{"total":217,"rows":[{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371,"area":null},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780,"area":null},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713,"area":null},{"id":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629,"area":null},{"id":"2109.00110","title":"MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics","created":"2021-08-31","cited_by_count":391,"area":null},{"id":"2305.19466","title":"The Impact of Positional Encoding on Length Generalization in Transformers","created":"2023-05-31","cited_by_count":327,"area":null},{"id":"2205.11491","title":"HyperTree Proof Search for Neural Theorem Proving","created":"2022-05-23","cited_by_count":197,"area":null},{"id":"2106.06427","title":"Neural Symbolic Regression that Scales","created":"2021-06-11","cited_by_count":192,"area":null},{"id":"2305.12524","title":"TheoremQA: A Theorem-driven Question Answering dataset","created":"2023-05-21","cited_by_count":192,"area":null},{"id":"2208.03306","title":"Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models","created":"2022-08-05","cited_by_count":191,"area":null},{"id":"2311.11045","title":"Orca 2: Teaching Small Language Models How to Reason","created":"2023-11-18","cited_by_count":159,"area":null},{"id":"2204.06031","title":"A Review on Language Models as Knowledge Bases","created":"2022-04-12","cited_by_count":157,"area":null},{"id":"2202.05441","title":"Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs","created":"2022-02-11","cited_by_count":144,"area":null},{"id":"2302.11055","title":"SGD learning on neural networks: leap complexity and saddle-to-saddle dynamics","created":"2023-02-21","cited_by_count":143,"area":null},{"id":"2102.13019","title":"Investigating the Limitations of Transformers with Simple Arithmetic Tasks","created":"2021-02-25","cited_by_count":139,"area":null},{"id":"2108.12284","title":"The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers","created":"2021-08-26","cited_by_count":117,"area":null},{"id":"2402.14903","title":"Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs","created":"2024-02-22","cited_by_count":115,"area":null},{"id":"2405.12209","title":"MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark","created":"2024-05-20","cited_by_count":105,"area":null},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2206.06336","title":"Language Models are General-Purpose Interfaces","created":"2022-06-13","cited_by_count":97,"area":null},{"id":"2106.06295","title":"Going Beyond Linear Transformers with Recurrent Fast Weight Programmers","created":"2021-06-11","cited_by_count":89,"area":null},{"id":"2103.05045","title":"Size-Invariant Graph Representations for Graph Classification Extrapolations","created":"2021-03-08","cited_by_count":84,"area":null},{"id":"2103.13136","title":"Representing Numbers in NLP: a Survey and a Vision","created":"2021-03-24","cited_by_count":83,"area":null},{"id":"2104.01112","title":"NaturalProofs: Mathematical Theorem Proving in Natural Language","created":"2021-03-24","cited_by_count":81,"area":null},{"id":"2112.03806","title":"OOD-GNN: Out-of-Distribution Generalized Graph Neural Network","created":"2021-12-07","cited_by_count":78,"area":null},{"id":"2405.17399","title":"Transformers Can Do Arithmetic with the Right Embeddings","created":"2024-05-27","cited_by_count":78,"area":null},{"id":"2310.18313","title":"FP8-LM: Training FP8 Large Language Models","created":"2023-10-27","cited_by_count":77,"area":null},{"id":"2301.13105","title":"Generalization on the Unseen, Logic Reasoning and Degree Curriculum","created":"2023-01-30","cited_by_count":73,"area":null},{"id":"2205.12910","title":"NaturalProver: Grounded Mathematical Proof Generation with Language Models","created":"2022-05-25","cited_by_count":72,"area":null},{"id":"2308.04430","title":"SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore","created":"2023-08-08","cited_by_count":71,"area":null},{"id":"2308.16149","title":"Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models","created":"2023-08-30","cited_by_count":69,"area":null},{"id":"2312.17120","title":"MathPile: A Billion-Token-Scale Pretraining Corpus for Math","created":"2023-12-28","cited_by_count":67,"area":null},{"id":"2304.14979","title":"MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks","created":"2023-04-28","cited_by_count":66,"area":null},{"id":"2112.01898","title":"Linear algebra with transformers","created":"2021-12-03","cited_by_count":63,"area":null},{"id":"2407.15390","title":"ALLaM: Large Language Models for Arabic and English","created":"2024-07-22","cited_by_count":55,"area":null},{"id":"2201.04600","title":"Deep Symbolic Regression for Recurrent Sequences","created":"2022-01-12","cited_by_count":54,"area":null},{"id":"2406.11385","title":"MetaGPT: Merging Large Language Models Using Model Exclusive Task Arithmetic","created":"2024-06-17","cited_by_count":53,"area":null},{"id":"2104.06598","title":"AR-LSAT: Investigating Analytical Reasoning of Text","created":"2021-04-14","cited_by_count":51,"area":null},{"id":"2505.13898","title":"Do Language Models Use Their Depth Efficiently?","created":"2025-05-20","cited_by_count":50,"area":null},{"id":"2310.02227","title":"SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training","created":"2023-10-03","cited_by_count":47,"area":null},{"id":"2404.02893","title":"ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline","created":"2024-04-03","cited_by_count":47,"area":null},{"id":"2101.06223","title":"LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning","created":"2021-01-15","cited_by_count":46,"area":null},{"id":"2305.09955","title":"Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models","created":"2023-05-17","cited_by_count":46,"area":null},{"id":"2409.01659","title":"Interpreting and Improving Large Language Models in Arithmetic Calculation","created":"2024-09-03","cited_by_count":45,"area":null},{"id":"2301.10884","title":"Break It Down: Evidence for Structural Compositionality in Neural Networks","created":"2023-01-26","cited_by_count":44,"area":null},{"id":"2407.08351","title":"AutoBencher: Towards Declarative Benchmark Construction","created":"2024-07-11","cited_by_count":44,"area":null},{"id":"2201.07311","title":"Datasheet for the Pile","created":"2022-01-13","cited_by_count":43,"area":null},{"id":"2411.03766","title":"Number Cookbook: Number Understanding of Language Models and How to Improve It","created":"2024-11-06","cited_by_count":42,"area":null},{"id":"2310.18362","title":"SoK: Memorization in General-Purpose Large Language Models","created":"2023-10-24","cited_by_count":37,"area":null},{"id":"2406.06467","title":"How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad","created":"2024-06-10","cited_by_count":36,"area":null},{"id":"2107.00101","title":"Latent Execution for Neural Program Synthesis","created":"2021-06-29","cited_by_count":35,"area":null},{"id":"2210.15889","title":"Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing","created":"2022-10-28","cited_by_count":35,"area":null},{"id":"2406.10323","title":"GenQA: Generating Millions of Instructions from a Handful of Prompts","created":"2024-06-14","cited_by_count":35,"area":null},{"id":"2105.14802","title":"On Compositional Generalization of Neural Machine Translation","created":"2021-05-31","cited_by_count":34,"area":null},{"id":"2305.05383","title":"Code Execution with Pre-trained Language Models","created":"2023-05-08","cited_by_count":34,"area":null},{"id":"2206.01962","title":"Formal Specifications from Natural Language","created":"2022-06-04","cited_by_count":33,"area":null},{"id":"2308.15594","title":"Learning the greatest common divisor: explaining transformer predictions","created":"2023-08-29","cited_by_count":33,"area":null},{"id":"2311.07568","title":"Feature emergence via margin maximization: case studies in algebraic tasks","created":"2023-11-13","cited_by_count":33,"area":null},{"id":"2104.02746","title":"Proof of the Theory-to-Practice Gap in Deep Learning via Sampling Complexity bounds for Neural Network Approximation Spaces","created":"2021-04-06","cited_by_count":30,"area":null},{"id":"2203.09978","title":"WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series","created":"2022-03-18","cited_by_count":30,"area":null},{"id":"2103.10685","title":"Controllable Generation from Pre-trained Language Models via Inverse Prompting","created":"2021-03-19","cited_by_count":29,"area":null},{"id":"2107.12580","title":"Pointer Value Retrieval: A new benchmark for understanding the limits of neural network generalization","created":"2021-07-27","cited_by_count":29,"area":null},{"id":"2110.02782","title":"How BPE Affects Memorization in Transformers","created":"2021-10-06","cited_by_count":29,"area":null},{"id":"2306.01103","title":"Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization","created":"2023-06-01","cited_by_count":29,"area":null},{"id":"2207.04785","title":"SALSA: Attacking Lattice Cryptography with Transformers","created":"2022-07-11","cited_by_count":28,"area":null},{"id":"2109.13986","title":"Symbolic Brittleness in Sequence Models: on Systematic Generalization in Symbolic Mathematics","created":"2021-09-28","cited_by_count":27,"area":null},{"id":"2505.13077","title":"Advancing Sequential Numerical Prediction in Autoregressive Models","created":"2025-05-19","cited_by_count":26,"area":null},{"id":"2102.03406","title":"Symbolic Behaviour in Artificial Intelligence","created":"2021-02-05","cited_by_count":25,"area":null},{"id":"2312.07622","title":"Mathematical Language Models: A Survey","created":"2023-12-12","cited_by_count":24,"area":null},{"id":"2407.08582","title":"On the Universal Truthfulness Hyperplane Inside LLMs","created":"2024-07-11","cited_by_count":24,"area":null},{"id":"2501.04961","title":"Demystifying Domain-adaptive Post-training for Financial LLMs","created":"2025-01-09","cited_by_count":24,"area":null},{"id":"2106.03921","title":"Measuring and Improving BERT's Mathematical Abilities by Predicting the Order of Reasoning","created":"2021-06-07","cited_by_count":23,"area":null},{"id":"2206.15030","title":"Modern Question Answering Datasets and Benchmarks: A Survey","created":"2022-06-30","cited_by_count":23,"area":null},{"id":"2110.14207","title":"How Much Coffee Was Consumed During EMNLP 2019? Fermi Problems: A New Reasoning Challenge for AI","created":"2021-10-27","cited_by_count":22,"area":null},{"id":"2502.09741","title":"FoNE: Precise Single-Token Number Embeddings via Fourier Features","created":"2025-02-13","cited_by_count":22,"area":null},{"id":"2604.03444","title":"Olmo Hybrid: From Theory to Practice and Back","created":"2026-04-03","cited_by_count":22,"area":null},{"id":"2410.04194","title":"Consistent Autoformalization for Constructing Mathematical Libraries","created":"2024-10-05","cited_by_count":21,"area":null},{"id":"2109.05925","title":"Adversarial Examples for Evaluating Math Word Problem Solvers","created":"2021-09-13","cited_by_count":20,"area":null},{"id":"2303.14770","title":"Koala: An Index for Quantifying Overlaps with Pre-training Corpora","created":"2023-03-26","cited_by_count":19,"area":null},{"id":"2405.03146","title":"Quantifying the Capabilities of LLMs across Scale and Precision","created":"2024-05-06","cited_by_count":19,"area":null},{"id":"2411.08324","title":"Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle","created":"2024-11-13","cited_by_count":19,"area":null},{"id":"2507.12466","title":"Language Models Improve When Pretraining Data Matches Target Tasks","created":"2025-07-16","cited_by_count":19,"area":null},{"id":"2402.18039","title":"ResLoRA: Identity Residual Mapping in Low-Rank Adaption","created":"2024-02-28","cited_by_count":18,"area":null},{"id":"2110.03501","title":"Pretrained Language Models are Symbolic Mathematics Solvers too!","created":"2021-10-07","cited_by_count":17,"area":null},{"id":"2409.19808","title":"Can Models Learn Skill Composition from Examples?","created":"2024-09-29","cited_by_count":17,"area":null},{"id":"2410.04368","title":"Algorithmic Capabilities of Random Transformers","created":"2024-10-06","cited_by_count":17,"area":null},{"id":"2105.03928","title":"Which transformer architecture fits my data? A vocabulary bottleneck in self-attention","created":"2021-05-09","cited_by_count":16,"area":null},{"id":"2505.14279","title":"YESciEval: Robust LLM-as-a-Judge for Scientific Question Answering","created":"2025-05-20","cited_by_count":16,"area":null},{"id":"2506.18110","title":"RL for Reasoning by Adaptively Revealing Rationales","created":"2025-06-22","cited_by_count":16,"area":null},{"id":"2109.02102","title":"Teaching Autoregressive Language Models Complex Tasks By Demonstration","created":"2021-09-05","cited_by_count":15,"area":null},{"id":"2206.04115","title":"Simplifying Polylogarithms with Machine Learning","created":"2022-06-08","cited_by_count":15,"area":null},{"id":"2304.10977","title":"Evaluating Transformer Language Models on Arithmetic Operations Using Number Decomposition","created":"2023-04-21","cited_by_count":15,"area":null},{"id":"2305.12199","title":"VNHSGE: VietNamese High School Graduation Examination Dataset for Large Language Models","created":"2023-05-20","cited_by_count":15,"area":null},{"id":"2510.14751","title":"Beyond Multi-Token Prediction: Pretraining LLMs with Future Summaries","created":"2025-10-16","cited_by_count":15,"area":null},{"id":"2603.10055","title":"Training Language Models via Neural Cellular Automata","created":"2026-03-09","cited_by_count":15,"area":null},{"id":"2402.17205","title":"Measuring Vision-Language STEM Skills of Neural Models","created":"2024-02-27","cited_by_count":14,"area":null},{"id":"2112.03204","title":"Quantifying Adaptability in Pre-trained Language Models with 500 Tasks","created":"2021-12-06","cited_by_count":13,"area":null},{"id":"2402.05785","title":"Limits of Transformer Language Models on Learning to Compose Algorithms","created":"2024-02-08","cited_by_count":13,"area":null},{"id":"2411.02083","title":"Regress, Don't Guess -- A Regression-like Loss on Number Tokens for Language Models","created":"2024-11-04","cited_by_count":13,"area":null},{"id":"2502.15343","title":"Tokenization is Sensitive to Language Variation","created":"2025-02-21","cited_by_count":13,"area":null}],"next_cursor":"100"}