{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1907.10902","title":"Optuna: A Next-generation Hyperparameter Optimization Framework","created":"2019-07-25","cited_by_count":2501},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906},{"id":"1911.00536","title":"DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation","created":"2019-11-01","cited_by_count":842},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698},{"id":"2006.05205","title":"On the Bottleneck of Graph Neural Networks and its Practical Implications","created":"2020-06-09","cited_by_count":631},{"id":"2004.13637","title":"Recipes for building an open-domain chatbot","created":"2020-04-28","cited_by_count":593},{"id":"2211.11559","title":"Visual Programming: Compositional visual reasoning without training","created":"2022-11-18","cited_by_count":516},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513},{"id":"2305.18654","title":"Faith and Fate: Limits of Transformers on Compositionality","created":"2023-05-29","cited_by_count":503},{"id":"2212.04088","title":"LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models","created":"2022-12-08","cited_by_count":462},{"id":"2207.04429","title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","created":"2022-07-10","cited_by_count":439},{"id":"2110.02861","title":"8-bit Optimizers via Block-wise Quantization","created":"2021-10-06","cited_by_count":403},{"id":"2005.00796","title":"A Simple Language Model for Task-Oriented Dialogue","created":"2020-05-02","cited_by_count":332},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305},{"id":"2302.08399","title":"Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks","created":"2023-02-16","cited_by_count":292},{"id":"2002.06157","title":"Generalization and Representational Limits of Graph Neural Networks","created":"2020-02-14","cited_by_count":218},{"id":"2210.06407","title":"Interactive Language: Talking to Robots in Real Time","created":"2022-10-12","cited_by_count":218},{"id":"2202.01110","title":"A Survey on Retrieval-Augmented Text Generation","created":"2022-02-02","cited_by_count":158},{"id":"1705.05414","title":"Key-Value Retrieval Networks for Task-Oriented Dialogue","created":"2017-05-15","cited_by_count":138},{"id":"2009.11423","title":"Task-Oriented Dialogue as Dataflow Synthesis","created":"2020-09-24","cited_by_count":122},{"id":"2210.06710","title":"Large Language Models are few(1)-shot Table Reasoners","created":"2022-10-13","cited_by_count":116},{"id":"2002.12328","title":"Few-shot Natural Language Generation for Task-Oriented Dialog","created":"2020-02-27","cited_by_count":89},{"id":"2212.10947","title":"Parallel Context Windows for Large Language Models","created":"2022-12-21","cited_by_count":81},{"id":"1810.09587","title":"Towards Universal Dialogue State Tracking","created":"2018-10-22","cited_by_count":33},{"id":"1910.00610","title":"DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphs","created":"2019-10-01","cited_by_count":33},{"id":"2102.04643","title":"Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialog","created":"2021-02-09","cited_by_count":33},{"id":"1809.05255","title":"SQL-to-Text Generation with Graph-to-Sequence Model","created":"2018-09-14","cited_by_count":31},{"id":"2010.03084","title":"Program Enhanced Fact Verification with Verbalization and Graph Attention Network","created":"2020-10-06","cited_by_count":29},{"id":"2308.07891","title":"Link-Context Learning for Multimodal LLMs","created":"2023-08-15","cited_by_count":24},{"id":"2102.02096","title":"Learning to Select External Knowledge with Multi-Scale Negative Sampling","created":"2021-02-03","cited_by_count":16},{"id":"2010.15411","title":"Conversation Graph: Data Augmentation, Training and Evaluation for Non-Deterministic Dialogue Management","created":"2020-10-29","cited_by_count":13},{"id":"2309.11064","title":"Exploring the Relationship between LLM Hallucinations and Prompt Linguistic Nuances: Readability, Formality, and Concreteness","created":"2023-09-20","cited_by_count":13},{"id":"1804.07789","title":"Generating Descriptions from Structured Data Using a Bifocal Attention Mechanism and Gated Orthogonalization","created":"2018-04-20","cited_by_count":12},{"id":"2305.01548","title":"Explainable Conversational Question Answering over Heterogeneous Sources via Iterative Graph Neural Networks","created":"2023-05-02","cited_by_count":9},{"id":"2209.03632","title":"AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog","created":"2022-09-08","cited_by_count":8},{"id":"2306.09114","title":"Relational Temporal Graph Reasoning for Dual-task Dialogue Language Understanding","created":"2023-06-15","cited_by_count":7},{"id":"2202.04161","title":"Logical Reasoning for Task Oriented Dialogue Systems","created":"2022-02-08","cited_by_count":5},{"id":"2203.00763","title":"Multi-Sentence Knowledge Selection in Open-Domain Dialogue","created":"2022-03-01","cited_by_count":5},{"id":"2006.15768","title":"Towards meaningful, grounded conversations with intelligent agents","created":"2020-06-29","cited_by_count":1},{"id":"2309.07974","title":"A Data Source for Reasoning Embodied Agents","created":"2023-09-14","cited_by_count":1},{"id":"2310.13566","title":"Retrieval-Augmented Neural Response Generation Using Logical Reasoning and Relevance Scoring","created":"2023-10-20","cited_by_count":1}],"next_cursor":null}