{"total":44,"rows":[{"id":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233,"area":null},{"id":"2505.11792","title":"Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modeling","created":"2025-05-17","cited_by_count":45,"area":null},{"id":"2411.11072","title":"Multilingual Large Language Models: A Systematic Survey","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2509.16591","title":"Heterogeneous Adaptive Policy Optimization: Tailoring Optimization to Every Token's Nature","created":"2025-09-20","cited_by_count":11,"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":"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":"2508.16013","title":"Political Ideology Shifts in Large Language Models","created":"2025-08-22","cited_by_count":5,"area":null},{"id":"2508.16771","title":"EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention","created":"2025-08-22","cited_by_count":4,"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":"2412.20340","title":"Distilling Desired Comments for Enhanced Code Review with Large Language Models","created":"2024-12-29","cited_by_count":2,"area":null},{"id":"2604.05756","title":"Controlling Distributional Bias in Multi-Round LLM Generation via KL-Optimized Fine-Tuning","created":"2026-04-07","cited_by_count":2,"area":null},{"id":"2606.12360","title":"Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2606.09293","title":"One Model, Multiple Goals: Adaptive Multi-Objective Learning for E-commerce Dialogue Systems","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.29201","title":"Behavior Uncloning: Distilling Mode Redirection into Policy Weights without Inference-Time Steering","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2607.24040","title":"Pointer-Augmented Autoregressive Generation of Patent Claims with Joint Topology and Content Decoding","created":"2026-07-27","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":"2609.12373","title":"Toward Robust Personalized Alignment for LLMs: Mitigating Persona Drift in Multi-Turn Dialogue","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2609.22512","title":"Agreement Overstates Evidence: Error Dependence in LLM Judge Consensus","created":"2026-09-18","cited_by_count":1,"area":null},{"id":"2602.10430","title":"Breaking the Curse of Repulsion: Remoteness-Aware Control of Negative Off-Policy Updates","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2602.17667","title":"When & How to Write for Personalized Demand-aware Query Rewriting in Video Search","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2603.12983","title":"Is Human Annotation Necessary? Iterative MBR Distillation for Error Span Detection in Machine Translation","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2604.26553","title":"TLPO: Token-Level Policy Optimization for Mitigating Language Confusion in Large Language Models","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.06582","title":"PairAlign: A Framework for Autoregressive Tokenization via Self-Alignment with Applications to Audio Tokenization","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.30219","title":"EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.05461","title":"AdaStop: Cost-Aware Early Stopping for DNN Test Selection","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.06175","title":"Improving LLM-Generated Process Model Quality Through Reinforcement Learning: The Role of Reward Function Design","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.11434","title":"Direct Image-to-Modern Vietnamese Translation of Han-Nom Manuscripts via Multimodal RLHF Preference Alignment","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.20057","title":"Antigen-specific Antibody Multi-modal Foundation Model for Functional Antibody Design","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2607.20470","title":"PlanE: Meta Planning of Data, Tuning, and Inference for Extractive-based LLMs","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2607.21627","title":"Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2608.09095","title":"Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.13622","title":"ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.13833","title":"AdsWorldEngine: A Self-Evolving Conversational Advertising Agent through Orchestrator and Tool Coevolution","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.16082","title":"Towards Reasonable Molecular Structure Elucidation from Infrared Spectroscopy with Chemical Feedback","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.23632","title":"Function-Level Execution Feedback for Code Preference Optimization","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2608.30987","title":"Stick to What You Know: A Study of Knowledge-Aligned Supervised Fine-Tuning","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.11739","title":"LOCUS: Task-Aware Low-Rank Post-Training for Token-Efficient Language Generation","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.28942","title":"From Static Personal Values to Contextualized Personalization: Bayesian Personalized Value Alignment for LLMs","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.30218","title":"Minimally Invasive Steering of Language Models","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.35291","title":"Narrow Multimodal Fine-Tuning Can Induce Emergent Misalignment","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.00061","title":"Gradient-Aligned Pair Selection for Personalized Preference Optimization","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2610.01170","title":"HeadEdit: Calibrating Language Model Behavior Through the Frozen Unembedding Matrix","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.11012","title":"Distillation for Incrimination and Distillation for Capabilities","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.17042","title":"AD4EDU: Benchmarking University Lecture Audio Description across Accessibility Standards, Metrics, and Learner Preferences","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}