{"total":51,"rows":[{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139,"area":"lr"},{"id":"2401.02954","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","created":"2024-01-05","cited_by_count":642,"area":"lr"},{"id":"2308.09583","title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct","created":"2023-08-18","cited_by_count":625,"area":"lr"},{"id":"2309.17452","title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","created":"2023-09-29","cited_by_count":282,"area":"lr"},{"id":"2310.15164","title":"LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers","created":"2023-10-23","cited_by_count":168,"area":"lr"},{"id":"2310.03731","title":"MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning","created":"2023-10-05","cited_by_count":156,"area":"lr"},{"id":"2310.06786","title":"OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text","created":"2023-10-10","cited_by_count":155,"area":"lr"},{"id":"2505.07608","title":"MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining","created":"2025-05-12","cited_by_count":121,"area":"lr"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2407.19825","title":"Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost","created":"2024-07-29","cited_by_count":109,"area":"lr"},{"id":"2310.10080","title":"Let's reward step by step: Step-Level reward model as the Navigators for Reasoning","created":"2023-10-16","cited_by_count":102,"area":"lr"},{"id":"2402.12840","title":"ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic","created":"2024-02-20","cited_by_count":88,"area":"lr"},{"id":"2311.07466","title":"On Measuring Faithfulness or Self-consistency of Natural Language Explanations","created":"2023-11-13","cited_by_count":73,"area":"lr"},{"id":"2401.06915","title":"DocFinQA: A Long-Context Financial Reasoning Dataset","created":"2024-01-12","cited_by_count":60,"area":"lr"},{"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":"2310.06272","title":"Let Models Speak Ciphers: Multiagent Debate through Embeddings","created":"2023-10-10","cited_by_count":51,"area":"lr"},{"id":"2504.02807","title":"MegaMath: Pushing the Limits of Open Math Corpora","created":"2025-04-03","cited_by_count":51,"area":"lr"},{"id":"2401.15585","title":"Evaluating Gender Bias in Large Language Models via Chain-of-Thought Prompting","created":"2024-01-28","cited_by_count":50,"area":"lr"},{"id":"2310.05506","title":"MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning","created":"2023-10-09","cited_by_count":45,"area":"lr"},{"id":"2310.08753","title":"CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models","created":"2023-10-12","cited_by_count":43,"area":"lr"},{"id":"2409.12568","title":"InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning","created":"2024-09-19","cited_by_count":36,"area":"lr"},{"id":"2401.10446","title":"Large Language Models are Efficient Learners of Noise-Robust Speech Recognition","created":"2024-01-19","cited_by_count":31,"area":"lr"},{"id":"2404.00459","title":"NumeroLogic: Number Encoding for Enhanced LLMs' Numerical Reasoning","created":"2024-03-30","cited_by_count":31,"area":"lr"},{"id":"2404.17729","title":"CoMM: Collaborative Multi-Agent, Multi-Reasoning-Path Prompting for Complex Problem Solving","created":"2024-04-26","cited_by_count":31,"area":"lr"},{"id":"2311.06602","title":"BizBench: A Quantitative Reasoning Benchmark for Business and Finance","created":"2023-11-11","cited_by_count":28,"area":"lr"},{"id":"2309.03224","title":"No Train Still Gain. Unleash Mathematical Reasoning of Large Language Models with Monte Carlo Tree Search Guided by Energy Function","created":"2023-09-01","cited_by_count":20,"area":"lr"},{"id":"2410.10735","title":"Embedding Self-Correction as an Inherent Ability in Large Language Models for Enhanced Mathematical Reasoning","created":"2024-10-14","cited_by_count":13,"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":"2402.11770","title":"Structured Chain-of-Thought Prompting for Few-Shot Generation of Content-Grounded QA Conversations","created":"2024-02-19","cited_by_count":9,"area":"lr"},{"id":"2412.16964","title":"System-2 Mathematical Reasoning via Enriched Instruction Tuning","created":"2024-12-22","cited_by_count":7,"area":"lr"},{"id":"2505.17592","title":"AstroMLab 4: Benchmark-Topping Performance in Astronomy Q&A with a 70B-Parameter Domain-Specialized Reasoning Model","created":"2025-05-23","cited_by_count":7,"area":"lr"},{"id":"2402.14404","title":"On the Tip of the Tongue: Analyzing Conceptual Representation in Large Language Models with Reverse-Dictionary Probe","created":"2024-02-22","cited_by_count":6,"area":"lr"},{"id":"2403.12373","title":"RankPrompt: Step-by-Step Comparisons Make Language Models Better Reasoners","created":"2024-03-19","cited_by_count":6,"area":"lr"},{"id":"2310.01074","title":"Back to the Future: Towards Explainable Temporal Reasoning with Large Language Models","created":"2023-10-02","cited_by_count":5,"area":"lr"},{"id":"2311.05113","title":"Conic10K: A Challenging Math Problem Understanding and Reasoning Dataset","created":"2023-11-09","cited_by_count":5,"area":"lr"},{"id":"2412.06845","title":"7B Fully Open Source Moxin-LLM/VLM -- From Pretraining to GRPO-based Reinforcement Learning Enhancement","created":"2024-12-08","cited_by_count":5,"area":"lr"},{"id":"2508.08386","title":"CoDAE: Adapting Large Language Models for Education via Chain-of-Thought Data Augmentation","created":"2025-08-11","cited_by_count":5,"area":"lr"},{"id":"2506.07463","title":"CCI4.0: A Bilingual Pretraining Dataset for Enhancing Reasoning in Large Language Models","created":"2025-06-09","cited_by_count":4,"area":"lr"},{"id":"2602.19548","title":"Beyond a Single Extractor: Re-thinking HTML-to-Text Extraction for LLM Pretraining","created":"2026-02-23","cited_by_count":4,"area":"lr"},{"id":"2405.13004","title":"MathDivide: Improved mathematical reasoning by large language models","created":"2024-05-12","cited_by_count":3,"area":"lr"},{"id":"2502.14155","title":"Giving AI Personalities Leads to More Human-Like Reasoning","created":"2025-02-19","cited_by_count":3,"area":"lr"},{"id":"2512.06201","title":"K2-V2: A 360-Open, Reasoning-Enhanced LLM","created":"2025-12-05","cited_by_count":3,"area":"lr"},{"id":"2512.24503","title":"Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice","created":"2025-12-30","cited_by_count":3,"area":"lr"},{"id":"2605.05227","title":"Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods","created":"2026-04-19","cited_by_count":3,"area":"lr"},{"id":"2508.21228","title":"Decoding Memories: An Efficient Pipeline for Self-Consistency Hallucination Detection","created":"2025-08-28","cited_by_count":2,"area":"lr"},{"id":"2410.06272","title":"The Mystery of Compositional Generalization in Graph-based Generative Commonsense Reasoning","created":"2024-10-08","cited_by_count":1,"area":"lr"},{"id":"2501.09107","title":"Rethinking Post-Training Quantization: Introducing a Statistical Pre-Calibration Approach","created":"2025-01-15","cited_by_count":1,"area":"lr"},{"id":"2502.15120","title":"Unveiling Reasoning Thresholds in Language Models: Scaling, Fine-Tuning, and Interpretability through Attention Maps","created":"2025-02-21","cited_by_count":1,"area":"lr"},{"id":"2603.09205","title":"Emotion is Not Just a Label: Latent Emotional Factors in LLM Processing","created":"2026-03-10","cited_by_count":1,"area":"lr"},{"id":"2410.07062","title":"TinyEmo: Scaling down Emotional Reasoning via Metric Projection","created":"2024-10-09","cited_by_count":0,"area":"lr"},{"id":"2509.00974","title":"RPRO: Ranked Preference Reinforcement Optimization for Enhancing Medical QA and Diagnostic Reasoning","created":"2025-08-31","cited_by_count":0,"area":"lr"}],"next_cursor":null}