{"total":19,"rows":[{"id":"2404.14367","title":"Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data","created":"2024-04-22","cited_by_count":185,"area":null},{"id":"2406.11704","title":"Nemotron-4 340B Technical Report","created":"2024-06-17","cited_by_count":144,"area":null},{"id":"2503.07067","title":"DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs","created":"2025-03-10","cited_by_count":84,"area":null},{"id":"2502.09053","title":"Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontiers","created":"2025-02-13","cited_by_count":16,"area":null},{"id":"2410.20749","title":"Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs","created":"2024-10-28","cited_by_count":9,"area":null},{"id":"2406.17312","title":"Not All Preference Pairs Are Created Equal: A Recipe for Annotation-Efficient Iterative Preference Learning","created":"2024-06-25","cited_by_count":7,"area":null},{"id":"2505.21959","title":"EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles","created":"2025-05-28","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":"2502.10505","title":"Preference learning made easy: Everything should be understood through win rate","created":"2025-02-14","cited_by_count":3,"area":null},{"id":"2408.16667","title":"Iterative Graph Alignment","created":"2024-08-29","cited_by_count":2,"area":null},{"id":"2602.00861","title":"Multi-Head Attention Is a Multi-Player Game","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2410.04571","title":"EnsemW2S: Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles","created":"2024-10-06","cited_by_count":1,"area":null},{"id":"2502.01127","title":"The Battling Influencers Game: Nash Equilibria Structure of a Potential Game and Implications to Value Alignment","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2603.01973","title":"CharacterFlywheel: Scaling Iterative Improvement of Engaging and Steerable LLMs in Production","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2601.19055","title":"Principled Fine-tuning of LLMs from User-Edits: A Medley of Preference, Supervision, and Reward","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.18437","title":"FineRef: Fine-Grained Error Reflection and Correction for Long-Form Generation with Citations","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2602.19041","title":"Back to Blackwell: Closing the Loop on Intransitivity in Multi-Objective Preference Fine-Tuning","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2609.22839","title":"A Horizon-Independent Regret Bound for Optimistic Hedge in General-Sum Games","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.31897","title":"Context-dependent agent evaluation with orthogonal equilibrium learning","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}