{"total":27,"rows":[{"id":"2403.17887","title":"The Unreasonable Ineffectiveness of the Deeper Layers","created":"2024-03-26","cited_by_count":226,"area":"lr"},{"id":"2402.10176","title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","created":"2024-02-15","cited_by_count":143,"area":"lr"},{"id":"2312.09241","title":"TinyGSM: achieving >80% on GSM8k with small language models","created":"2023-12-14","cited_by_count":70,"area":"lr"},{"id":"2309.06979","title":"Auto-Regressive Next-Token Predictors are Universal Learners","created":"2023-09-13","cited_by_count":67,"area":"lr"},{"id":"2501.18101","title":"Diverse Preference Optimization","created":"2025-01-30","cited_by_count":52,"area":"lr"},{"id":"2503.18866","title":"Reasoning to Learn from Latent Thoughts","created":"2025-03-24","cited_by_count":45,"area":"lr"},{"id":"2410.12881","title":"MIND: Math Informed syNthetic Dialogues for Pretraining LLMs","created":"2024-10-15","cited_by_count":14,"area":"lr"},{"id":"2502.04375","title":"An Analysis for Reasoning Bias of Language Models with Small Initialization","created":"2025-02-05","cited_by_count":13,"area":"lr"},{"id":"2404.04293","title":"Reason from Fallacy: Enhancing Large Language Models' Logical Reasoning through Logical Fallacy Understanding","created":"2024-04-04","cited_by_count":12,"area":"lr"},{"id":"2402.16844","title":"Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding","created":"2024-02-26","cited_by_count":11,"area":"lr"},{"id":"2312.03633","title":"Exploring the Reversal Curse and Other Deductive Logical Reasoning in BERT and GPT-Based Large Language Models","created":"2023-12-06","cited_by_count":5,"area":"lr"},{"id":"2502.19409","title":"ImageChain: Advancing Sequential Image-to-Text Reasoning in Multimodal Large Language Models","created":"2025-02-26","cited_by_count":4,"area":"lr"},{"id":"2508.05305","title":"SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens","created":"2025-08-07","cited_by_count":4,"area":"lr"},{"id":"2509.16551","title":"Rethinking the Role of Text Complexity in Language Model Pretraining","created":"2025-09-20","cited_by_count":2,"area":"lr"},{"id":"2511.11810","title":"On the Notion that Language Models Reason","created":"2025-11-14","cited_by_count":2,"area":"lr"},{"id":"2402.14355","title":"Rule or Story, Which is a Better Commonsense Expression for Talking with Large Language Models?","created":"2024-02-22","cited_by_count":1,"area":"lr"},{"id":"2512.07198","title":"Generating Storytelling Images with Rich Chains-of-Reasoning","created":"2025-12-08","cited_by_count":1,"area":"lr"},{"id":"2602.11081","title":"SteuerLLM: Local specialized large language model for German tax law analysis","created":"2026-02-11","cited_by_count":1,"area":"lr"},{"id":"2401.11626","title":"Freely Long-Thinking Transformer (FraiLT)","created":"2024-01-21","cited_by_count":0,"area":"lr"},{"id":"2502.18452","title":"FRIDA to the Rescue! Analyzing Synthetic Data Effectiveness in Object-Based Common Sense Reasoning for Disaster Response","created":"2025-02-25","cited_by_count":0,"area":"lr"},{"id":"2510.13915","title":"Readability $\\ne$ Learnability: Rethinking the Role of Simplicity in Training Small Language Models","created":"2025-10-15","cited_by_count":0,"area":"lr"},{"id":"2512.21280","title":"SMART SLM: Structured Memory and Reasoning Transformer, A Small Language Model for Accurate Document Assistance","created":"2025-12-24","cited_by_count":0,"area":"lr"},{"id":"2601.03268","title":"WRAVAL -- WRiting Assist eVALuation","created":"2025-12-19","cited_by_count":0,"area":"lr"},{"id":"2605.26934","title":"Reasoning Depth and Environment Complexity: A Controlled Study of RLVR Data Allocation across Logical Reasoning Tasks","created":"2026-05-26","cited_by_count":0,"area":"lr"},{"id":"2605.30415","title":"Domain Adaptation and Reasoning Frameworks in Language Models: A Controlled Experiment with Historical Cosmology","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2609.29845","title":"Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs","created":"2026-09-24","cited_by_count":0,"area":"lr"},{"id":"2610.09003","title":"Algorithmic Scratchpads and Curriculum Staging for Arithmetic Reasoning in Tiny Transformers","created":"2026-10-06","cited_by_count":0,"area":"lr"}],"next_cursor":null}