{"total":80,"rows":[{"id":"2405.01535","title":"Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models","created":"2024-05-02","cited_by_count":446,"area":null},{"id":"2307.13269","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","created":"2023-07-25","cited_by_count":364,"area":null},{"id":"2310.11564","title":"Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging","created":"2023-10-17","cited_by_count":280,"area":"alignment"},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2408.07666","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","created":"2024-08-14","cited_by_count":254,"area":null},{"id":"2306.04488","title":"Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards","created":"2023-06-07","cited_by_count":243,"area":"alignment"},{"id":"2307.10928","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","created":"2023-07-20","cited_by_count":201,"area":"alignment"},{"id":"2402.01364","title":"Continual Learning for Large Language Models: A Survey","created":"2024-02-02","cited_by_count":147,"area":null},{"id":"2402.06954","title":"OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning","created":"2024-02-10","cited_by_count":128,"area":null},{"id":"2305.14045","title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","created":"2023-05-23","cited_by_count":108,"area":"lr"},{"id":"2312.12379","title":"Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuning","created":"2023-12-19","cited_by_count":106,"area":"mllm"},{"id":"2406.05761","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","created":"2024-06-09","cited_by_count":93,"area":null},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"area":null},{"id":"2404.14851","title":"From Matching to Generation: A Survey on Generative Information Retrieval","created":"2024-04-23","cited_by_count":89,"area":null},{"id":"2502.08773","title":"Universal Model Routing for Efficient LLM Inference","created":"2025-02-12","cited_by_count":86,"area":"inference"},{"id":"2410.10347","title":"A Unified Approach to Routing and Cascading for LLMs","created":"2024-10-14","cited_by_count":80,"area":"agents"},{"id":"2406.10471","title":"Personalized Pieces: Efficient Personalized Large Language Models through Collaborative Efforts","created":"2024-06-15","cited_by_count":74,"area":null},{"id":"2405.11157","title":"Towards Modular LLMs by Building and Reusing a Library of LoRAs","created":"2024-05-18","cited_by_count":72,"area":null},{"id":"2308.04430","title":"SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore","created":"2023-08-08","cited_by_count":71,"area":null},{"id":"2407.15186","title":"A Survey on Employing Large Language Models for Text-to-SQL Tasks","created":"2024-07-21","cited_by_count":67,"area":null},{"id":"2402.05859","title":"Learning to Route Among Specialized Experts for Zero-Shot Generalization","created":"2024-02-08","cited_by_count":65,"area":null},{"id":"2406.06391","title":"Towards Lifelong Learning of Large Language Models: A Survey","created":"2024-06-10","cited_by_count":64,"area":null},{"id":"2503.10657","title":"RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs","created":"2025-03-08","cited_by_count":61,"area":null},{"id":"2303.14177","title":"Scaling Expert Language Models with Unsupervised Domain Discovery","created":"2023-03-24","cited_by_count":60,"area":null},{"id":"2305.09246","title":"Maybe Only 0.5% Data is Needed: A Preliminary Exploration of Low Training Data Instruction Tuning","created":"2023-05-16","cited_by_count":58,"area":null},{"id":"2403.11435","title":"InsCL: A Data-efficient Continual Learning Paradigm for Fine-tuning Large Language Models with Instructions","created":"2024-03-18","cited_by_count":58,"area":null},{"id":"2311.00288","title":"Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks","created":"2023-11-01","cited_by_count":55,"area":null},{"id":"2410.03617","title":"What Matters for Model Merging at Scale?","created":"2024-10-04","cited_by_count":55,"area":null},{"id":"2408.07057","title":"A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning","created":"2024-08-13","cited_by_count":52,"area":null},{"id":"2310.01542","title":"Fusing Models with Complementary Expertise","created":"2023-10-02","cited_by_count":46,"area":null},{"id":"2405.18653","title":"Recent Advances of Foundation Language Models-based Continual Learning: A Survey","created":"2024-05-28","cited_by_count":46,"area":null},{"id":"2304.05568","title":"Improving Diffusion Models for Scene Text Editing with Dual Encoders","created":"2023-04-12","cited_by_count":45,"area":"diffusion"},{"id":"2307.16184","title":"UnIVAL: Unified Model for Image, Video, Audio and Language Tasks","created":"2023-07-30","cited_by_count":45,"area":null},{"id":"2403.07384","title":"SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models","created":"2024-03-12","cited_by_count":44,"area":null},{"id":"2401.10440","title":"Breaking the Curse of Multilinguality with Cross-lingual Expert Language Models","created":"2024-01-19","cited_by_count":38,"area":null},{"id":"2308.05696","title":"A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment","created":"2023-08-10","cited_by_count":33,"area":"alignment"},{"id":"2303.10475","title":"Large Language Model Instruction Following: A Survey of Progresses and Challenges","created":"2023-03-18","cited_by_count":31,"area":null},{"id":"2412.04692","title":"Smoothie: Label Free Language Model Routing","created":"2024-12-06","cited_by_count":31,"area":null},{"id":"2502.01976","title":"CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing","created":"2025-02-04","cited_by_count":30,"area":null},{"id":"2408.02085","title":"Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models","created":"2024-08-04","cited_by_count":29,"area":"alignment"},{"id":"2410.11163","title":"Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2306.05539","title":"Instruction Tuned Models are Quick Learners","created":"2023-05-17","cited_by_count":21,"area":null},{"id":"2502.00409","title":"Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systems","created":"2025-02-01","cited_by_count":20,"area":null},{"id":"2311.09758","title":"OrchestraLLM: Efficient Orchestration of Language Models for Dialogue State Tracking","created":"2023-11-16","cited_by_count":19,"area":null},{"id":"2403.08755","title":"DAM: Dynamic Adapter Merging for Continual Video QA Learning","created":"2024-03-13","cited_by_count":19,"area":null},{"id":"2308.10529","title":"SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understanding","created":"2023-08-21","cited_by_count":18,"area":null},{"id":"2410.13394","title":"Cross-Lingual Auto Evaluation for Assessing Multilingual LLMs","created":"2024-10-17","cited_by_count":18,"area":null},{"id":"2312.01700","title":"Data Management For Training Large Language Models: A Survey","created":"2023-12-04","cited_by_count":17,"area":null},{"id":"2401.16553","title":"SelectLLM: Can LLMs Select Important Instructions to Annotate?","created":"2024-01-29","cited_by_count":16,"area":null},{"id":"2507.07024","title":"FlexOlmo: Open Language Models for Flexible Data Use","created":"2025-07-09","cited_by_count":15,"area":"moe"},{"id":"2504.11042","title":"LazyReview A Dataset for Uncovering Lazy Thinking in NLP Peer Reviews","created":"2025-04-15","cited_by_count":13,"area":"lr"},{"id":"2507.00469","title":"Bisecle: Binding and Separation in Continual Learning for Video Language Understanding","created":"2025-07-01","cited_by_count":13,"area":"mllm"},{"id":"2409.02685","title":"RouterRetriever: Routing over a Mixture of Expert Embedding Models","created":"2024-09-04","cited_by_count":12,"area":"moe"},{"id":"2303.03628","title":"CoTEVer: Chain of Thought Prompting Annotation Toolkit for Explanation Verification","created":"2023-03-07","cited_by_count":11,"area":"lr"},{"id":"2305.13256","title":"TaskWeb: Selecting Better Source Tasks for Multi-task NLP","created":"2023-05-22","cited_by_count":11,"area":null},{"id":"2402.10073","title":"Both Matter: Enhancing the Emotional Intelligence of Large Language Models without Compromising the General Intelligence","created":"2024-02-15","cited_by_count":11,"area":null},{"id":"2410.05725","title":"KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from Server","created":"2024-10-08","cited_by_count":11,"area":"distill"},{"id":"2506.16655","title":"Arch-Router: Aligning LLM Routing with Human Preferences","created":"2025-06-19","cited_by_count":9,"area":"alignment"},{"id":"2312.14751","title":"Hazards from Increasingly Accessible Fine-Tuning of Downloadable Foundation Models","created":"2023-12-22","cited_by_count":7,"area":null},{"id":"2404.16418","title":"Instruction Matters: A Simple yet Effective Task Selection for Optimized Instruction Tuning of Specific Tasks","created":"2024-04-25","cited_by_count":6,"area":null},{"id":"2410.03440","title":"Exploring the Benefit of Activation Sparsity in Pre-training","created":"2024-10-04","cited_by_count":5,"area":"moe"},{"id":"2504.05342","title":"MASS: MoErging through Adaptive Subspace Selection","created":"2025-04-06","cited_by_count":5,"area":null},{"id":"2605.05676","title":"Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning","created":"2026-05-07","cited_by_count":5,"area":null},{"id":"2308.02955","title":"An Empirical Study of AI-based Smart Contract Creation","created":"2023-08-05","cited_by_count":4,"area":null},{"id":"2407.11019","title":"Efficacy of Various Large Language Models in Generating Smart Contracts","created":"2024-06-28","cited_by_count":4,"area":null},{"id":"2408.03762","title":"'Finance Wizard' at the FinLLM Challenge Task: Financial Text Summarization","created":"2024-08-07","cited_by_count":4,"area":null},{"id":"2410.07172","title":"Glider: Global and Local Instruction-Driven Expert Router","created":"2024-10-09","cited_by_count":4,"area":null},{"id":"2411.09539","title":"Fine-tuning Large Language Models with Limited Data: A Survey and Practical Guide","created":"2024-11-14","cited_by_count":4,"area":null},{"id":"2411.17204","title":"Strategic Prompting for Conversational Tasks: A Comparative Analysis of Large Language Models Across Diverse Conversational Tasks","created":"2024-11-26","cited_by_count":3,"area":null},{"id":"2502.18517","title":"RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis","created":"2025-02-23","cited_by_count":3,"area":"synth"},{"id":"2408.15915","title":"Leveraging Open Knowledge for Advancing Task Expertise in Large Language Models","created":"2024-08-28","cited_by_count":2,"area":"moe"},{"id":"2509.23893","title":"Dynamic Orthogonal Continual Fine-tuning for Mitigating Catastrophic Forgettings","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2406.08796","title":"Deep Exploration of Cross-Lingual Zero-Shot Generalization in Instruction Tuning","created":"2024-06-13","cited_by_count":1,"area":null},{"id":"2307.03506","title":"Derivative Free Weight-space Ensembling","created":"2023-07-07","cited_by_count":0,"area":null},{"id":"2506.13188","title":"SPOT: Bridging Natural Language and Geospatial Search for Investigative Journalists","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2506.13479","title":"Position: Pause Recycling LoRAs and Prioritize Mechanisms to Uncover Limits and Effectiveness","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2601.22146","title":"FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale","created":"2026-01-29","cited_by_count":0,"area":"synth"},{"id":"2603.24376","title":"GeoRouter: Dynamic Paradigm Routing for Worldwide Image Geolocalization","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2608.15817","title":"RLCascadeRouter: Quality-Estimator-Free Cascade Routing via Reinforcement Learning","created":"2026-08-16","cited_by_count":0,"area":"lr"},{"id":"2609.39702","title":"A helps B while B hurts A: directed transfer in instruction-tuning mixture","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}