","title":"Large Language Models Are Human-Level Prompt Engineers","created":"2022-11-03","cited_by_count":1045},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"1705.04146","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","created":"2017-05-11","cited_by_count":650},{"id":"2309.16797","title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","created":"2023-09-28","cited_by_count":551},{"id":"1911.12237","title":"SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization","created":"2019-11-27","cited_by_count":535},{"id":"2205.12548","title":"RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning","created":"2022-05-25","cited_by_count":366},{"id":"1705.00648","title":"\"Liar, Liar Pants on Fire\": A New Benchmark Dataset for Fake News Detection","created":"2017-05-01","cited_by_count":363},{"id":"2005.00333","title":"XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning","created":"2020-05-01","cited_by_count":333},{"id":"2203.07540","title":"ScienceWorld: Is your Agent Smarter than a 5th Grader?","created":"2022-03-14","cited_by_count":327},{"id":"2301.12661","title":"Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models","created":"2023-01-30","cited_by_count":324},{"id":"1706.09254","title":"The E2E Dataset: New Challenges For End-to-End Generation","created":"2017-06-28","cited_by_count":253},{"id":"1806.08730","title":"The Natural Language Decathlon: Multitask Learning as Question Answering","created":"2018-06-20","cited_by_count":236},{"id":"2011.03088","title":"HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification","created":"2020-11-05","cited_by_count":201},{"id":"2205.10782","title":"Instruction Induction: From Few Examples to Natural Language Task Descriptions","created":"2022-05-22","cited_by_count":152},{"id":"2010.04898","title":"Open-Domain Question Answering Goes Conversational via Question Rewriting","created":"2020-10-10","cited_by_count":148},{"id":"2307.11760","title":"Large Language Models Understand and Can be Enhanced by Emotional Stimuli","created":"2023-07-14","cited_by_count":146},{"id":"2310.19046","title":"Large Language Models as Evolutionary Optimizers","created":"2023-10-29","cited_by_count":124},{"id":"2402.10571","title":"Direct Preference Optimization with an Offset","created":"2024-02-16","cited_by_count":122},{"id":"2302.11520","title":"Guiding Large Language Models via Directional Stimulus Prompting","created":"2023-02-22","cited_by_count":95},{"id":"2407.16216","title":"Reinforcement Learning for LLM Post-Training: A Survey","created":"2024-07-23","cited_by_count":92},{"id":"2403.17804","title":"Improving Text-to-Image Consistency via Automatic Prompt Optimization","created":"2024-03-26","cited_by_count":90},{"id":"2305.09993","title":"Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling","created":"2023-05-17","cited_by_count":47},{"id":"2401.08189","title":"PRewrite: Prompt Rewriting with Reinforcement Learning","created":"2024-01-16","cited_by_count":45},{"id":"2310.04444","title":"What's the Magic Word? A Control Theory of LLM Prompting","created":"2023-10-02","cited_by_count":41},{"id":"2008.12520","title":"A Dataset and Baselines for Visual Question Answering on Art","created":"2020-08-28","cited_by_count":38},{"id":"2309.06553","title":"Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL","created":"2023-09-13","cited_by_count":37},{"id":"2212.09257","title":"PromptBoosting: Black-Box Text Classification with Ten Forward Passes","created":"2022-12-19","cited_by_count":36},{"id":"2110.15486","title":"DOCKSTRING: easy molecular docking yields better benchmarks for ligand design","created":"2021-10-29","cited_by_count":35},{"id":"2404.02319","title":"Symbolic Prompt Program Search: A Structure-Aware Approach to Efficient Compile-Time Prompt Optimization","created":"2024-04-02","cited_by_count":30},{"id":"2410.14826","title":"SPRIG: Improving Large Language Model Performance by System Prompt Optimization","created":"2024-10-18","cited_by_count":29},{"id":"2308.12033","title":"PREFER: Prompt Ensemble Learning via Feedback-Reflect-Refine","created":"2023-08-23","cited_by_count":28},{"id":"2406.10504","title":"Task Facet Learning: A Structured Approach to Prompt Optimization","created":"2024-06-15","cited_by_count":19},{"id":"2305.19426","title":"ScoNe: Benchmarking Negation Reasoning in Language Models With Fine-Tuning and In-Context Learning","created":"2023-05-30","cited_by_count":18},{"id":"2410.02748","title":"CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text Generation","created":"2024-10-03","cited_by_count":18},{"id":"2310.12774","title":"Survival of the Most Influential Prompts: Efficient Black-Box Prompt Search via Clustering and Pruning","created":"2023-10-19","cited_by_count":17},{"id":"2402.11711","title":"MORL-Prompt: An Empirical Analysis of Multi-Objective Reinforcement Learning for Discrete Prompt Optimization","created":"2024-02-18","cited_by_count":16},{"id":"2305.19835","title":"Deliberate then Generate: Enhanced Prompting Framework for Text Generation","created":"2023-05-31","cited_by_count":13},{"id":"2405.20701","title":"Unveiling the Lexical Sensitivity of LLMs: Combinatorial Optimization for Prompt Enhancement","created":"2024-05-31","cited_by_count":13},{"id":"2410.08696","title":"AMPO: Automatic Multi-Branched Prompt Optimization","created":"2024-10-11","cited_by_count":11},{"id":"1908.07085","title":"BoxNet: A Deep Learning Method for 2D Bounding Box Estimation from Bird's-Eye View Point Cloud","created":"2019-08-19","cited_by_count":3}],"next_cursor":null}