{"total":105,"rows":[{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103,"area":null},{"id":"2210.10749","title":"Transformers Learn Shortcuts to Automata","created":"2022-10-19","cited_by_count":268,"area":null},{"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,"area":null},{"id":"2310.16028","title":"What Algorithms can Transformers Learn? A Study in Length Generalization","created":"2023-10-24","cited_by_count":199,"area":null},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148,"area":null},{"id":"2204.07580","title":"mGPT: Few-Shot Learners Go Multilingual","created":"2022-04-15","cited_by_count":142,"area":null},{"id":"2307.03381","title":"Teaching Arithmetic to Small Transformers","created":"2023-07-07","cited_by_count":123,"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":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2305.14201","title":"Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks","created":"2023-05-23","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":"2306.00946","title":"Exposing Attention Glitches with Flip-Flop Language Modeling","created":"2023-06-01","cited_by_count":75,"area":null},{"id":"2309.03241","title":"GPT Can Solve Mathematical Problems Without a Calculator","created":"2023-09-06","cited_by_count":68,"area":null},{"id":"2306.15400","title":"Length Generalization in Arithmetic Transformers","created":"2023-06-27","cited_by_count":66,"area":null},{"id":"2402.01035","title":"Getting the most out of your tokenizer for pre-training and domain adaptation","created":"2024-02-01","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":"2503.13423","title":"SuperBPE: Space Travel for Language Models","created":"2025-03-17","cited_by_count":63,"area":null},{"id":"2311.14737","title":"Positional Description Matters for Transformers Arithmetic","created":"2023-11-22","cited_by_count":56,"area":null},{"id":"2402.17810","title":"BioT5+: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning","created":"2024-02-27","cited_by_count":54,"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":"2404.16563","title":"Evaluating Large Language Models on Time Series Feature Understanding: A Comprehensive Taxonomy and Benchmark","created":"2024-04-25","cited_by_count":38,"area":null},{"id":"2309.06236","title":"The first step is the hardest: Pitfalls of Representing and Tokenizing Temporal Data for Large Language Models","created":"2023-09-12","cited_by_count":34,"area":null},{"id":"2402.14547","title":"OmniPred: Language Models as Universal Regressors","created":"2024-02-22","cited_by_count":34,"area":null},{"id":"2411.00566","title":"PatternBoost: Constructions in Mathematics with a Little Help from AI","created":"2024-11-01","cited_by_count":34,"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":"2305.12820","title":"MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering","created":"2023-05-22","cited_by_count":32,"area":null},{"id":"2410.11781","title":"Language Models Encode Numbers Using Digit Representations in Base 10","created":"2024-10-15","cited_by_count":32,"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":"2206.05056","title":"On Neural Architecture Inductive Biases for Relational Tasks","created":"2022-06-09","cited_by_count":26,"area":null},{"id":"2406.19228","title":"Tools Fail: Detecting Silent Errors in Faulty Tools","created":"2024-06-27","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":"2406.02356","title":"Language Models Do Hard Arithmetic Tasks Easily and Hardly Do Easy Arithmetic Tasks","created":"2024-06-04","cited_by_count":24,"area":null},{"id":"2405.20671","title":"Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure","created":"2024-05-31","cited_by_count":23,"area":null},{"id":"2202.04996","title":"AA-TransUNet: Attention Augmented TransUNet For Nowcasting Tasks","created":"2022-02-10","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":"2405.01964","title":"Position: Understanding LLMs Requires More Than Statistical Generalization","created":"2024-05-03","cited_by_count":21,"area":null},{"id":"2211.00170","title":"What is my math transformer doing? -- Three results on interpretability and generalization","created":"2022-10-31","cited_by_count":19,"area":null},{"id":"2411.14708","title":"Understanding LLM Embeddings for Regression","created":"2024-11-22","cited_by_count":19,"area":null},{"id":"2405.06107","title":"Transforming the Bootstrap: Using Transformers to Compute Scattering Amplitudes in Planar N = 4 Super Yang-Mills Theory","created":"2024-05-09","cited_by_count":18,"area":null},{"id":"2108.06743","title":"Exploring Generalization Ability of Pretrained Language Models on Arithmetic and Logical Reasoning","created":"2021-08-15","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":"2506.19004","title":"Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations","created":"2025-06-23","cited_by_count":17,"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":"2304.10977","title":"Evaluating Transformer Language Models on Arithmetic Operations Using Number Decomposition","created":"2023-04-21","cited_by_count":15,"area":null},{"id":"2502.19981","title":"The Lookahead Limitation: Why Multi-Operand Addition is Hard for LLMs","created":"2025-02-27","cited_by_count":15,"area":null},{"id":"2109.04672","title":"Investigating Numeracy Learning Ability of a Text-to-Text Transfer Model","created":"2021-09-10","cited_by_count":13,"area":null},{"id":"2110.09419","title":"Compositional Attention: Disentangling Search and Retrieval","created":"2021-10-18","cited_by_count":12,"area":null},{"id":"2308.01154","title":"Arithmetic with Language Models: from Memorization to Computation","created":"2023-08-02","cited_by_count":12,"area":null},{"id":"2405.19313","title":"Language Models Trained to do Arithmetic Predict Human Risky and Intertemporal Choice","created":"2024-05-29","cited_by_count":12,"area":null},{"id":"2501.19383","title":"Decoding-based Regression","created":"2025-01-31","cited_by_count":12,"area":null},{"id":"2404.00560","title":"A Theory for Length Generalization in Learning to Reason","created":"2024-03-31","cited_by_count":11,"area":null},{"id":"2205.03815","title":"Beyond Distributional Hypothesis: Let Language Models Learn Meaning-Text Correspondence","created":"2022-05-08","cited_by_count":10,"area":null},{"id":"2207.12571","title":"Innovations in Neural Data-to-text Generation: A Survey","created":"2022-07-25","cited_by_count":10,"area":null},{"id":"2208.11445","title":"Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Models","created":"2022-08-24","cited_by_count":10,"area":null},{"id":"2310.11984","title":"From Interpolation to Extrapolation: Complete Length Generalization for Arithmetic Transformers","created":"2023-10-18","cited_by_count":10,"area":null},{"id":"2412.15210","title":"Tokenisation is NP-Complete","created":"2024-12-19","cited_by_count":10,"area":null},{"id":"2409.17391","title":"Scaling Behavior for Large Language Models regarding Numeral Systems: An Example using Pythia","created":"2024-09-25","cited_by_count":8,"area":null},{"id":"2402.01082","title":"Salsa Fresca: Angular Embeddings and Pre-Training for ML Attacks on Learning With Errors","created":"2024-02-02","cited_by_count":7,"area":null},{"id":"2405.15722","title":"Models That Prove Their Own Correctness","created":"2024-05-24","cited_by_count":7,"area":null},{"id":"2410.18077","title":"ALTA: Compiler-Based Analysis of Transformers","created":"2024-10-23","cited_by_count":7,"area":null},{"id":"2502.11525","title":"Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs","created":"2025-02-17","cited_by_count":7,"area":null},{"id":"2510.06824","title":"Efficient numeracy in language models through single-token number embeddings","created":"2025-10-08","cited_by_count":7,"area":null},{"id":"2512.15134","title":"From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?","created":"2025-12-17","cited_by_count":7,"area":null},{"id":"2211.07455","title":"Towards Robust Numerical Question Answering: Diagnosing Numerical Capabilities of NLP Systems","created":"2022-11-14","cited_by_count":6,"area":null},{"id":"2408.04720","title":"Learning the Simplicity of Scattering Amplitudes","created":"2024-08-08","cited_by_count":6,"area":null},{"id":"2405.16727","title":"Disentangling and Integrating Relational and Sensory Information in Transformer Architectures","created":"2024-05-26","cited_by_count":5,"area":null},{"id":"2411.05943","title":"Quantifying artificial intelligence through algorithmic generalization","created":"2024-11-08","cited_by_count":5,"area":null},{"id":"2502.18273","title":"Beyond In-Distribution Success: Scaling Curves of CoT Granularity for Language Model Generalization","created":"2025-02-25","cited_by_count":5,"area":null},{"id":"2402.18678","title":"RORA: Robust Free-Text Rationale Evaluation","created":"2024-02-28","cited_by_count":4,"area":null},{"id":"2502.16763","title":"Learning to Add, Multiply, and Execute Algorithmic Instructions Exactly with Neural Networks","created":"2025-02-24","cited_by_count":4,"area":null},{"id":"2506.11769","title":"Long-Short Alignment for Effective Long-Context Modeling in LLMs","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2510.14826","title":"To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models","created":"2025-10-16","cited_by_count":4,"area":null},{"id":"2603.02238","title":"Length Generalization Bounds for Transformers","created":"2026-02-13","cited_by_count":4,"area":null},{"id":"2402.07543","title":"Show Me How It's Done: The Role of Explanations in Fine-Tuning Language Models","created":"2024-02-12","cited_by_count":3,"area":null},{"id":"2502.12717","title":"Learning the symmetric group: large from small","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2508.06030","title":"Efficient Knowledge Probing of Large Language Models by Adapting Pre-trained Embeddings","created":"2025-08-08","cited_by_count":3,"area":null},{"id":"2510.18196","title":"Contrastive Decoding Mitigates Score Range Bias in LLM-as-a-Judge","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2604.13082","title":"The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior","created":"2026-03-30","cited_by_count":3,"area":null},{"id":"2308.08268","title":"It Ain't That Bad: Understanding the Mysterious Performance Drop in OOD Generalization for Generative Transformer Models","created":"2023-08-16","cited_by_count":2,"area":null},{"id":"2407.04787","title":"Re-Tuning: Overcoming the Compositionality Limits of Large Language Models with Recursive Tuning","created":"2024-07-05","cited_by_count":2,"area":null},{"id":"2409.13728","title":"Rule Extrapolation in Language Models: A Study of Compositional Generalization on OOD Prompts","created":"2024-09-09","cited_by_count":2,"area":null},{"id":"2606.02384","title":"TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks","created":"2026-06-01","cited_by_count":2,"area":null},{"id":"2306.12198","title":"Opening the Black Box: Analyzing Attention Weights and Hidden States in Pre-trained Language Models for Non-language Tasks","created":"2023-06-21","cited_by_count":1,"area":null},{"id":"2306.12205","title":"Investigating Pre-trained Language Models on Cross-Domain Datasets, a Step Closer to General AI","created":"2023-06-21","cited_by_count":1,"area":null},{"id":"2310.06204","title":"Estimating Numbers without Regression","created":"2023-10-09","cited_by_count":1,"area":null},{"id":"2403.05713","title":"tsGT: Stochastic Time Series Modeling With Transformer","created":"2024-03-08","cited_by_count":1,"area":null},{"id":"2404.01182","title":"A Neuro-Symbolic Approach to Monitoring Salt Content in Food","created":"2024-04-01","cited_by_count":1,"area":null},{"id":"2404.01536","title":"Laying Anchors: Semantically Priming Numerals in Language Modeling","created":"2024-04-02","cited_by_count":1,"area":null},{"id":"2407.10283","title":"Numbers Matter! Bringing Quantity-awareness to Retrieval Systems","created":"2024-07-14","cited_by_count":1,"area":null},{"id":"2502.17513","title":"Int2Int: a framework for mathematics with transformers","created":"2025-02-22","cited_by_count":1,"area":null},{"id":"2601.15251","title":"The Effect of Scripts and Formats on LLM Numeracy","created":"2026-01-21","cited_by_count":1,"area":null},{"id":"2601.15714","title":"Even GPT-5.2 Can't Count to Five: The Case for Zero-Error Horizons in Trustworthy LLMs","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2602.10416","title":"AI-rithmetic","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2211.15416","title":"Development of a Neural Network-Based Mathematical Operation Protocol for Embedded Hexadecimal Digits Using Neural Architecture Search (NAS)","created":"2022-11-12","cited_by_count":0,"area":null},{"id":"2401.07993","title":"Carrying over algorithm in transformers","created":"2024-01-15","cited_by_count":0,"area":null},{"id":"2406.00075","title":"Arbitrary-Length Generalization for Addition in a Tiny Transformer","created":"2024-05-31","cited_by_count":0,"area":null},{"id":"2407.14430","title":"The Extrapolation Power of Implicit Models","created":"2024-07-19","cited_by_count":0,"area":null},{"id":"2502.00197","title":"Learning Model Successors","created":"2025-01-31","cited_by_count":0,"area":null},{"id":"2507.10678","title":"A Group Theoretic Analysis of the Symmetries Underlying Base Addition and Their Learnability by Neural Networks","created":"2025-07-14","cited_by_count":0,"area":null}],"next_cursor":"100"}