{"total":121,"rows":[{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464,"area":null},{"id":"2407.15390","title":"ALLaM: Large Language Models for Arabic and English","created":"2024-07-22","cited_by_count":55,"area":null},{"id":"2505.11711","title":"Reinforcement Learning Finetunes Small Subnetworks in Large Language Models","created":"2025-05-16","cited_by_count":49,"area":null},{"id":"2410.03115","title":"X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale","created":"2024-10-04","cited_by_count":36,"area":null},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2506.06303","title":"Reward Is Enough: LLMs Are In-Context Reinforcement Learners","created":"2025-05-21","cited_by_count":31,"area":null},{"id":"2406.01394","title":"PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration","created":"2024-06-03","cited_by_count":28,"area":null},{"id":"2501.06521","title":"Fine-tuning Large Language Models for Improving Factuality in Legal Question Answering","created":"2025-01-11","cited_by_count":28,"area":null},{"id":"2407.10627","title":"Arena Learning: Build Data Flywheel for LLMs Post-training via Simulated Chatbot Arena","created":"2024-07-15","cited_by_count":26,"area":null},{"id":"2508.09303","title":"ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning","created":"2025-08-12","cited_by_count":26,"area":null},{"id":"2506.21495","title":"Bridging Offline and Online Reinforcement Learning for LLMs","created":"2025-06-26","cited_by_count":25,"area":null},{"id":"2502.19110","title":"Conformal Linguistic Calibration: Trading-off between Factuality and Specificity","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2502.04498","title":"Verifiable Format Control for Large Language Model Generations","created":"2025-02-06","cited_by_count":17,"area":null},{"id":"2505.23912","title":"LoVeC: Reinforcement Learning for Better Verbalized Confidence in Long-Form Generations","created":"2025-05-29","cited_by_count":17,"area":null},{"id":"2408.04342","title":"Towards Explainable Network Intrusion Detection using Large Language Models","created":"2024-08-08","cited_by_count":14,"area":null},{"id":"2508.13514","title":"ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs","created":"2025-08-19","cited_by_count":13,"area":null},{"id":"2505.18658","title":"Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2506.03483","title":"APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training","created":"2025-06-04","cited_by_count":12,"area":null},{"id":"2409.00113","title":"Wait, that's not an option: LLMs Robustness with Incorrect Multiple-Choice Options","created":"2024-08-27","cited_by_count":11,"area":null},{"id":"2503.13733","title":"CoDet-M4: Detecting Machine-Generated Code in Multi-Lingual, Multi-Generator and Multi-Domain Settings","created":"2025-03-17","cited_by_count":11,"area":null},{"id":"2509.23659","title":"Aligning LLMs for Multilingual Consistency in Enterprise Applications","created":"2025-09-28","cited_by_count":11,"area":null},{"id":"2409.12623","title":"CamelEval: Advancing Culturally Aligned Arabic Language Models and Benchmarks","created":"2024-09-19","cited_by_count":10,"area":null},{"id":"2509.14268","title":"DetectAnyLLM: Towards Generalizable and Robust Detection of Machine-Generated Text Across Domains and Models","created":"2025-09-15","cited_by_count":9,"area":null},{"id":"2510.20411","title":"Teacher Demonstrations in a BabyLM's Zone of Proximal Development for Contingent Multi-Turn Interaction","created":"2025-10-23","cited_by_count":9,"area":null},{"id":"2501.09766","title":"iTool: Reinforced Fine-Tuning with Dynamic Deficiency Calibration for Advanced Tool Use","created":"2025-01-15","cited_by_count":7,"area":null},{"id":"2603.16848","title":"Mediocrity is the key for LLM as a Judge Anchor Selection","created":"2026-03-17","cited_by_count":7,"area":null},{"id":"2406.14155","title":"Aligning Large Language Models with Diverse Political Viewpoints","created":"2024-06-20","cited_by_count":6,"area":null},{"id":"2411.05830","title":"GitChameleon: Unmasking the Version-Switching Capabilities of Code Generation Models","created":"2024-11-05","cited_by_count":6,"area":null},{"id":"2411.06824","title":"Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs","created":"2024-11-11","cited_by_count":6,"area":null},{"id":"2510.17881","title":"POPI: Personalizing LLMs via Optimized Natural Language Preference Inference","created":"2025-10-17","cited_by_count":6,"area":null},{"id":"2604.07941","title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","created":"2026-04-09","cited_by_count":6,"area":null},{"id":"2412.07633","title":"ChocoLlama: Lessons Learned From Teaching Llamas Dutch","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2502.13674","title":"SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2502.21112","title":"Optimizing Large Language Models for ESG Activity Detection in Financial Texts","created":"2025-02-28","cited_by_count":5,"area":null},{"id":"2504.05321","title":"VALUE: Value-Aware Large Language Model for Query Rewriting via Weighted Trie in Sponsored Search","created":"2025-02-25","cited_by_count":5,"area":null},{"id":"2510.10009","title":"Beyond the limitation of a single query: Train your LLM for query expansion with Reinforcement Learning","created":"2025-10-11","cited_by_count":5,"area":null},{"id":"2510.12178","title":"Evolution of meta's llama models and parameter-efficient fine-tuning of large language models: a survey","created":"2025-10-14","cited_by_count":5,"area":null},{"id":"2606.03994","title":"SimuScene: Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image","created":"2026-06-02","cited_by_count":5,"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":"2412.03527","title":"FANAL -- Financial Activity News Alerting Language Modeling Framework","created":"2024-12-04","cited_by_count":4,"area":null},{"id":"2412.06843","title":"Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs","created":"2024-12-07","cited_by_count":4,"area":null},{"id":"2412.21006","title":"Verbosity-Aware Rationale Reduction: Effective Reduction of Redundant Rationale via Principled Criteria","created":"2024-12-30","cited_by_count":4,"area":null},{"id":"2508.04329","title":"Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning","created":"2025-08-06","cited_by_count":4,"area":null},{"id":"2509.24678","title":"Reference-Free Rating of LLM Responses via Latent Information","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2510.06677","title":"Incremental Summarization for Customer Support via Progressive Note-Taking and Agent Feedback","created":"2025-10-08","cited_by_count":4,"area":null},{"id":"2512.16145","title":"MRG-R1: Reinforcement Learning for Clinically Aligned Medical Report Generation","created":"2025-12-18","cited_by_count":4,"area":null},{"id":"2604.08553","title":"GNN-as-Judge: Unleashing the Power of LLMs for Graph Learning with GNN Feedback","created":"2026-03-11","cited_by_count":4,"area":null},{"id":"2605.31140","title":"EvoDefense: Co-Evolving Black-Box Defense with Large Language Models","created":"2026-05-29","cited_by_count":4,"area":null},{"id":"2409.18170","title":"Evaluation of Large Language Models for Summarization Tasks in the Medical Domain: A Narrative Review","created":"2024-09-26","cited_by_count":3,"area":null},{"id":"2502.14645","title":"Edit Once, Update Everywhere: A Simple Framework for Cross-Lingual Knowledge Synchronization in LLMs","created":"2025-02-20","cited_by_count":3,"area":null},{"id":"2504.13603","title":"Continual Pre-Training is (not) What You Need in Domain Adaption","created":"2025-04-18","cited_by_count":3,"area":null},{"id":"2505.15353","title":"Establishing a Scale for Kullback-Leibler Divergence in Language Models Across Various Settings","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2505.19116","title":"Controlling Language Confusion in Multilingual LLMs","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2506.20666","title":"Cognitive models can reveal interpretable value trade-offs in language models","created":"2025-06-25","cited_by_count":3,"area":null},{"id":"2507.19586","title":"Mitigating Geospatial Knowledge Hallucination in Large Language Models: Benchmarking and Dynamic Factuality Aligning","created":"2025-07-25","cited_by_count":3,"area":null},{"id":"2509.16779","title":"Improving User Interface Generation Models from Designer Feedback","created":"2025-09-20","cited_by_count":3,"area":null},{"id":"2511.09002","title":"Convergence and Stability Analysis of Self-Consuming Generative Models with Heterogeneous Human Curation","created":"2025-11-12","cited_by_count":3,"area":null},{"id":"2511.12991","title":"Fine-Tuned LLMs Know They Don't Know: A Parameter-Efficient Approach to Recovering Honesty","created":"2025-11-17","cited_by_count":3,"area":null},{"id":"2606.03070","title":"ASymPO: Asymmetric-Scale Policy Optimization for Asynchronous LLM Post-Training Without Behavior Information","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2410.12989","title":"Qtok: A Comprehensive Framework for Evaluating Multilingual Tokenizer Quality in Large Language Models","created":"2024-10-16","cited_by_count":2,"area":null},{"id":"2505.02410","title":"Bielik 11B v2 Technical Report","created":"2025-05-05","cited_by_count":2,"area":null},{"id":"2505.14297","title":"Cross-Lingual Optimization for Language Transfer in Large Language Models","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2509.10708","title":"SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation","created":"2025-09-12","cited_by_count":2,"area":null},{"id":"2604.10125","title":"PhyMix: Towards Physically Consistent Single-Image 3D Indoor Scene Generation with Implicit--Explicit Optimization","created":"2026-04-11","cited_by_count":2,"area":null},{"id":"2605.30524","title":"Representation Collapse in Sequential Post-Training of Large Language Models","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2606.22676","title":"Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Representations","created":"2026-06-21","cited_by_count":2,"area":null},{"id":"2407.13561","title":"Research on Tibetan Tourism Viewpoints information generation system based on LLM","created":"2024-07-18","cited_by_count":1,"area":null},{"id":"2410.01810","title":"Propaganda is all you need","created":"2024-09-13","cited_by_count":1,"area":null},{"id":"2501.05787","title":"MARS6: A Small and Robust Hierarchical-Codec Text-to-Speech Model","created":"2025-01-10","cited_by_count":1,"area":null},{"id":"2502.12998","title":"Personalized Top-k Set Queries Over Predicted Scores","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2503.21813","title":"OAEI-LLM-T: A TBox Benchmark Dataset for Understanding Large Language Model Hallucinations in Ontology Matching","created":"2025-03-25","cited_by_count":1,"area":null},{"id":"2504.13471","title":"From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMs","created":"2025-04-18","cited_by_count":1,"area":null},{"id":"2505.14015","title":"AUTOLAW: Enhancing Legal Compliance in Large Language Models via Case Law Generation and Jury-Inspired Deliberation","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2509.18600","title":"OraPO: Oracle-educated Reinforcement Learning for Data-efficient and Factual Radiology Report Generation","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2511.17161","title":"The PLLuM Instruction Corpus","created":"2025-11-21","cited_by_count":1,"area":null},{"id":"2512.15009","title":"Model Agnostic Preference Optimization for Medical Image Segmentation","created":"2025-12-17","cited_by_count":1,"area":null},{"id":"2512.24787","title":"HiGR: Industrial-Scale Hierarchical Generative Slate Recommendation Framework in Tencent","created":"2025-12-31","cited_by_count":1,"area":null},{"id":"2605.02469","title":"Reference-Sampled Boltzmann Projection for KL-Regularized RLVR: Target-Matched Weighted SFT, Finite One-Shot Gaps, and Policy Mirror Descent","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2605.26442","title":"Alignment Tuning for Large Language Models: A Data-Centric Lens on Alignment Data Pipelines","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2608.25622","title":"Plans You Can Check: Verifier-Grounded Learning of an Open-Weight Planner for Executable Video-Editing","created":"2026-08-26","cited_by_count":1,"area":null},{"id":"2405.13386","title":"360Zhinao Technical Report","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2408.05606","title":"Exploring Applications of State Space Models and Advanced Training Techniques in Sequential Recommendations: A Comparative Study on Efficiency and Performance","created":"2024-08-10","cited_by_count":0,"area":null},{"id":"2409.13749","title":"KodeXv0.1: A Family of State-of-the-Art Financial Large Language Models","created":"2024-09-13","cited_by_count":0,"area":null},{"id":"2410.15990","title":"Augmenting Legal Decision Support Systems with LLM-based NLI for Analyzing Social Media Evidence","created":"2024-10-21","cited_by_count":0,"area":null},{"id":"2411.06850","title":"1-800-SHARED-TASKS @ NLU of Devanagari Script Languages: Detection of Language, Hate Speech, and Targets using LLMs","created":"2024-11-11","cited_by_count":0,"area":null},{"id":"2502.18480","title":"QExplorer: Large Language Model Based Query Extraction for Toxic Content Exploration","created":"2025-02-06","cited_by_count":0,"area":null},{"id":"2502.19347","title":"Controlled Diversity: Length-optimized Natural Language Generation","created":"2025-02-26","cited_by_count":0,"area":null},{"id":"2506.21536","title":"PsyLite Technical Report","created":"2025-06-26","cited_by_count":0,"area":null},{"id":"2507.15714","title":"Chinchunmei at SemEval-2025 Task 11: Boosting the Large Language Model's Capability of Emotion Perception using Contrastive Learning","created":"2025-07-21","cited_by_count":0,"area":null},{"id":"2508.18884","title":"HAEPO: History-Aggregated Exploratory Policy Optimization","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2510.03955","title":"Harnessing Synthetic Preference Data for Enhancing Temporal Understanding of Video-LLMs","created":"2025-10-04","cited_by_count":0,"area":null},{"id":"2510.17614","title":"OG-Rank: Learning to Rank Fast and Slow with Uncertainty and Reward-Trend Guided Adaptive Exploration","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2511.22169","title":"Real-Time Long Horizon Air Quality Forecasting via Group-Relative Policy Optimization","created":"2025-11-27","cited_by_count":0,"area":null},{"id":"2601.06158","title":"PsyAgent: Constructing Human-like Agents Based on Psychological Modeling and Contextual Interaction","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2601.23222","title":"Region-Normalized DPO for Medical Image Segmentation under Noisy Judges","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.03696","title":"Conflict-Resolving and Sharpness-Aware Minimization for Generalized Knowledge Editing with Multiple Updates","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.15913","title":"Foundation Models for Medical Imaging: Status, Challenges, and Directions","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2602.16856","title":"Analytic Score Optimization for Multi Dimension Video Quality Assessment","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2602.17787","title":"Market Games for Generative Models: Equilibria, Welfare, and Strategic Entry","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.02565","title":"FlashEvaluator: Expanding Search Space with Parallel Sequence-Level Evaluation","created":"2026-03-03","cited_by_count":0,"area":null}],"next_cursor":"100"}