{"total":100,"rows":[{"id":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233,"area":null},{"id":"2505.13995","title":"ELEPHANT: Measuring and understanding social sycophancy in LLMs","created":"2025-05-20","cited_by_count":129,"area":null},{"id":"2502.01534","title":"Preference Leakage: A Contamination Problem in LLM-as-a-judge","created":"2025-02-03","cited_by_count":125,"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":"2408.16673","title":"Preserving Diversity in Supervised Fine-Tuning of Large Language Models","created":"2024-08-29","cited_by_count":70,"area":null},{"id":"2406.06144","title":"Language Models Resist Alignment: Evidence From Data Compression","created":"2024-06-10","cited_by_count":53,"area":null},{"id":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52,"area":null},{"id":"2412.10271","title":"Benchmarking Linguistic Diversity of Large Language Models","created":"2024-12-13","cited_by_count":38,"area":null},{"id":"2504.12285","title":"BitNet b1.58 2B4T Technical Report","created":"2025-04-16","cited_by_count":38,"area":null},{"id":"2504.05747","title":"SEA-LION: Southeast Asian Languages in One Network","created":"2025-04-08","cited_by_count":22,"area":null},{"id":"2411.15242","title":"The Zamba2 Suite: Technical Report","created":"2024-11-22","cited_by_count":21,"area":null},{"id":"2502.10441","title":"AI Alignment at Your Discretion","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2509.21117","title":"TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them","created":"2025-09-25","cited_by_count":20,"area":null},{"id":"2411.11072","title":"Multilingual Large Language Models: A Systematic Survey","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2407.20999","title":"MoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-Tuning","created":"2024-07-30","cited_by_count":14,"area":null},{"id":"2410.09247","title":"Benchmark Inflation: Revealing LLM Performance Gaps Using Retro-Holdouts","created":"2024-10-11","cited_by_count":14,"area":null},{"id":"2502.13259","title":"HumT DumT: Measuring and controlling human-like language in LLMs","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2504.21202","title":"Automatic Legal Writing Evaluation of LLMs","created":"2025-04-29","cited_by_count":12,"area":null},{"id":"2501.17178","title":"Tuning LLM Judge Design Decisions for 1/1000 of the Cost","created":"2025-01-24","cited_by_count":11,"area":null},{"id":"2502.14019","title":"Dehumanizing Machines: Mitigating Anthropomorphic Behaviors in Text Generation Systems","created":"2025-02-19","cited_by_count":11,"area":null},{"id":"2505.15433","title":"Set-LLM: A Permutation-Invariant LLM","created":"2025-05-21","cited_by_count":11,"area":null},{"id":"2506.13326","title":"VIS-Shepherd: Constructing Critic for LLM-based Data Visualization Generation","created":"2025-06-16","cited_by_count":9,"area":null},{"id":"2406.14026","title":"Demystifying Language Model Forgetting with Low-rank Example Associations","created":"2024-06-20","cited_by_count":8,"area":null},{"id":"2410.11182","title":"A Middle Path for On-Premises LLM Deployment: Preserving Privacy Without Sacrificing Model Confidentiality","created":"2024-10-15","cited_by_count":8,"area":null},{"id":"2504.00623","title":"Efficient Construction of Model Family through Progressive Training Using Model Expansion","created":"2025-04-01","cited_by_count":8,"area":null},{"id":"2507.15066","title":"Time-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedback","created":"2025-07-20","cited_by_count":8,"area":null},{"id":"2605.22817","title":"Vector Policy Optimization: Training for Diversity Improves Test-Time Search","created":"2026-05-21","cited_by_count":8,"area":null},{"id":"2504.09389","title":"Measuring LLM Novelty As The Frontier Of Original And High-Quality Output","created":"2025-04-13","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2602.06625","title":"FairJudge: An Adaptive, Debiased, and Consistent LLM-as-a-Judge","created":"2026-02-06","cited_by_count":5,"area":null},{"id":"2412.04092","title":"GEITje 7B Ultra: A Conversational Model for Dutch","created":"2024-12-05","cited_by_count":4,"area":null},{"id":"2504.11381","title":"RankAlign: A Ranking View of the Generator-Validator Gap in Large Language Models","created":"2025-04-15","cited_by_count":4,"area":null},{"id":"2506.06686","title":"Learning Distribution-Wise Control in Representation Space for Language Models","created":"2025-06-07","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":"2511.00382","title":"Efficiency vs. Alignment: Investigating Safety and Fairness Risks in Parameter-Efficient Fine-Tuning of LLMs","created":"2025-11-01","cited_by_count":4,"area":null},{"id":"2602.09003","title":"Data Science and Technology Towards AGI Part I: Tiered Data Management","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2605.14967","title":"InfoSFT: Learn More and Forget Less with Information-Aware Token Weighting","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2605.30803","title":"PReMISE: Policy Rubrics as Measurement Specifications for LLM Judges","created":"2026-05-29","cited_by_count":4,"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":"2508.15815","title":"User-Assistant Bias in LLMs","created":"2025-08-16","cited_by_count":3,"area":null},{"id":"2510.07000","title":"Pragyaan: Designing and Curating High-Quality Cultural Post-Training Datasets for Indian Languages","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2510.09103","title":"AdaPM: a Partial Momentum Algorithm for LLM Training","created":"2025-10-10","cited_by_count":3,"area":null},{"id":"2510.17389","title":"EduAdapt: A Question Answer Benchmark Dataset for Evaluating Grade-Level Adaptability in LLMs","created":"2025-10-20","cited_by_count":3,"area":null},{"id":"2604.04204","title":"How Does \"English (US)\" Become the Default? Triangulating Structural Bias Towards American English Across the LLM Pipeline","created":"2026-04-05","cited_by_count":3,"area":null},{"id":"2605.13467","title":"PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2410.13841","title":"A Unified View of Delta Parameter Editing in Post-Trained Large-Scale Models","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2411.02930","title":"Textual Aesthetics in Large Language Models","created":"2024-11-05","cited_by_count":2,"area":null},{"id":"2411.07120","title":"Lean and Mean Adaptive Optimization via Subset-Norm and Subspace-Momentum with Convergence Guarantees","created":"2024-11-11","cited_by_count":2,"area":null},{"id":"2501.05465","title":"Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)","created":"2025-01-03","cited_by_count":2,"area":null},{"id":"2510.09316","title":"A Survey of LLM Prompt Datasets: Taxonomy, Linguistic Patterns, and Practical Uses","created":"2025-10-10","cited_by_count":2,"area":null},{"id":"2510.21180","title":"Social Simulations with Large Language Model Risk Utopian Illusion","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2510.25770","title":"E-Scores for (In)Correctness Assessment of Generative Model Outputs","created":"2025-10-29","cited_by_count":2,"area":null},{"id":"2602.21215","title":"Inference-time Alignment via Sparse Junction Steering","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2606.13808","title":"The Culture Funnel: You Can't Align What isn't in the Data","created":"2026-06-11","cited_by_count":2,"area":null},{"id":"2606.29184","title":"BaRA: Bayesian Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning","created":"2026-06-28","cited_by_count":2,"area":null},{"id":"2606.30931","title":"RoPoLL: Robust Panel of LLM Judges","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2609.38827","title":"More Choices, Fewer Decisions: Ordinal-Scale Bias in JEV-like Direct-Decision Models","created":"2026-09-30","cited_by_count":2,"area":null},{"id":"2506.02449","title":"IP-Dialog: Evaluating Implicit Personalization in Dialogue Systems with Synthetic Data","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2506.19325","title":"FEAT: A Preference Feedback Dataset through a Cost-Effective Auto-Generation and Labeling Framework for English AI Tutoring","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2510.08145","title":"Mitigating Judgment Preference Bias in Large Language Models through Group-Based Polling","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2603.00963","title":"Stabilizing Policy Optimization via Logits Convexity","created":"2026-03-01","cited_by_count":1,"area":null},{"id":"2605.09227","title":"Two Ways to De-Bias an LLM-as-a-Judge: A Continuous-Score Comparison of Hierarchical Bayesian Calibration and Neural-ODE Score Transport","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2605.13695","title":"RTLC -- Research, Teach-to-Learn, Critique: A three-stage prompting paradigm inspired by the Feynman Learning Technique that lifts LLM-as-judge accuracy on JudgeBench with no fine-tuning","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2606.11196","title":"PoQ-Judge: A Multi-Architecture Evaluation Framework for Cost-Aware Proof-of-Quality in Decentralized LLM Inference","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2606.12385","title":"Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2606.32029","title":"When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2607.04733","title":"LP-SFT: Keeping Plausible Alternatives Alive in Supervised Fine-Tuning","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2607.07669","title":"DiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2608.12097","title":"Graph-Structured Rubrics: Compiling Rubrics into Typed Evaluation Graphs for LLM Judges","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2609.00892","title":"CARE: Contrastive Anchor-based Rubric Evolution for Large Language Model Post-Training","created":"2026-09-01","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":"2506.23979","title":"TaP: A Taxonomy-Guided Framework for Automated and Scalable Preference Data Generation","created":"2025-06-30","cited_by_count":0,"area":null},{"id":"2509.04442","title":"Delta Activations: A Representation for Finetuned Large Language Models","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2511.10868","title":"Go-UT-Bench: A Fine-Tuning Dataset for LLM-Based Unit Test Generation in Go","created":"2025-11-14","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":"2603.21438","title":"PROMPT2BOX:Improving LLM Weakness Discovery and Specificity Estimation by Uncovering Entailment Structure among Prompts","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2604.10557","title":"LLMs Should Incorporate Explicit Mechanisms for Human Empathy","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2605.07162","title":"CLIPer: Tailoring Diverse User Preference via Classifier-Guided Inference-Time Personalization","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.07724","title":"Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.07925","title":"How Value Induction Reshapes LLM Behaviour","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.27441","title":"A Unified Structured Query Understanding Framework for Industrial Semantic Search","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.00544","title":"Escaping the Mode Lottery: Multi-Response Training Improves Language Model Generalization","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2606.12332","title":"Measuring Semantic Progress in Multi-turn Dialogue via Information Gain","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2607.16122","title":"CRAFT: Clustering Rubrics to Diagnose Weak LLM Capabilities and Generate Targeted Fine-Tuning Data","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2607.22632","title":"VlogReward: Learning Multi-Dimensional Evaluation for Vlog Editing","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.25063","title":"Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.26529","title":"Multi-Expert Conformal Risk Control for Pairwise LLM Judging in Open-Ended Dialogue","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2608.26762","title":"Equal Ranking Quality, Different Decisions: Measuring and Reducing Order Dependence in LLM Scorers","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.24128","title":"OSCAR: Order-aware Sensitivity Correction for AI Rankings","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.30751","title":"Backbone-Adaptive Evidence Routing for Robust Pairwise LLM Judging","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.33194","title":"Orthogonal Witness Control for Muon Optimization via Sigmoid Spectral Reshaping","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.34348","title":"Commutator Memory: Sparse, Path-Local Reading and Steering in Language Models","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.34850","title":"From Soft Targets to Reward Signals: How Assignment and Reward Objectives Interact","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35392","title":"The Hidden Ratio in Adam: Stable Structure, Compression, and Sign Dynamics","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36705","title":"JudgeProfile: Understanding and Steering Subjectivity in LLM Judges","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00389","title":"MatrixReward: Reward from Rubric Matrix for Open-Ended Generation","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.11458","title":"Generative Adversarial Loops","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.15028","title":"UltraBERT: Beyond the Limit of BERT Pre-Training","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.17158","title":"The Format is the Filter: Scoring Format Fixes What an LLM Judge Can Express","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.19685","title":"Beyond Distribution Matching: Selective Margin Preservation for Supervised Fine-Tuning","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}