{"list":"other","total":54,"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":"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":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"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":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"id":"2211.14275","title":"Solving math word problems with process- and outcome-based feedback","created":"2022-11-25","cited_by_count":901},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"id":"2210.11610","title":"Large Language Models Can Self-Improve","created":"2022-10-20","cited_by_count":664},{"id":"1705.04146","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","created":"2017-05-11","cited_by_count":650},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"id":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539},{"id":"2210.03057","title":"Language Models are Multilingual Chain-of-Thought Reasoners","created":"2022-10-06","cited_by_count":530},{"id":"1912.10077","title":"Are Transformers universal approximators of sequence-to-sequence functions?","created":"2019-12-20","cited_by_count":406},{"id":"1906.02361","title":"Explain Yourself! Leveraging Language Models for Commonsense Reasoning","created":"2019-06-06","cited_by_count":367},{"id":"1608.01413","title":"Solving General Arithmetic Word Problems","created":"2016-08-04","cited_by_count":360},{"id":"2212.09196","title":"Emergent Analogical Reasoning in Large Language Models","created":"2022-12-19","cited_by_count":240},{"id":"2301.13196","title":"Looped Transformers as Programmable Computers","created":"2023-01-30","cited_by_count":237},{"id":"2207.04901","title":"Exploring Length Generalization in Large Language Models","created":"2022-07-11","cited_by_count":206},{"id":"2305.00586","title":"How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model","created":"2023-04-30","cited_by_count":202},{"id":"1909.07940","title":"Do NLP Models Know Numbers? Probing Numeracy in Embeddings","created":"2019-09-17","cited_by_count":159},{"id":"2202.07206","title":"Impact of Pretraining Term Frequencies on Few-Shot Reasoning","created":"2022-02-15","cited_by_count":142},{"id":"2102.13019","title":"Investigating the Limitations of Transformers with Simple Arithmetic Tasks","created":"2021-02-25","cited_by_count":139},{"id":"2304.02015","title":"How well do Large Language Models perform in Arithmetic tasks?","created":"2023-03-16","cited_by_count":130},{"id":"2211.09066","title":"Teaching Algorithmic Reasoning via In-context Learning","created":"2022-11-15","cited_by_count":112},{"id":"1410.4615","title":"Learning to Execute","created":"2014-10-17","cited_by_count":106},{"id":"2107.13163","title":"Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers","created":"2021-07-28","cited_by_count":102},{"id":"2209.15003","title":"Compositional Semantic Parsing with Large Language Models","created":"2022-09-29","cited_by_count":95},{"id":"2306.00946","title":"Exposing Attention Glitches with Flip-Flop Language Modeling","created":"2023-06-01","cited_by_count":75},{"id":"2108.04378","title":"Making Transformers Solve Compositional Tasks","created":"2021-08-09","cited_by_count":72},{"id":"2208.05051","title":"Limitations of Language Models in Arithmetic and Symbolic Induction","created":"2022-08-09","cited_by_count":71},{"id":"2112.01898","title":"Linear algebra with transformers","created":"2021-12-03","cited_by_count":63},{"id":"2210.11399","title":"Transcending Scaling Laws with 0.1% Extra Compute","created":"2022-10-20","cited_by_count":57},{"id":"1704.06611","title":"Making Neural Programming Architectures Generalize via Recursion","created":"2017-04-21","cited_by_count":35},{"id":"2110.03613","title":"A Data-Centric Approach for Training Deep Neural Networks with Less Data","created":"2021-10-07","cited_by_count":28},{"id":"2211.00170","title":"What is my math transformer doing? -- Three results on interpretability and generalization","created":"2022-10-31","cited_by_count":19},{"id":"2108.06743","title":"Exploring Generalization Ability of Pretrained Language Models on Arithmetic and Logical Reasoning","created":"2021-08-15","cited_by_count":17},{"id":"1406.1584","title":"Learning to Discover Efficient Mathematical Identities","created":"2014-06-06","cited_by_count":9},{"id":"2110.02491","title":"Data-Centric AI Requires Rethinking Data Notion","created":"2021-10-06","cited_by_count":8},{"id":"1312.6192","title":"Can recursive neural tensor networks learn logical reasoning?","created":"2013-12-21","cited_by_count":4},{"id":"1406.1827","title":"Recursive Neural Networks Can Learn Logical Semantics","created":"2014-06-06","cited_by_count":2}],"next_cursor":null}