{"list":"other","total":52,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"1911.02116","title":"Unsupervised Cross-lingual Representation Learning at Scale","created":"2019-11-05","cited_by_count":3935},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"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":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2211.12588","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","created":"2022-11-22","cited_by_count":1076},{"id":"2211.01910","title":"Large Language Models Are Human-Level Prompt Engineers","created":"2022-11-03","cited_by_count":1045},{"id":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"2301.00234","title":"A Survey on In-context Learning","created":"2022-12-31","cited_by_count":721},{"id":"2305.04091","title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","created":"2023-05-06","cited_by_count":560},{"id":"2005.00700","title":"UnifiedQA: Crossing Format Boundaries With a Single QA System","created":"2020-05-02","cited_by_count":476},{"id":"2210.00720","title":"Complexity-Based Prompting for Multi-Step Reasoning","created":"2022-10-03","cited_by_count":388},{"id":"2212.09561","title":"Large Language Models are Better Reasoners with Self-Verification","created":"2022-12-19","cited_by_count":307},{"id":"2212.09597","title":"Reasoning with Language Model Prompting: A Survey","created":"2022-12-19","cited_by_count":252},{"id":"2309.04658","title":"Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf","created":"2023-09-09","cited_by_count":241},{"id":"2308.03188","title":"Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies","created":"2023-08-06","cited_by_count":238},{"id":"2305.08291","title":"Large Language Model Guided Tree-of-Thought","created":"2023-05-15","cited_by_count":221},{"id":"2309.15402","title":"Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future","created":"2023-09-27","cited_by_count":184},{"id":"2310.01320","title":"Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation","created":"2023-10-02","cited_by_count":104},{"id":"2311.08516","title":"LLMs cannot find reasoning errors, but can correct them given the error location","created":"2023-11-14","cited_by_count":85},{"id":"2207.14502","title":"Language Models Can Teach Themselves to Program Better","created":"2022-07-29","cited_by_count":78},{"id":"2311.04254","title":"Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation","created":"2023-11-07","cited_by_count":74},{"id":"2309.17277","title":"Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4","created":"2023-09-29","cited_by_count":68},{"id":"2310.14985","title":"LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay","created":"2023-10-23","cited_by_count":63},{"id":"2310.04959","title":"Towards Better Chain-of-Thought Prompting Strategies: A Survey","created":"2023-10-08","cited_by_count":62},{"id":"2101.00376","title":"RiddleSense: Reasoning about Riddle Questions Featuring Linguistic Creativity and Commonsense Knowledge","created":"2021-01-02","cited_by_count":61},{"id":"2308.08614","title":"Boosting Logical Reasoning in Large Language Models through a New Framework: The Graph of Thought","created":"2023-08-16","cited_by_count":41},{"id":"2303.08033","title":"Large Language Models (GPT) Struggle to Answer Multiple-Choice Questions about Code","created":"2023-03-09","cited_by_count":32},{"id":"2308.12466","title":"Are ChatGPT and GPT-4 Good Poker Players? -- A Pre-Flop Analysis","created":"2023-08-23","cited_by_count":20},{"id":"2310.12342","title":"Eliminating Reasoning via Inferring with Planning: A New Framework to Guide LLMs' Non-linear Thinking","created":"2023-10-18","cited_by_count":19},{"id":"2104.08620","title":"Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLP","created":"2021-04-17","cited_by_count":16},{"id":"1805.07470","title":"Solving the Rubik's Cube Without Human Knowledge","created":"2018-05-18","cited_by_count":15},{"id":"2103.01242","title":"Cryptonite: A Cryptic Crossword Benchmark for Extreme Ambiguity in Language","created":"2021-03-01","cited_by_count":15},{"id":"2311.07387","title":"Assessing Logical Puzzle Solving in Large Language Models: Insights from a Minesweeper Case Study","created":"2023-11-13","cited_by_count":15},{"id":"2109.11087","title":"BiRdQA: A Bilingual Dataset for Question Answering on Tricky Riddles","created":"2021-09-23","cited_by_count":10},{"id":"2109.02797","title":"Puzzle Solving without Search or Human Knowledge: An Unnatural Language Approach","created":"2021-09-07","cited_by_count":8},{"id":"2206.13778","title":"CC-Riddle: A Question Answering Dataset of Chinese Character Riddles","created":"2022-06-28","cited_by_count":6},{"id":"2312.01339","title":"ArabIcros: AI-Powered Arabic Crossword Puzzle Generation for Educational Applications","created":"2023-12-03","cited_by_count":5},{"id":"2401.07181","title":"Reinforcement Learning from LLM Feedback to Counteract Goal Misgeneralization","created":"2024-01-14","cited_by_count":5},{"id":"2112.05742","title":"A Puzzle-Based Dataset for Natural Language Inference","created":"2021-12-10","cited_by_count":4}],"next_cursor":null}