{"total":112,"rows":[{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392,"area":"lr"},{"id":"2309.05653","title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","created":"2023-09-11","cited_by_count":487,"area":null},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403,"area":"lr"},{"id":"2212.09597","title":"Reasoning with Language Model Prompting: A Survey","created":"2022-12-19","cited_by_count":252,"area":"lr"},{"id":"2209.00840","title":"FOLIO: Natural Language Reasoning with First-Order Logic","created":"2022-09-02","cited_by_count":235,"area":"lr"},{"id":"2404.16789","title":"Continual Learning of Large Language Models: A Comprehensive Survey","created":"2024-04-25","cited_by_count":234,"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":"2404.02078","title":"Advancing LLM Reasoning Generalists with Preference Trees","created":"2024-04-02","cited_by_count":192,"area":"lr"},{"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,"area":"lr"},{"id":"2311.11045","title":"Orca 2: Teaching Small Language Models How to Reason","created":"2023-11-18","cited_by_count":159,"area":null},{"id":"2402.19255","title":"GSM-Plus: A Comprehensive Benchmark for Evaluating the Robustness of LLMs as Mathematical Problem Solvers","created":"2024-02-29","cited_by_count":158,"area":"lr"},{"id":"2402.14830","title":"Orca-Math: Unlocking the potential of SLMs in Grade School Math","created":"2024-02-16","cited_by_count":151,"area":"lr"},{"id":"2212.02746","title":"UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression","created":"2022-12-06","cited_by_count":137,"area":"lr"},{"id":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135,"area":null},{"id":"2212.10535","title":"A Survey of Deep Learning for Mathematical Reasoning","created":"2022-12-20","cited_by_count":124,"area":"lr"},{"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":"2305.15023","title":"Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models","created":"2023-05-24","cited_by_count":101,"area":null},{"id":"2410.11325","title":"Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling","created":"2024-10-15","cited_by_count":90,"area":"distill"},{"id":"2305.15054","title":"A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis","created":"2023-05-24","cited_by_count":89,"area":"lr"},{"id":"2401.06838","title":"MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization","created":"2024-01-12","cited_by_count":69,"area":"lr"},{"id":"2210.12023","title":"A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models","created":"2022-10-21","cited_by_count":68,"area":"lr"},{"id":"2404.15522","title":"LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models","created":"2024-04-23","cited_by_count":68,"area":"lr"},{"id":"2310.06762","title":"TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models","created":"2023-10-10","cited_by_count":66,"area":"alignment"},{"id":"2402.18865","title":"Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning","created":"2024-02-29","cited_by_count":60,"area":null},{"id":"2310.04928","title":"Large Language Models Only Pass Primary School Exams in Indonesia: A Comprehensive Test on IndoMMLU","created":"2023-10-07","cited_by_count":53,"area":"lr"},{"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":"2403.07384","title":"SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models","created":"2024-03-12","cited_by_count":44,"area":null},{"id":"2401.07950","title":"SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models","created":"2024-01-15","cited_by_count":39,"area":null},{"id":"2406.03445","title":"Pre-trained Large Language Models Use Fourier Features to Compute Addition","created":"2024-06-05","cited_by_count":39,"area":"lr"},{"id":"2205.12538","title":"Is a Question Decomposition Unit All We Need?","created":"2022-05-25","cited_by_count":37,"area":null},{"id":"2310.00836","title":"Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models","created":"2023-10-02","cited_by_count":35,"area":"lr"},{"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":"2410.19313","title":"COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training","created":"2024-10-25","cited_by_count":33,"area":null},{"id":"2305.16896","title":"MultiTool-CoT: GPT-3 Can Use Multiple External Tools with Chain of Thought Prompting","created":"2023-05-26","cited_by_count":27,"area":"lr"},{"id":"2404.02827","title":"BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models","created":"2024-04-03","cited_by_count":27,"area":null},{"id":"2411.07602","title":"Circuit Complexity Bounds for RoPE-based Transformer Architecture","created":"2024-11-12","cited_by_count":26,"area":null},{"id":"2312.07622","title":"Mathematical Language Models: A Survey","created":"2023-12-12","cited_by_count":24,"area":null},{"id":"2410.01920","title":"Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlo","created":"2024-10-02","cited_by_count":22,"area":"lr"},{"id":"2502.12065","title":"Autoformalization in the Wild: Assessing LLMs on Real-World Mathematical Definitions","created":"2025-02-17","cited_by_count":22,"area":null},{"id":"2412.11041","title":"Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models","created":"2024-12-15","cited_by_count":20,"area":"alignment"},{"id":"2502.01618","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","created":"2025-02-03","cited_by_count":20,"area":"lr"},{"id":"2408.15778","title":"LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language Models","created":"2024-08-28","cited_by_count":19,"area":"lr"},{"id":"2303.07735","title":"Can neural networks do arithmetic? A survey on the elementary numerical skills of state-of-the-art deep learning models","created":"2023-03-14","cited_by_count":18,"area":"lr"},{"id":"2410.02108","title":"ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement","created":"2024-10-03","cited_by_count":18,"area":"lr"},{"id":"2204.07600","title":"In-BoXBART: Get Instructions into Biomedical Multi-Task Learning","created":"2022-04-15","cited_by_count":16,"area":null},{"id":"2210.07471","title":"\"John is 50 years old, can his son be 65?\" Evaluating NLP Models' Understanding of Feasibility","created":"2022-10-14","cited_by_count":15,"area":null},{"id":"2310.02439","title":"Novice Learner and Expert Tutor: Evaluating Math Reasoning Abilities of Large Language Models with Misconceptions","created":"2023-10-03","cited_by_count":15,"area":"lr"},{"id":"2408.07089","title":"InfinityMATH: A Scalable Instruction Tuning Dataset in Programmatic Mathematical Reasoning","created":"2024-08-09","cited_by_count":15,"area":"lr"},{"id":"2211.16482","title":"Chaining Simultaneous Thoughts for Numerical Reasoning","created":"2022-11-29","cited_by_count":14,"area":null},{"id":"2210.17517","title":"Lila: A Unified Benchmark for Mathematical Reasoning","created":"2022-10-31","cited_by_count":13,"area":"lr"},{"id":"2402.13764","title":"CriticEval: Evaluating Large Language Model as Critic","created":"2024-02-21","cited_by_count":13,"area":null},{"id":"2308.07902","title":"Through the Lens of Core Competency: Survey on Evaluation of Large Language Models","created":"2023-08-15","cited_by_count":12,"area":null},{"id":"2404.13099","title":"Mathify: Evaluating Large Language Models on Mathematical Problem Solving Tasks","created":"2024-04-19","cited_by_count":12,"area":null},{"id":"2407.19580","title":"Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures","created":"2024-07-28","cited_by_count":12,"area":null},{"id":"2503.17726","title":"A Survey on Mathematical Reasoning and Optimization with Large Language Models","created":"2025-03-22","cited_by_count":12,"area":"lr"},{"id":"2402.15729","title":"How Do Humans Write Code? Large Models Do It the Same Way Too","created":"2024-02-24","cited_by_count":11,"area":"lr"},{"id":"2412.15184","title":"Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning","created":"2024-12-19","cited_by_count":11,"area":null},{"id":"2502.07274","title":"Forget Forgetting: Continual Learning in a World of Abundant Memory","created":"2025-02-11","cited_by_count":11,"area":null},{"id":"2506.02011","title":"OASIS: Online Sample Selection for Continual Visual Instruction Tuning","created":"2025-05-27","cited_by_count":9,"area":null},{"id":"2205.09898","title":"Let the Model Decide its Curriculum for Multitask Learning","created":"2022-05-19","cited_by_count":8,"area":null},{"id":"2407.21571","title":"PMoE: Progressive Mixture of Experts with Asymmetric Transformer for Continual Learning","created":"2024-07-31","cited_by_count":8,"area":"moe"},{"id":"2409.20303","title":"A Looming Replication Crisis in Evaluating Behavior in Language Models? Evidence and Solutions","created":"2024-09-30","cited_by_count":8,"area":null},{"id":"2505.21505","title":"How Does Alignment Enhance LLMs' Multilingual Capabilities? A Language Neurons Perspective","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2605.29495","title":"On-Policy Replay for Continual Supervised Fine-Tuning","created":"2026-05-28","cited_by_count":8,"area":"distill"},{"id":"2205.12496","title":"Teaching Broad Reasoning Skills for Multi-Step QA by Generating Hard Contexts","created":"2022-05-25","cited_by_count":7,"area":"lr"},{"id":"2305.13179","title":"Teaching Probabilistic Logical Reasoning to Transformers","created":"2023-05-22","cited_by_count":7,"area":"lr"},{"id":"2402.15861","title":"MATHWELL: Generating Educational Math Word Problems Using Teacher Annotations","created":"2024-02-24","cited_by_count":7,"area":null},{"id":"2310.10062","title":"A Comprehensive Evaluation of Tool-Assisted Generation Strategies","created":"2023-10-16","cited_by_count":6,"area":null},{"id":"2311.01230","title":"Multi-Operational Mathematical Derivations in Latent Space","created":"2023-11-02","cited_by_count":6,"area":null},{"id":"2505.13406","title":"AutoMathKG: The automated mathematical knowledge graph based on LLM and vector database","created":"2025-05-19","cited_by_count":6,"area":null},{"id":"2505.21963","title":"LaMDAgent: An Autonomous Framework for Post-Training Pipeline Optimization via LLM Agents","created":"2025-05-28","cited_by_count":6,"area":"agents"},{"id":"2510.08988","title":"MASA: LLM-Driven Multi-Agent Systems for Autoformalization","created":"2025-10-10","cited_by_count":6,"area":"agents"},{"id":"2309.04635","title":"Can NLP Models 'Identify', 'Distinguish', and 'Justify' Questions that Don't have a Definitive Answer?","created":"2023-09-08","cited_by_count":4,"area":null},{"id":"2402.11432","title":"Can Deception Detection Go Deeper? Dataset, Evaluation, and Benchmark for Deception Reasoning","created":"2024-02-18","cited_by_count":4,"area":null},{"id":"2507.11936","title":"A Survey of Deep Learning for Geometry Problem Solving","created":"2025-07-16","cited_by_count":4,"area":"lr"},{"id":"2508.00459","title":"Thinking Machines: Mathematical Reasoning in the Age of LLMs","created":"2025-08-01","cited_by_count":4,"area":"lr"},{"id":"2510.05825","title":"Mitigating Premature Exploitation in Particle-based Monte Carlo for Inference-Time Scaling","created":"2025-10-07","cited_by_count":4,"area":"lr"},{"id":"2305.17491","title":"FERMAT: An Alternative to Accuracy for Numerical Reasoning","created":"2023-05-27","cited_by_count":3,"area":"lr"},{"id":"2510.07118","title":"TRIM: Token-wise Attention-Derived Saliency for Data-Efficient Instruction Tuning","created":"2025-10-08","cited_by_count":3,"area":"alignment"},{"id":"2601.21225","title":"MGSM-Pro: A Simple Strategy for Robust Multilingual Mathematical Reasoning Evaluation","created":"2026-01-29","cited_by_count":3,"area":"lr"},{"id":"2412.01004","title":"Take Only What You Need: Rank Minimization as an Implicit Forgetting Regularizer in Continual Learning","created":"2024-12-01","cited_by_count":2,"area":null},{"id":"2511.05811","title":"MOSS: Efficient and Accurate FP8 LLM Training with Microscaling and Automatic Scaling","created":"2025-11-08","cited_by_count":2,"area":null},{"id":"2511.15375","title":"Parameter Importance-Driven Continual Learning for Foundation Models","created":"2025-11-19","cited_by_count":2,"area":"lr"},{"id":"2601.21577","title":"Collaborative Parameter Learning: Mitigating Forgetting via Parameter-Level Gradient Analysis","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2604.10952","title":"UniPROT: Uniform Prototype Selection via Partial Optimal Transport with Submodular Guarantees","created":"2026-04-13","cited_by_count":2,"area":null},{"id":"2205.16005","title":"Neural Retriever and Go Beyond: A Thesis Proposal","created":"2022-05-31","cited_by_count":1,"area":null},{"id":"2210.07566","title":"A Survey of Parameters Associated with the Quality of Benchmarks in NLP","created":"2022-10-14","cited_by_count":1,"area":null},{"id":"2408.12148","title":"Multi-tool Integration Application for Math Reasoning Using Large Language Model","created":"2024-08-22","cited_by_count":1,"area":"lr"},{"id":"2410.13666","title":"VL-GLUE: A Suite of Fundamental yet Challenging Visuo-Linguistic Reasoning Tasks","created":"2024-10-17","cited_by_count":1,"area":"lr"},{"id":"2412.12609","title":"MultiLingPoT: Enhancing Mathematical Reasoning with Multilingual Program Fine-tuning","created":"2024-12-17","cited_by_count":1,"area":"lr"},{"id":"2506.13464","title":"Unveiling the Learning Mind of Language Models: A Cognitive Framework and Empirical Study","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2506.24006","title":"Large Language Models Don't Make Sense of Word Problems. A Scoping Review from a Mathematics Education Perspective","created":"2025-06-30","cited_by_count":1,"area":null},{"id":"2510.06965","title":"EDUMATH: Generating Standards-aligned Educational Math Word Problems","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2606.07500","title":"Sparse Subspace-to-Expert Sharing for Task-Agnostic Continual Learning","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2607.15587","title":"Rethinking Transfer in Continual Learning: A Replay-Based Realisation","created":"2026-07-17","cited_by_count":1,"area":"lr"},{"id":"2609.22253","title":"CAMFT: Conflict-Aware Mergeable Fine-Tuning for Large Language Models","created":"2026-09-06","cited_by_count":1,"area":null},{"id":"2305.07475","title":"Comprehensive Solution Program Centric Pretraining for Table-and-Text Hybrid Numerical Reasoning","created":"2023-05-12","cited_by_count":0,"area":null},{"id":"2404.03887","title":"SAAS: Solving Ability Amplification Strategy for Enhanced Mathematical Reasoning in Large Language Models","created":"2024-04-05","cited_by_count":0,"area":"lr"},{"id":"2404.14355","title":"Pre-Calc: Learning to Use the Calculator Improves Numeracy in Language Models","created":"2024-04-22","cited_by_count":0,"area":null},{"id":"2406.02864","title":"NUMCoT: Numerals and Units of Measurement in Chain-of-Thought Reasoning using Large Language Models","created":"2024-06-05","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}