{"list":"other","total":56,"rows":[{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"id":"2304.12244","title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","created":"2023-04-24","cited_by_count":1125},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"2009.09025","title":"COMET: A Neural Framework for MT Evaluation","created":"2020-09-18","cited_by_count":1033},{"id":"2004.09297","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","created":"2020-04-20","cited_by_count":981},{"id":"2305.14233","title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","created":"2023-05-23","cited_by_count":839},{"id":"2303.17548","title":"Whose Opinions Do Language Models Reflect?","created":"2023-03-30","cited_by_count":773},{"id":"2305.14387","title":"AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback","created":"2023-05-22","cited_by_count":748},{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723},{"id":"2309.00267","title":"RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback","created":"2023-09-01","cited_by_count":625},{"id":"2004.09813","title":"Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation","created":"2020-04-21","cited_by_count":593},{"id":"2306.02561","title":"LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion","created":"2023-06-05","cited_by_count":564},{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437},{"id":"2212.09689","title":"Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor","created":"2022-12-19","cited_by_count":397},{"id":"2308.12032","title":"From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning","created":"2023-08-23","cited_by_count":307},{"id":"1610.02424","title":"Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models","created":"2016-10-07","cited_by_count":301},{"id":"2107.00061","title":"All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text","created":"2021-06-30","cited_by_count":287},{"id":"2310.11564","title":"Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging","created":"2023-10-17","cited_by_count":280},{"id":"2209.01975","title":"Selective Annotation Makes Language Models Better Few-Shot Learners","created":"2022-09-05","cited_by_count":243},{"id":"2303.17466","title":"Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study","created":"2023-03-30","cited_by_count":206},{"id":"2404.02078","title":"Advancing LLM Reasoning Generalists with Preference Trees","created":"2024-04-02","cited_by_count":192},{"id":"2404.14367","title":"Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data","created":"2024-04-22","cited_by_count":185},{"id":"2403.15412","title":"Towards Measuring and Modeling \"Culture\" in LLMs: A Survey","created":"2024-03-05","cited_by_count":167},{"id":"2210.00045","title":"Calibrating Sequence likelihood Improves Conditional Language Generation","created":"2022-09-30","cited_by_count":121},{"id":"1808.05697","title":"Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Study","created":"2018-08-16","cited_by_count":90},{"id":"2303.05453","title":"Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback","created":"2023-03-09","cited_by_count":87},{"id":"2309.16349","title":"Human Feedback is not Gold Standard","created":"2023-09-28","cited_by_count":83},{"id":"2108.04718","title":"Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation","created":"2021-08-10","cited_by_count":65},{"id":"2305.09860","title":"Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum Bayes Risk Decoding for Machine Translation","created":"2023-05-17","cited_by_count":58},{"id":"2211.07634","title":"Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding","created":"2022-11-14","cited_by_count":54},{"id":"2402.18191","title":"Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation","created":"2024-02-28","cited_by_count":53},{"id":"2301.05036","title":"Everyone's Voice Matters: Quantifying Annotation Disagreement Using Demographic Information","created":"2023-01-12","cited_by_count":52},{"id":"2310.01387","title":"It's MBR All the Way Down: Modern Generation Techniques Through the Lens of Minimum Bayes Risk","created":"2023-10-02","cited_by_count":51},{"id":"2404.08495","title":"Dataset Reset Policy Optimization for RLHF","created":"2024-04-12","cited_by_count":41},{"id":"2207.06814","title":"BERTIN: Efficient Pre-Training of a Spanish Language Model using Perplexity Sampling","created":"2022-07-14","cited_by_count":30},{"id":"2402.18120","title":"Exploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?","created":"2024-02-28","cited_by_count":24},{"id":"2402.10891","title":"Instruction Diversity Drives Generalization To Unseen Tasks","created":"2024-02-16","cited_by_count":16},{"id":"2401.05054","title":"Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding","created":"2024-01-10","cited_by_count":11},{"id":"1410.5877","title":"Bucking the Trend: Large-Scale Cost-Focused Active Learning for Statistical Machine Translation","created":"2014-10-21","cited_by_count":10},{"id":"2310.06450","title":"Constructive Large Language Models Alignment with Diverse Feedback","created":"2023-10-10","cited_by_count":9},{"id":"2405.12081","title":"Selective Annotation via Data Allocation: These Data Should Be Triaged to Experts for Annotation Rather Than the Model","created":"2024-05-20","cited_by_count":6},{"id":"1605.06588","title":"Optimal Number of Choices in Rating Contexts","created":"2016-05-21","cited_by_count":1},{"id":"2405.11226","title":"The Power of Active Multi-Task Learning in Reinforcement Learning from Human Feedback","created":"2024-05-18","cited_by_count":1}],"next_cursor":null}