{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"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":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"id":"1404.7828","title":"Deep Learning in Neural Networks: An Overview","created":"2014-04-30","cited_by_count":770},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"2301.00234","title":"A Survey on In-context Learning","created":"2022-12-31","cited_by_count":721},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656},{"id":"2309.03882","title":"Large Language Models Are Not Robust Multiple Choice Selectors","created":"2023-09-07","cited_by_count":486},{"id":"2403.03507","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","created":"2024-03-06","cited_by_count":463},{"id":"2306.09212","title":"CMMLU: Measuring massive multitask language understanding in Chinese","created":"2023-06-15","cited_by_count":449},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429},{"id":"2306.15626","title":"LeanDojo: Theorem Proving with Retrieval-Augmented Language Models","created":"2023-06-27","cited_by_count":427},{"id":"2309.12288","title":"The Reversal Curse: LLMs trained on \"A is B\" fail to learn \"B is A\"","created":"2023-09-21","cited_by_count":407},{"id":"2401.11817","title":"Hallucination is Inevitable: An Innate Limitation of Large Language Models","created":"2024-01-22","cited_by_count":332},{"id":"2305.17126","title":"Large Language Models as Tool Makers","created":"2023-05-26","cited_by_count":303},{"id":"2305.08291","title":"Large Language Model Guided Tree-of-Thought","created":"2023-05-15","cited_by_count":221},{"id":"2211.05110","title":"Large Language Models with Controllable Working Memory","created":"2022-11-09","cited_by_count":169},{"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":"2311.08718","title":"Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling","created":"2023-11-15","cited_by_count":114},{"id":"1905.09381","title":"Learning to Prove Theorems via Interacting with Proof Assistants","created":"2019-05-21","cited_by_count":109},{"id":"2406.04271","title":"Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models","created":"2024-06-06","cited_by_count":91},{"id":"2310.12505","title":"Attack Prompt Generation for Red Teaming and Defending Large Language Models","created":"2023-10-19","cited_by_count":76},{"id":"2306.01694","title":"Evaluating Language Models for Mathematics through Interactions","created":"2023-06-02","cited_by_count":70},{"id":"2305.17256","title":"Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning","created":"2023-05-26","cited_by_count":69},{"id":"2403.17752","title":"Can multiple-choice questions really be useful in detecting the abilities of LLMs?","created":"2024-03-26","cited_by_count":69},{"id":"2406.02061","title":"Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models","created":"2024-06-04","cited_by_count":68},{"id":"2405.18870","title":"LLMs achieve adult human performance on higher-order theory of mind tasks","created":"2024-05-29","cited_by_count":61},{"id":"1908.02660","title":"SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition","created":"2019-08-07","cited_by_count":55},{"id":"2305.14279","title":"Two Failures of Self-Consistency in the Multi-Step Reasoning of LLMs","created":"2023-05-23","cited_by_count":36},{"id":"2405.11966","title":"Multiple-Choice Questions are Efficient and Robust LLM Evaluators","created":"2024-05-20","cited_by_count":28},{"id":"2406.02356","title":"Language Models Do Hard Arithmetic Tasks Easily and Hardly Do Easy Arithmetic Tasks","created":"2024-06-04","cited_by_count":24},{"id":"2109.06133","title":"Neuro-Symbolic AI: An Emerging Class of AI Workloads and their Characterization","created":"2021-09-13","cited_by_count":22},{"id":"2402.11764","title":"ChatGPT Based Data Augmentation for Improved Parameter-Efficient Debiasing of LLMs","created":"2024-02-19","cited_by_count":18},{"id":"2209.01882","title":"PromptAttack: Prompt-based Attack for Language Models via Gradient Search","created":"2022-09-05","cited_by_count":15},{"id":"2312.10065","title":"Exploring Social Bias in Downstream Applications of Text-to-Image Foundation Models","created":"2023-12-05","cited_by_count":7},{"id":"2309.08181","title":"Large Language Models for Failure Mode Classification: An Investigation","created":"2023-09-15","cited_by_count":6},{"id":"2402.00861","title":"Evaluating Large Language Models for Generalization and Robustness via Data Compression","created":"2024-02-01","cited_by_count":5},{"id":"2401.16012","title":"Finding Challenging Metaphors that Confuse Pretrained Language Models","created":"2024-01-29","cited_by_count":3}],"next_cursor":null}