{"list":"other","total":76,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"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":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"2211.01910","title":"Large Language Models Are Human-Level Prompt Engineers","created":"2022-11-03","cited_by_count":1045},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2308.09687","title":"Graph of Thoughts: Solving Elaborate Problems with Large Language Models","created":"2023-08-18","cited_by_count":886},{"id":"2305.14992","title":"Reasoning with Language Model is Planning with World Model","created":"2023-05-24","cited_by_count":861},{"id":"1702.08165","title":"Reinforcement Learning with Deep Energy-Based Policies","created":"2017-02-27","cited_by_count":669},{"id":"2009.07118","title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","created":"2020-09-15","cited_by_count":669},{"id":"2308.09583","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","created":"2023-08-18","cited_by_count":625},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609},{"id":"2305.18654","title":"Faith and Fate: Limits of Transformers on Compositionality","created":"2023-05-29","cited_by_count":503},{"id":"2105.03023","title":"DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts","created":"2021-05-07","cited_by_count":441},{"id":"1604.01696","title":"A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories","created":"2016-04-06","cited_by_count":417},{"id":"2106.04399","title":"Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation","created":"2021-06-08","cited_by_count":392},{"id":"2104.05218","title":"FUDGE: Controlled Text Generation With Future Discriminators","created":"2021-04-12","cited_by_count":376},{"id":"1610.02424","title":"Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models","created":"2016-10-07","cited_by_count":301},{"id":"2111.09266","title":"GFlowNet Foundations","created":"2021-11-17","cited_by_count":290},{"id":"2212.08410","title":"Teaching Small Language Models to Reason","created":"2022-12-16","cited_by_count":284},{"id":"2201.13259","title":"Trajectory balance: Improved credit assignment in GFlowNets","created":"2022-01-31","cited_by_count":251},{"id":"1704.07138","title":"Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search","created":"2017-04-24","cited_by_count":237},{"id":"2303.05398","title":"MathPrompter: Mathematical Reasoning using Large Language Models","created":"2023-03-04","cited_by_count":236},{"id":"1902.04094","title":"BERT has a Mouth, and It Must Speak: BERT as a Markov Random Field Language Model","created":"2019-02-11","cited_by_count":185},{"id":"1702.08892","title":"Bridging the Gap Between Value and Policy Based Reinforcement Learning","created":"2017-02-28","cited_by_count":182},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176},{"id":"2203.04115","title":"Biological Sequence Design with GFlowNets","created":"2022-03-02","cited_by_count":174},{"id":"2112.08726","title":"NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics","created":"2021-12-16","cited_by_count":154},{"id":"2202.13903","title":"Bayesian Structure Learning with Generative Flow Networks","created":"2022-02-28","cited_by_count":153},{"id":"2209.12782","title":"Learning GFlowNets from partial episodes for improved convergence and stability","created":"2022-09-26","cited_by_count":132},{"id":"2307.03381","title":"Teaching Arithmetic to Small Transformers","created":"2023-07-07","cited_by_count":123},{"id":"2005.05339","title":"Enabling Language Models to Fill in the Blanks","created":"2020-05-11","cited_by_count":122},{"id":"2211.09066","title":"Teaching Algorithmic Reasoning via In-context Learning","created":"2022-11-15","cited_by_count":112},{"id":"2212.06094","title":"Prompting Is Programming: A Query Language for Large Language Models","created":"2022-12-12","cited_by_count":110},{"id":"2207.10342","title":"Language Model Cascades","created":"2022-07-21","cited_by_count":107},{"id":"2210.00580","title":"GFlowNets and variational inference","created":"2022-10-02","cited_by_count":106},{"id":"1811.10996","title":"CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling","created":"2018-11-14","cited_by_count":94},{"id":"2306.03081","title":"Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs","created":"2023-06-05","cited_by_count":80},{"id":"2305.07170","title":"Towards Understanding and Improving GFlowNet Training","created":"2023-05-11","cited_by_count":75},{"id":"2306.15400","title":"Length Generalization in Arithmetic Transformers","created":"2023-06-27","cited_by_count":66},{"id":"2302.00615","title":"GFlowNets for AI-Driven Scientific Discovery","created":"2023-02-01","cited_by_count":63},{"id":"2309.02144","title":"Making Large Language Models Better Reasoners with Alignment","created":"2023-09-05","cited_by_count":63},{"id":"2002.02492","title":"Consistency of a Recurrent Language Model With Respect to Incomplete Decoding","created":"2020-02-06","cited_by_count":54},{"id":"2212.12393","title":"A-NeSI: A Scalable Approximate Method for Probabilistic Neurosymbolic Inference","created":"2022-12-23","cited_by_count":50},{"id":"2305.19366","title":"Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network","created":"2023-05-30","cited_by_count":50},{"id":"2305.09993","title":"Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling","created":"2023-05-17","cited_by_count":47},{"id":"2004.12681","title":"Lexically Constrained Neural Machine Translation with Levenshtein Transformer","created":"2020-04-27","cited_by_count":45},{"id":"1701.03185","title":"Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models","created":"2017-01-11","cited_by_count":42},{"id":"2205.14219","title":"Controllable Text Generation with Neurally-Decomposed Oracle","created":"2022-05-27","cited_by_count":41},{"id":"2302.06576","title":"GFlowNet-EM for learning compositional latent variable models","created":"2023-02-13","cited_by_count":40},{"id":"2210.07992","title":"A Variational Perspective on Generative Flow Networks","created":"2022-10-14","cited_by_count":39},{"id":"2110.08294","title":"Coherence boosting: When your pretrained language model is not paying enough attention","created":"2021-10-15","cited_by_count":38},{"id":"2106.02736","title":"Exposing the Implicit Energy Networks behind Masked Language Models via Metropolis--Hastings","created":"2021-06-04","cited_by_count":37},{"id":"2106.07704","title":"Efficient (Soft) Q-Learning for Text Generation with Limited Good Data","created":"2021-06-14","cited_by_count":37},{"id":"1901.00158","title":"Text Infilling","created":"2019-01-01","cited_by_count":32},{"id":"2306.12509","title":"Joint Prompt Optimization of Stacked LLMs using Variational Inference","created":"2023-06-21","cited_by_count":32},{"id":"2302.03686","title":"Long Horizon Temperature Scaling","created":"2023-02-07","cited_by_count":18},{"id":"2102.11008","title":"InsNet: An Efficient, Flexible, and Performant Insertion-based Text Generation Model","created":"2021-02-12","cited_by_count":14},{"id":"2202.12226","title":"Probing BERT's priors with serial reproduction chains","created":"2022-02-24","cited_by_count":11},{"id":"1905.10752","title":"TIGS: An Inference Algorithm for Text Infilling with Gradient Search","created":"2019-05-26","cited_by_count":10},{"id":"2109.04867","title":"Studying word order through iterative shuffling","created":"2021-09-10","cited_by_count":9},{"id":"2305.15501","title":"Deriving Language Models from Masked Language Models","created":"2023-05-24","cited_by_count":9},{"id":"1604.08633","title":"Word Ordering Without Syntax","created":"2016-04-28","cited_by_count":7}],"next_cursor":null}