{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2210.11610","title":"Large Language Models Can Self-Improve","created":"2022-10-20","cited_by_count":664},{"id":"2305.18654","title":"Faith and Fate: Limits of Transformers on Compositionality","created":"2023-05-29","cited_by_count":503},{"id":"1905.08094","title":"Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation","created":"2019-05-17","cited_by_count":497},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467},{"id":"2305.17493","title":"The Curse of Recursion: Training on Generated Data Makes Models Forget","created":"2023-05-27","cited_by_count":356},{"id":"2312.06585","title":"Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models","created":"2023-12-11","cited_by_count":349},{"id":"2305.19466","title":"The Impact of Positional Encoding on Length Generalization in Transformers","created":"2023-05-31","cited_by_count":327},{"id":"1908.08351","title":"Compositionality decomposed: how do neural networks generalise?","created":"2019-08-22","cited_by_count":265},{"id":"2307.01850","title":"Self-Consuming Generative Models Go MAD","created":"2023-07-04","cited_by_count":250},{"id":"2405.14838","title":"From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step","created":"2024-05-23","cited_by_count":235},{"id":"2402.06457","title":"V-STaR: Training Verifiers for Self-Taught Reasoners","created":"2024-02-09","cited_by_count":217},{"id":"2207.04901","title":"Exploring Length Generalization in Large Language Models","created":"2022-07-11","cited_by_count":206},{"id":"2310.16028","title":"What Algorithms can Transformers Learn? A Study in Length Generalization","created":"2023-10-24","cited_by_count":199},{"id":"1705.10694","title":"Deep Learning is Robust to Massive Label Noise","created":"2017-05-30","cited_by_count":165},{"id":"2403.06963","title":"The pitfalls of next-token prediction","created":"2024-03-11","cited_by_count":160},{"id":"2404.01413","title":"Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data","created":"2024-04-01","cited_by_count":151},{"id":"2402.07043","title":"A Tale of Tails: Model Collapse as a Change of Scaling Laws","created":"2024-02-10","cited_by_count":130},{"id":"2010.08853","title":"From Local Structures to Size Generalization in Graph Neural Networks","created":"2020-10-17","cited_by_count":124},{"id":"2307.03381","title":"Teaching Arithmetic to Small Transformers","created":"2023-07-07","cited_by_count":123},{"id":"2106.04537","title":"Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks","created":"2021-06-08","cited_by_count":117},{"id":"2305.16843","title":"Randomized Positional Encodings Boost Length Generalization of Transformers","created":"2023-05-26","cited_by_count":117},{"id":"2310.00429","title":"On the Stability of Iterative Retraining of Generative Models on their own Data","created":"2023-09-30","cited_by_count":100},{"id":"2409.15647","title":"Looped Transformers for Length Generalization","created":"2024-09-24","cited_by_count":99},{"id":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96},{"id":"2402.09371","title":"Transformers Can Achieve Length Generalization But Not Robustly","created":"2024-02-14","cited_by_count":86},{"id":"2410.05192","title":"Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape Perspective","created":"2024-10-07","cited_by_count":81},{"id":"2311.16822","title":"Large Language Models Suffer From Their Own Output: An Analysis of the Self-Consuming Training Loop","created":"2023-11-28","cited_by_count":79},{"id":"2405.17399","title":"Transformers Can Do Arithmetic with the Right Embeddings","created":"2024-05-27","cited_by_count":78},{"id":"2306.15400","title":"Length Generalization in Arithmetic Transformers","created":"2023-06-27","cited_by_count":66},{"id":"2408.16737","title":"Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling","created":"2024-08-29","cited_by_count":61},{"id":"2211.08095","title":"Will Large-scale Generative Models Corrupt Future Datasets?","created":"2022-11-15","cited_by_count":59},{"id":"2311.14737","title":"Positional Description Matters for Transformers Arithmetic","created":"2023-11-22","cited_by_count":56},{"id":"2010.07174","title":"The EOS Decision and Length Extrapolation","created":"2020-10-14","cited_by_count":46},{"id":"2303.01255","title":"Combining Generative Artificial Intelligence (AI) and the Internet: Heading towards Evolution or Degradation?","created":"2023-02-17","cited_by_count":41},{"id":"2401.06751","title":"The Unreasonable Effectiveness of Easy Training Data for Hard Tasks","created":"2024-01-12","cited_by_count":40},{"id":"2402.07087","title":"Self-Correcting Self-Consuming Loops for Generative Model Training","created":"2024-02-11","cited_by_count":37},{"id":"2310.13121","title":"Understanding Addition in Transformers","created":"2023-10-19","cited_by_count":34},{"id":"2411.00566","title":"PatternBoost: Constructions in Mathematics with a Little Help from AI","created":"2024-11-01","cited_by_count":34},{"id":"1911.03872","title":"Location Attention for Extrapolation to Longer Sequences","created":"2019-11-10","cited_by_count":33},{"id":"2408.08072","title":"I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement Paradigm","created":"2024-08-15","cited_by_count":27},{"id":"2405.20671","title":"Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure","created":"2024-05-31","cited_by_count":23},{"id":"2412.03881","title":"Weak-to-Strong Generalization Through the Data-Centric Lens","created":"2024-12-05","cited_by_count":21},{"id":"2406.11741","title":"Transcendence: Generative Models Can Outperform The Experts That Train Them","created":"2024-06-17","cited_by_count":20},{"id":"2412.07684","title":"The Pitfalls of Memorization: When Memorization Hurts Generalization","created":"2024-12-10","cited_by_count":19},{"id":"2410.02108","title":"ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement","created":"2024-10-03","cited_by_count":18},{"id":"2406.01895","title":"Explicitly Encoding Structural Symmetry is Key to Length Generalization in Arithmetic Tasks","created":"2024-06-04","cited_by_count":11},{"id":"2310.11984","title":"From Interpolation to Extrapolation: Complete Length Generalization for Arithmetic Transformers","created":"2023-10-18","cited_by_count":10},{"id":"2309.08589","title":"Chain-of-Thought Reasoning is a Policy Improvement Operator","created":"2023-09-15","cited_by_count":8}],"next_cursor":null}