{"list":"other","total":53,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"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":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"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":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609},{"id":"2310.16944","title":"Zephyr: Direct Distillation of LM Alignment","created":"2023-10-25","cited_by_count":506},{"id":"2106.04399","title":"Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation","created":"2021-06-08","cited_by_count":392},{"id":"2305.12295","title":"Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning","created":"2023-05-20","cited_by_count":391},{"id":"2309.17179","title":"Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training","created":"2023-09-29","cited_by_count":295},{"id":"2111.09266","title":"GFlowNet Foundations","created":"2021-11-17","cited_by_count":290},{"id":"2210.10723","title":"TabLLM: Few-shot Classification of Tabular Data with Large Language Models","created":"2022-10-19","cited_by_count":277},{"id":"2212.09196","title":"Emergent Analogical Reasoning in Large Language Models","created":"2022-12-19","cited_by_count":240},{"id":"2002.09291","title":"Transformer Hawkes Process","created":"2020-02-21","cited_by_count":235},{"id":"2307.14984","title":"S$^3$: Social-network Simulation System with Large Language Model-Empowered Agents","created":"2023-07-27","cited_by_count":233},{"id":"2005.00343","title":"The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines","created":"2020-04-29","cited_by_count":225},{"id":"1711.04574","title":"Learning Explanatory Rules from Noisy Data","created":"2017-11-13","cited_by_count":211},{"id":"1705.11040","title":"End-to-End Differentiable Proving","created":"2017-05-31","cited_by_count":161},{"id":"2112.08726","title":"NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics","created":"2021-12-16","cited_by_count":154},{"id":"2301.11916","title":"Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning","created":"2023-01-27","cited_by_count":149},{"id":"1909.12127","title":"Intensity-Free Learning of Temporal Point Processes","created":"2019-09-26","cited_by_count":140},{"id":"2209.12782","title":"Learning GFlowNets from partial episodes for improved convergence and stability","created":"2022-09-26","cited_by_count":132},{"id":"2310.04363","title":"Amortizing intractable inference in large language models","created":"2023-10-06","cited_by_count":97},{"id":"1811.10996","title":"CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling","created":"2018-11-14","cited_by_count":94},{"id":"1705.08982","title":"Modeling The Intensity Function Of Point Process Via Recurrent Neural Networks","created":"2017-05-24","cited_by_count":93},{"id":"2011.04583","title":"Neural Spatio-Temporal Point Processes","created":"2020-11-09","cited_by_count":93},{"id":"2201.00044","title":"Transformer Embeddings of Irregularly Spaced Events and Their Participants","created":"2021-12-31","cited_by_count":93},{"id":"2306.03081","title":"Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs","created":"2023-06-05","cited_by_count":80},{"id":"2307.08097","title":"EasyTPP: Towards Open Benchmarking Temporal Point Processes","created":"2023-07-16","cited_by_count":68},{"id":"2310.12934","title":"Generative Flow Networks as Entropy-Regularized RL","created":"2023-10-19","cited_by_count":64},{"id":"2312.15198","title":"Do LLM Agents Exhibit Social Behavior?","created":"2023-12-23","cited_by_count":53},{"id":"2212.12393","title":"A-NeSI: A Scalable Approximate Method for Probabilistic Neurosymbolic Inference","created":"2022-12-23","cited_by_count":50},{"id":"2306.02231","title":"Fine-Tuning Language Models with Advantage-Induced Policy Alignment","created":"2023-06-04","cited_by_count":48},{"id":"2305.16646","title":"Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning","created":"2023-05-26","cited_by_count":45},{"id":"2402.10309","title":"Discrete Probabilistic Inference as Control in Multi-path Environments","created":"2024-02-15","cited_by_count":44},{"id":"2302.06576","title":"GFlowNet-EM for learning compositional latent variable models","created":"2023-02-13","cited_by_count":40},{"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":"2310.04993","title":"Prompt-augmented Temporal Point Process for Streaming Event Sequence","created":"2023-10-08","cited_by_count":24},{"id":"2112.13418","title":"Neuro-Symbolic Hierarchical Rule Induction","created":"2021-12-26","cited_by_count":23},{"id":"2309.03224","title":"No Train Still Gain. Unleash Mathematical Reasoning of Large Language Models with Monte Carlo Tree Search Guided by Energy Function","created":"2023-09-01","cited_by_count":20},{"id":"1907.10952","title":"Logical reduction of metarules","created":"2019-07-25","cited_by_count":19},{"id":"2011.03231","title":"User-Dependent Neural Sequence Models for Continuous-Time Event Data","created":"2020-11-06","cited_by_count":17},{"id":"1809.02193","title":"Logical Rule Induction and Theory Learning Using Neural Theorem Proving","created":"2018-09-06","cited_by_count":13},{"id":"1702.08367","title":"Differentiable Learning of Logical Rules for Knowledge Base Reasoning","created":"2017-02-27","cited_by_count":8}],"next_cursor":null}