{"total":65,"rows":[{"id":"2405.04434","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","created":"2024-05-07","cited_by_count":1135,"area":"moe"},{"id":"2401.06066","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","created":"2024-01-11","cited_by_count":867,"area":"moe"},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648,"area":null},{"id":"2401.02954","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","created":"2024-01-05","cited_by_count":642,"area":"lr"},{"id":"2403.03853","title":"ShortGPT: Layers in Large Language Models are More Redundant Than You Expect","created":"2024-03-06","cited_by_count":383,"area":null},{"id":"2107.02137","title":"ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","created":"2021-07-05","cited_by_count":260,"area":null},{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147,"area":null},{"id":"2104.12369","title":"PanGu-$\\alpha$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation","created":"2021-04-26","cited_by_count":134,"area":null},{"id":"2402.11187","title":"LaCo: Large Language Model Pruning via Layer Collapse","created":"2024-02-17","cited_by_count":126,"area":null},{"id":"2402.18158","title":"Evaluating Quantized Large Language Models","created":"2024-02-28","cited_by_count":77,"area":null},{"id":"2507.11005","title":"AdaMuon: Adaptive Muon Optimizer","created":"2025-07-15","cited_by_count":67,"area":null},{"id":"2303.10845","title":"PanGu-{\\Sigma}: Towards Trillion Parameter Language Model with Sparse Heterogeneous Computing","created":"2023-03-20","cited_by_count":56,"area":null},{"id":"2112.12731","title":"ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","created":"2021-12-23","cited_by_count":46,"area":null},{"id":"2110.06696","title":"Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinese","created":"2021-10-13","cited_by_count":45,"area":null},{"id":"2107.07498","title":"FewCLUE: A Chinese Few-shot Learning Evaluation Benchmark","created":"2021-07-15","cited_by_count":41,"area":null},{"id":"2410.18517","title":"KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing","created":"2024-10-24","cited_by_count":41,"area":"lr"},{"id":"2110.04725","title":"Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot Learning","created":"2021-10-10","cited_by_count":35,"area":null},{"id":"2308.13961","title":"Translate Meanings, Not Just Words: IdiomKB's Role in Optimizing Idiomatic Translation with Language Models","created":"2023-08-26","cited_by_count":24,"area":null},{"id":"2109.03564","title":"NSP-BERT: A Prompt-based Few-Shot Learner Through an Original Pre-training Task--Next Sentence Prediction","created":"2021-09-08","cited_by_count":23,"area":null},{"id":"2406.03496","title":"Wings: Learning Multimodal LLMs without Text-only Forgetting","created":"2024-06-05","cited_by_count":23,"area":"mllm"},{"id":"2209.10372","title":"WeLM: A Well-Read Pre-trained Language Model for Chinese","created":"2022-09-21","cited_by_count":19,"area":null},{"id":"2401.03804","title":"TeleChat Technical Report","created":"2024-01-08","cited_by_count":15,"area":null},{"id":"2109.06838","title":"ePiC: Employing Proverbs in Context as a Benchmark for Abstract Language Understanding","created":"2021-09-14","cited_by_count":14,"area":null},{"id":"2308.04813","title":"CLEVA: Chinese Language Models EVAluation Platform","created":"2023-08-09","cited_by_count":13,"area":null},{"id":"2505.02819","title":"ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization","created":"2025-05-05","cited_by_count":13,"area":null},{"id":"2305.14150","title":"WYWEB: A NLP Evaluation Benchmark For Classical Chinese","created":"2023-05-23","cited_by_count":12,"area":null},{"id":"2404.16645","title":"Tele-FLM Technical Report","created":"2024-04-25","cited_by_count":12,"area":null},{"id":"2405.06694","title":"SUTRA: Scalable Multilingual Language Model Architecture","created":"2024-05-07","cited_by_count":11,"area":"lr"},{"id":"2202.09509","title":"PETCI: A Parallel English Translation Dataset of Chinese Idioms","created":"2022-02-19","cited_by_count":10,"area":null},{"id":"2307.08074","title":"Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling","created":"2023-07-16","cited_by_count":10,"area":null},{"id":"2403.12316","title":"OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety","created":"2024-03-18","cited_by_count":9,"area":null},{"id":"2106.09896","title":"Continuity of Topic, Interaction, and Query: Learning to Quote in Online Conversations","created":"2021-06-18","cited_by_count":8,"area":null},{"id":"2506.18105","title":"Chengyu-Bench: Benchmarking Large Language Models for Chinese Idiom Understanding and Use","created":"2025-06-22","cited_by_count":8,"area":null},{"id":"2106.00400","title":"Sub-Character Tokenization for Chinese Pretrained Language Models","created":"2021-06-01","cited_by_count":7,"area":null},{"id":"2309.10706","title":"OpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch","created":"2023-09-19","cited_by_count":7,"area":null},{"id":"2505.16216","title":"Memorization or Reasoning? Exploring the Idiom Understanding of LLMs","created":"2025-05-22","cited_by_count":7,"area":"lr"},{"id":"2510.00567","title":"Are Large Language Models Chronically Online Surfers? A Dataset for Chinese Internet Meme Explanation","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2601.07338","title":"Beyond Literal Mapping: Benchmarking and Improving Non-Literal Translation Evaluation","created":"2026-01-12","cited_by_count":6,"area":null},{"id":"2204.07555","title":"Chinese Idiom Paraphrasing","created":"2022-04-15","cited_by_count":5,"area":null},{"id":"2406.14887","title":"InternLM-Law: An Open Source Chinese Legal Large Language Model","created":"2024-06-21","cited_by_count":5,"area":null},{"id":"2501.00339","title":"GRASP: Replace Redundant Layers with Adaptive Singular Parameters for Efficient Model Compression","created":"2024-12-31","cited_by_count":5,"area":null},{"id":"2502.13794","title":"LESA: Learnable LLM Layer Scaling-Up","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2112.02994","title":"IBERT: Idiom Cloze-style reading comprehension with Attention","created":"2021-11-05","cited_by_count":4,"area":null},{"id":"2308.14353","title":"ZhuJiu: A Multi-dimensional, Multi-faceted Chinese Benchmark for Large Language Models","created":"2023-08-28","cited_by_count":4,"area":null},{"id":"2107.12627","title":"Cross-lingual Transferring of Pre-trained Contextualized Language Models","created":"2021-07-27","cited_by_count":3,"area":null},{"id":"2109.05149","title":"Extract, Integrate, Compete: Towards Verification Style Reading Comprehension","created":"2021-09-11","cited_by_count":3,"area":null},{"id":"2506.20480","title":"GPTailor: Large Language Model Pruning Through Layer Cutting and Stitching","created":"2025-06-25","cited_by_count":3,"area":null},{"id":"2601.18130","title":"RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents","created":"2026-01-26","cited_by_count":3,"area":"agents"},{"id":"2112.06494","title":"Native Chinese Reader: A Dataset Towards Native-Level Chinese Machine Reading Comprehension","created":"2021-12-13","cited_by_count":2,"area":null},{"id":"2412.07111","title":"Predictable Emergent Abilities of LLMs: Proxy Tasks Are All You Need","created":"2024-12-10","cited_by_count":2,"area":null},{"id":"2508.10421","title":"Evaluating LLMs on Chinese Idiom Translation","created":"2025-08-14","cited_by_count":2,"area":null},{"id":"2508.11828","title":"A Survey of Idiom Datasets for Psycholinguistic and Computational Research","created":"2025-08-15","cited_by_count":2,"area":null},{"id":"2510.05026","title":"Idiom Understanding as a Tool to Measure the Dialect Gap","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2602.11089","title":"DataChef: Cooking Up Optimal Data Recipes for LLM Adaptation via Reinforcement Learning","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2310.20195","title":"Generating Continuations in Multilingual Idiomatic Contexts","created":"2023-10-31","cited_by_count":1,"area":null},{"id":"2602.09866","title":"SinFoS: A Parallel Dataset for Translating Sinhala Figures of Speech","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2602.14649","title":"GradMAP: Faster Layer Pruning with Gradient Metric and Projection Compensation","created":"2026-02-16","cited_by_count":1,"area":"lr"},{"id":"2211.13376","title":"InDEX: Indonesian Idiom and Expression Dataset for Cloze Test","created":"2022-11-24","cited_by_count":0,"area":null},{"id":"2404.05560","title":"Chinese Sequence Labeling with Semi-Supervised Boundary-Aware Language Model Pre-training","created":"2024-04-08","cited_by_count":0,"area":null},{"id":"2504.12332","title":"Can the capability of Large Language Models be described by human ability? A Meta Study","created":"2025-04-13","cited_by_count":0,"area":null},{"id":"2605.01323","title":"SiNFluD: Creating and Evaluating Figurative Language Dataset for Sindhi","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2606.14187","title":"Zeta: Dual Whitening for Matrix Optimization via Coordinate-Adaptive Preconditioning","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.23440","title":"Reasoning or Memorization: Can LLMs Understand and Generate Chinese Xiehouyu Riddles?","created":"2026-07-26","cited_by_count":0,"area":"lr"},{"id":"2609.21722","title":"CIBuzzBench: A Benchmark for Cross-Lingual Understanding of Chinese Internet Buzzwords","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.36965","title":"Chinese-Jev: Bringing System One Model to Chinese-Language Tasks","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}