{"list":"other","total":53,"rows":[{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2305.01210","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","created":"2023-05-02","cited_by_count":1391},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"2402.14008","title":"OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems","created":"2024-02-21","cited_by_count":1136},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"2205.14217","title":"Diffusion-LM Improves Controllable Text Generation","created":"2022-05-27","cited_by_count":1027},{"id":"2502.09992","title":"Large Language Diffusion Models","created":"2025-02-14","cited_by_count":912},{"id":"2506.13131","title":"AlphaEvolve: A coding agent for scientific and algorithmic discovery","created":"2025-06-16","cited_by_count":867},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609},{"id":"2506.01939","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning","created":"2025-06-02","cited_by_count":559},{"id":"2508.15487","title":"Dream 7B: Diffusion Large Language Models","created":"2025-08-21","cited_by_count":544},{"id":"1908.04319","title":"Neural Text Generation with Unlikelihood Training","created":"2019-08-12","cited_by_count":503},{"id":"2406.11939","title":"From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline","created":"2024-06-17","cited_by_count":500},{"id":"1802.01886","title":"Texygen: A Benchmarking Platform for Text Generation Models","created":"2018-02-06","cited_by_count":491},{"id":"2505.22618","title":"Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding","created":"2025-05-28","cited_by_count":420},{"id":"2310.06452","title":"Understanding the Effects of RLHF on LLM Generalisation and Diversity","created":"2023-10-10","cited_by_count":396},{"id":"2409.04109","title":"Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers","created":"2024-09-06","cited_by_count":363},{"id":"2410.18451","title":"Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs","created":"2024-10-24","cited_by_count":327},{"id":"2506.14758","title":"Reasoning with Exploration: An Entropy Perspective","created":"2025-06-17","cited_by_count":281},{"id":"1702.01806","title":"Beam Search Strategies for Neural Machine Translation","created":"2017-02-06","cited_by_count":232},{"id":"2305.20009","title":"Protein Design with Guided Discrete Diffusion","created":"2023-05-31","cited_by_count":157},{"id":"2407.01082","title":"Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs","created":"2024-07-01","cited_by_count":150},{"id":"2310.17347","title":"CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling","created":"2023-10-26","cited_by_count":129},{"id":"2510.06303","title":"SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation","created":"2025-10-07","cited_by_count":129},{"id":"2210.15191","title":"Truncation Sampling as Language Model Desmoothing","created":"2022-10-27","cited_by_count":123},{"id":"2405.00492","title":"Is Temperature the Creativity Parameter of Large Language Models?","created":"2024-05-01","cited_by_count":93},{"id":"2505.12346","title":"SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization","created":"2025-05-18","cited_by_count":89},{"id":"2509.06949","title":"Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models","created":"2025-09-08","cited_by_count":88},{"id":"2509.02534","title":"Jointly Reinforcing Diversity and Quality in Language Model Generations","created":"2025-09-02","cited_by_count":80},{"id":"2508.10875","title":"A Survey on Diffusion Language Models","created":"2025-08-14","cited_by_count":78},{"id":"2310.13102","title":"Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models","created":"2023-10-19","cited_by_count":71},{"id":"2408.16673","title":"Preserving Diversity in Supervised Fine-Tuning of Large Language Models","created":"2024-08-29","cited_by_count":70},{"id":"2504.05228","title":"NoveltyBench: Evaluating Language Models for Humanlike Diversity","created":"2025-04-07","cited_by_count":66},{"id":"2501.18101","title":"Diverse Preference Optimization","created":"2025-01-30","cited_by_count":52},{"id":"2404.10859","title":"Forcing Diffuse Distributions out of Language Models","created":"2024-04-16","cited_by_count":48},{"id":"2503.17126","title":"Modifying Large Language Model Post-Training for Diverse Creative Writing","created":"2025-03-21","cited_by_count":40},{"id":"2309.02772","title":"Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models","created":"2023-09-06","cited_by_count":38},{"id":"2502.13917","title":"TESS 2: A Large-Scale Generalist Diffusion Language Model","created":"2025-02-19","cited_by_count":30},{"id":"2504.15266","title":"Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction","created":"2025-04-21","cited_by_count":29},{"id":"2202.13587","title":"Rethinking and Refining the Distinct Metric","created":"2022-02-28","cited_by_count":27},{"id":"2402.10342","title":"Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization","created":"2024-02-15","cited_by_count":25},{"id":"2505.14442","title":"Creative Preference Optimization","created":"2025-05-20","cited_by_count":25},{"id":"2511.08594","title":"Diverse Preference Learning for Capabilities and Alignment","created":"2025-10-29","cited_by_count":25},{"id":"2511.00432","title":"G2: Guided Generation for Enhanced Output Diversity in LLMs","created":"2025-11-01","cited_by_count":14},{"id":"2306.01286","title":"KL-Divergence Guided Temperature Sampling","created":"2023-06-02","cited_by_count":9},{"id":"2410.06151","title":"Diversifying Policy Behaviors with Extrinsic Behavioral Curiosity","created":"2024-10-08","cited_by_count":4},{"id":"2411.06965","title":"Imitation from Diverse Behaviors: Wasserstein Quality Diversity Imitation Learning with Single-Step Archive Exploration","created":"2024-11-11","cited_by_count":4},{"id":"2412.03343","title":"Improving Linguistic Diversity of Large Language Models with Possibility Exploration Fine-Tuning","created":"2024-12-04","cited_by_count":4}],"next_cursor":null}