{"list":"other","total":54,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439},{"id":"2308.14508","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","created":"2023-08-28","cited_by_count":1417},{"id":"2310.08560","title":"MemGPT: Towards LLMs as Operating Systems","created":"2023-10-12","cited_by_count":1389},{"id":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216},{"id":"2404.14469","title":"SnapKV: LLM Knows What You are Looking for Before Generation","created":"2024-04-22","cited_by_count":880},{"id":"2304.08467","title":"Learning to Compress Prompts with Gist Tokens","created":"2023-04-17","cited_by_count":390},{"id":"2210.00720","title":"Complexity-Based Prompting for Multi-Step Reasoning","created":"2022-10-03","cited_by_count":388},{"id":"2412.15204","title":"LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks","created":"2024-12-19","cited_by_count":379},{"id":"2305.14788","title":"Adapting Language Models to Compress Contexts","created":"2023-05-24","cited_by_count":356},{"id":"2407.06204","title":"A Survey on Mixture of Experts in Large Language Models","created":"2024-06-26","cited_by_count":237},{"id":"2310.06201","title":"Compressing Context to Enhance Inference Efficiency of Large Language Models","created":"2023-10-09","cited_by_count":189},{"id":"2402.10171","title":"Data Engineering for Scaling Language Models to 128K Context","created":"2024-02-15","cited_by_count":186},{"id":"2105.08209","title":"BookSum: A Collection of Datasets for Long-form Narrative Summarization","created":"2021-05-18","cited_by_count":184},{"id":"2411.12372","title":"RedPajama: an Open Dataset for Training Large Language Models","created":"2024-11-19","cited_by_count":182},{"id":"2402.09727","title":"A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts","created":"2024-02-15","cited_by_count":146},{"id":"2107.00910","title":"Learned Token Pruning for Transformers","created":"2021-07-02","cited_by_count":139},{"id":"2310.03025","title":"Retrieval meets Long Context Large Language Models","created":"2023-10-04","cited_by_count":115},{"id":"2411.17558","title":"Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey","created":"2024-11-26","cited_by_count":76},{"id":"2304.12102","title":"Unlocking Context Constraints of LLMs: Enhancing Context Efficiency of LLMs with Self-Information-Based Content Filtering","created":"2023-04-24","cited_by_count":65},{"id":"2411.02937","title":"Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent","created":"2024-11-05","cited_by_count":65},{"id":"2407.09014","title":"CompAct: Compressing Retrieved Documents Actively for Question Answering","created":"2024-07-12","cited_by_count":64},{"id":"2111.04060","title":"Are we ready for a new paradigm shift? A Survey on Visual Deep MLP","created":"2021-11-07","cited_by_count":63},{"id":"2203.00991","title":"The Past Mistake is the Future Wisdom: Error-driven Contrastive Probability Optimization for Chinese Spell Checking","created":"2022-03-02","cited_by_count":56},{"id":"2312.03414","title":"Compressed Context Memory For Online Language Model Interaction","created":"2023-12-06","cited_by_count":43},{"id":"2507.09477","title":"Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs","created":"2025-07-13","cited_by_count":42},{"id":"2510.06186","title":"RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback","created":"2025-10-07","cited_by_count":25},{"id":"2402.11100","title":"When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models","created":"2024-02-16","cited_by_count":22},{"id":"2402.19248","title":"Let LLMs Take on the Latest Challenges! A Chinese Dynamic Question Answering Benchmark","created":"2024-02-29","cited_by_count":22},{"id":"2502.11493","title":"DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens","created":"2025-02-17","cited_by_count":22},{"id":"2501.01945","title":"Cold-Start Recommendation towards the Era of Large Language Models (LLMs): A Comprehensive Survey and Roadmap","created":"2025-01-03","cited_by_count":20},{"id":"2406.05317","title":"LoCoCo: Dropping In Convolutions for Long Context Compression","created":"2024-06-08","cited_by_count":19},{"id":"2510.25694","title":"Process-Level Trajectory Evaluation for Environment Configuration in Software Engineering Agents","created":"2025-10-29","cited_by_count":18},{"id":"2502.07184","title":"Refine Knowledge of Large Language Models via Adaptive Contrastive Learning","created":"2025-02-11","cited_by_count":15},{"id":"2502.10454","title":"One Example Shown, Many Concepts Known! Counterexample-Driven Conceptual Reasoning in Mathematical LLMs","created":"2025-02-12","cited_by_count":14},{"id":"2309.03450","title":"XGen-7B Technical Report","created":"2023-09-07","cited_by_count":12},{"id":"2305.03688","title":"DAMO-NLP at SemEval-2023 Task 2: A Unified Retrieval-augmented System for Multilingual Named Entity Recognition","created":"2023-05-05","cited_by_count":9},{"id":"2402.11420","title":"Rethinking the Roles of Large Language Models in Chinese Grammatical Error Correction","created":"2024-02-18","cited_by_count":9},{"id":"2403.12077","title":"Evaluating Robustness of Generative Search Engine on Adversarial Factual Questions","created":"2024-02-25","cited_by_count":9},{"id":"2402.16058","title":"Say More with Less: Understanding Prompt Learning Behaviors through Gist Compression","created":"2024-02-25","cited_by_count":8},{"id":"2509.25725","title":"Atomic Thinking of LLMs: Decoupling and Exploring Mathematical Reasoning Abilities","created":"2025-09-30","cited_by_count":6},{"id":"2504.07433","title":"From Token to Line: Enhancing Code Generation with a Long-Term Perspective","created":"2025-04-10","cited_by_count":4},{"id":"2304.03531","title":"From Retrieval to Generation: Efficient and Effective Entity Set Expansion","created":"2023-04-07","cited_by_count":3},{"id":"2504.07288","title":"MDIT: A Model-free Data Interpolation Method for Diverse Instruction Tuning","created":"2025-04-09","cited_by_count":3}],"next_cursor":null}