{"total":115,"rows":[{"id":"2411.04427","title":"One fish, two fish, but not the whole sea: Alignment reduces language models' conceptual diversity","created":"2024-11-07","cited_by_count":58,"area":"alignment"},{"id":"2509.18658","title":"Analyzing Uncertainty of LLM-as-a-Judge: Interval Evaluations with Conformal Prediction","created":"2025-09-23","cited_by_count":27,"area":null},{"id":"2505.15229","title":"Multilingual Prompting for Improving LLM Generation Diversity","created":"2025-05-21","cited_by_count":25,"area":null},{"id":"2410.15956","title":"Do Large Language Models Have an English Accent? Evaluating and Improving the Naturalness of Multilingual LLMs","created":"2024-10-21","cited_by_count":19,"area":null},{"id":"2503.16870","title":"Sparse Logit Sampling: Accelerating Knowledge Distillation in LLMs","created":"2025-03-21","cited_by_count":16,"area":"distill"},{"id":"2503.19092","title":"Rankers, Judges, and Assistants: Towards Understanding the Interplay of LLMs in Information Retrieval Evaluation","created":"2025-03-24","cited_by_count":15,"area":null},{"id":"2501.03937","title":"A solvable model of learning generative diffusion: theory and insights","created":"2025-01-07","cited_by_count":14,"area":"diffusion"},{"id":"2502.15654","title":"Machine-generated text detection prevents language model collapse","created":"2025-02-21","cited_by_count":14,"area":"synth"},{"id":"2410.15234","title":"Bias Amplification: Large Language Models as Increasingly Biased Media","created":"2024-10-19","cited_by_count":12,"area":"synth"},{"id":"2502.06604","title":"Do we really have to filter out random noise in pre-training data for language models?","created":"2025-02-10","cited_by_count":11,"area":null},{"id":"2412.07646","title":"Searching for Structure: Investigating Emergent Communication with Large Language Models","created":"2024-12-10","cited_by_count":10,"area":null},{"id":"2601.02997","title":"From Memorization to Creativity: LLM as a Designer of Novel Neural Architectures","created":"2026-01-06","cited_by_count":10,"area":null},{"id":"2604.09377","title":"Task-Aware LLM Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarios","created":"2026-04-10","cited_by_count":10,"area":"synth"},{"id":"2502.04419","title":"Understanding and Mitigating Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks","created":"2025-02-06","cited_by_count":9,"area":"synth"},{"id":"2507.10583","title":"$\\texttt{Droid}$: A Resource Suite for AI-Generated Code Detection","created":"2025-07-11","cited_by_count":9,"area":null},{"id":"2511.20022","title":"WaymoQA: A Multi-View Visual Question Answering Dataset for Safety-Critical Reasoning in Autonomous Driving","created":"2025-11-25","cited_by_count":9,"area":"lr"},{"id":"2505.20416","title":"GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation","created":"2025-05-26","cited_by_count":8,"area":"synth"},{"id":"2510.18333","title":"Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption","created":"2025-10-21","cited_by_count":7,"area":"safety"},{"id":"2602.13855","title":"From Fluent to Verifiable: Claim-Level Auditability for Deep Research Agents","created":"2026-02-14","cited_by_count":7,"area":"agents"},{"id":"2412.02906","title":"Does Few-Shot Learning Help LLM Performance in Code Synthesis?","created":"2024-12-03","cited_by_count":6,"area":"lr"},{"id":"2412.10281","title":"One world, one opinion? The superstar effect in LLM responses","created":"2024-12-13","cited_by_count":6,"area":null},{"id":"2505.00022","title":"Aleph-Alpha-GermanWeb: Improving German-language LLM pre-training with model-based data curation and synthetic data generation","created":"2025-04-24","cited_by_count":6,"area":"synth"},{"id":"2506.15690","title":"LLM Web Dynamics: Tracing Model Collapse in a Network of LLMs","created":"2025-05-26","cited_by_count":6,"area":"synth"},{"id":"2507.03373","title":"WETBench: A Benchmark for Detecting Task-Specific Machine-Generated Text on Wikipedia","created":"2025-07-04","cited_by_count":6,"area":null},{"id":"2410.17131","title":"Self-Steering Optimization: Autonomous Preference Optimization for Large Language Models","created":"2024-10-22","cited_by_count":5,"area":"alignment"},{"id":"2501.15007","title":"Controllable Protein Sequence Generation with LLM Preference Optimization","created":"2025-01-25","cited_by_count":5,"area":null},{"id":"2508.14231","title":"Incident Analysis for AI Agents","created":"2025-08-19","cited_by_count":5,"area":null},{"id":"2508.17465","title":"Bias Amplification in Stable Diffusion's Representation of Stigma Through Skin Tones and Their Homogeneity","created":"2025-08-24","cited_by_count":5,"area":"diffusion"},{"id":"2510.15200","title":"The Economics of AI Foundation Models: Openness, Competition, and Governance","created":"2025-10-17","cited_by_count":4,"area":null},{"id":"2511.12742","title":"Stabilizing Self-Consuming Diffusion Models with Latent Space Filtering","created":"2025-11-16","cited_by_count":4,"area":"diffusion"},{"id":"2603.10374","title":"Reactive Writers: How Co-Writing with AI Changes How We Engage with Ideas","created":"2026-03-11","cited_by_count":4,"area":null},{"id":"2502.07164","title":"Does Training on Synthetic Data Make Models Less Robust?","created":"2025-02-11","cited_by_count":3,"area":"synth"},{"id":"2507.00088","title":"How large language models judge and influence human cooperation","created":"2025-06-30","cited_by_count":3,"area":null},{"id":"2508.02271","title":"Dynaword: From One-shot to Continuously Developed Datasets","created":"2025-08-04","cited_by_count":3,"area":null},{"id":"2510.04268","title":"LongTail-Swap: benchmarking language models' abilities on rare words","created":"2025-10-05","cited_by_count":3,"area":null},{"id":"2511.13052","title":"Learning from the Undesirable: Robust Adaptation of Language Models without Forgetting","created":"2025-11-17","cited_by_count":3,"area":null},{"id":"2601.19914","title":"Simulating Complex Multi-Turn Tool Calling Interactions in Stateless Execution Environments","created":"2026-01-06","cited_by_count":3,"area":"agents"},{"id":"2410.14897","title":"From Test-Taking to Test-Making: Examining LLM Authoring of Commonsense Assessment Items","created":"2024-10-18","cited_by_count":2,"area":null},{"id":"2411.04637","title":"Hands-On Tutorial: Labeling with LLM and Human-in-the-Loop","created":"2024-11-07","cited_by_count":2,"area":null},{"id":"2412.18041","title":"An information theoretic limit to data amplification","created":"2024-12-23","cited_by_count":2,"area":null},{"id":"2501.17980","title":"Limits to AI Growth: The Ecological and Social Consequences of Scaling","created":"2025-01-29","cited_by_count":2,"area":null},{"id":"2502.18518","title":"Swallowing the Poison Pills: Insights from Vulnerability Disparity Among LLMs","created":"2025-02-23","cited_by_count":2,"area":"safety"},{"id":"2504.03814","title":"Recursive Training Loops in LLMs: How training data properties modulate distribution shift in generated data?","created":"2025-04-04","cited_by_count":2,"area":null},{"id":"2504.20610","title":"Information Retrieval in the Age of Generative AI: The RGB Model","created":"2025-04-29","cited_by_count":2,"area":null},{"id":"2508.19570","title":"Generative Models for Synthetic Data: Transforming Data Mining in the GenAI Era","created":"2025-08-27","cited_by_count":2,"area":"diffusion"},{"id":"2601.05184","title":"Observations and Remedies for Large Language Model Bias in Self-Consuming Performative Loop","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2601.05882","title":"An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift","created":"2026-01-09","cited_by_count":2,"area":"alignment"},{"id":"2601.06116","title":"The Homogenization Problem in LLMs: Towards Meaningful Diversity in AI Safety","created":"2026-01-03","cited_by_count":2,"area":null},{"id":"2602.11318","title":"The Consensus Trap: Dissecting Subjectivity and the \"Ground Truth\" Illusion in Data Annotation","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2603.00883","title":"Knowledge without Wisdom: Measuring Misalignment between LLMs and Intended Impact","created":"2026-03-01","cited_by_count":2,"area":null},{"id":"2603.16142","title":"Parametric Social Identity Injection and Diversification in Public Opinion Simulation","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2605.25358","title":"AI-Associated Lexical Shifts Across 34 Languages: Cross-Lingual Convergence and Diachronic Uptake in News Writing","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2608.26958","title":"Scaling Model-Generated Distillation Data Can Make Latent Teacher Traits More Recoverable","created":"2026-08-27","cited_by_count":2,"area":"synth"},{"id":"2411.16813","title":"Incivility and Rigidity: Evaluating the Risks of Fine-Tuning LLMs for Political Argumentation","created":"2024-11-25","cited_by_count":1,"area":null},{"id":"2503.04569","title":"ValuePilot: A Two-Phase Framework for Value-Driven Decision-Making","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2503.17753","title":"Building Resource-Constrained Language Agents: A Korean Case Study on Chemical Toxicity Information","created":"2025-03-22","cited_by_count":1,"area":"agents"},{"id":"2503.22973","title":"XL-Suite: Cross-Lingual Synthetic Training and Evaluation Data for Open-Ended Generation","created":"2025-03-29","cited_by_count":1,"area":null},{"id":"2505.12381","title":"From n-gram to Attention: How Model Architectures Learn and Propagate Bias in Language Modeling","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2505.12452","title":"Missing vs. Unused Knowledge Hypothesis for Language Model Bottlenecks in Patent Understanding","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2505.18680","title":"$PD^3F$: A Pluggable and Dynamic DoS-Defense Framework Against Resource Consumption Attacks Targeting Large Language Models","created":"2025-05-24","cited_by_count":1,"area":null},{"id":"2506.21874","title":"On the Feasibility of Poisoning Text-to-Image AI Models via Adversarial Mislabeling","created":"2025-06-27","cited_by_count":1,"area":"mllm"},{"id":"2509.09629","title":"Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systems","created":"2025-09-11","cited_by_count":1,"area":"agents"},{"id":"2510.01472","title":"LLM-NAS: LLM-driven Hardware-Aware Neural Architecture Search","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2510.08245","title":"Contrastive Decoding for Synthetic Data Generation in Low-Resource Language Modeling","created":"2025-10-09","cited_by_count":1,"area":"synth"},{"id":"2510.15977","title":"Bolster Hallucination Detection via Prompt-Guided Data Augmentation","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2511.01490","title":"Synthetic Eggs in Many Baskets: The Impact of Synthetic Data Diversity on LLM Fine-Tuning","created":"2025-11-03","cited_by_count":1,"area":"synth"},{"id":"2511.12075","title":"Treatment Stitching with Schr\\\"odinger Bridge for Enhancing Offline Reinforcement Learning in Adaptive Treatment Strategies","created":"2025-11-15","cited_by_count":1,"area":"offlinerl"},{"id":"2511.17161","title":"The PLLuM Instruction Corpus","created":"2025-11-21","cited_by_count":1,"area":null},{"id":"2604.21255","title":"When Agents Look the Same: Quantifying Distillation-Induced Similarity in Tool-Use Behaviors","created":"2026-04-23","cited_by_count":1,"area":"agents"},{"id":"2604.27666","title":"VOW: Verifiable and Oblivious Watermark Detection for Large Language Models","created":"2026-04-30","cited_by_count":1,"area":"safety"},{"id":"2605.23054","title":"Model Collapse as Cultural Evolution","created":"2026-05-21","cited_by_count":1,"area":"synth"},{"id":"2606.01736","title":"Argument Collapse: LLMs Flatten Long-Form Public Debate","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.02113","title":"A Primer in Post-Training Reasoning Data: What We Know About How It Works","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2608.11426","title":"Is Convergence Inevitable? Tracing Output Homogeneity Back to Base Models","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2608.16577","title":"BabelSteering: Multilingual Safety Alignment via English Steering Vectors","created":"2026-08-17","cited_by_count":1,"area":"alignment"},{"id":"2609.00077","title":"Beneath the Diff: Diagnosing and Mitigating Algorithmic Mode Collapse in Code-Level Autonomous Research Loops","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2410.22041","title":"An LLM-based Simulation Framework for Embodied Conversational Agents in Psychological Counseling","created":"2024-10-29","cited_by_count":0,"area":"agents"},{"id":"2501.05497","title":"Spatial Information Integration in Small Language Models for Document Layout Generation and Classification","created":"2025-01-09","cited_by_count":0,"area":null},{"id":"2501.15503","title":"Domain Adaptation from Generated Multi-Weather Images for Unsupervised Maritime Object Classification","created":"2025-01-26","cited_by_count":0,"area":null},{"id":"2502.17268","title":"MonoTODia: Translating Monologue Requests to Task-Oriented Dialogues","created":"2025-02-24","cited_by_count":0,"area":null},{"id":"2505.01364","title":"Monitoring morphometric drift in lifelong learning segmentation of the spinal cord","created":"2025-05-02","cited_by_count":0,"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":"2510.08236","title":"The Hidden Bias: A Study on Explicit and Implicit Political Stereotypes in Large Language Models","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2511.02958","title":"Automatic Machine Translation Detection Using a Surrogate Multilingual Translation Model","created":"2025-11-04","cited_by_count":0,"area":null},{"id":"2511.05535","title":"Future of AI Models: A Computational perspective on Model collapse","created":"2025-10-29","cited_by_count":0,"area":"diffusion"},{"id":"2511.12301","title":"Rethinking Bias in Generative Data Augmentation for Medical AI: a Frequency Recalibration Method","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2511.15763","title":"Identifying the Supply Chain of AI for Trustworthiness and Risk Management in Critical Applications","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2512.13716","title":"ValuePilot: A Two-Phase Framework for Value-Driven Decision-Making","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2601.20099","title":"Dynamics of Human-AI Collective Knowledge on the Web: A Scalable Model and Insights for Sustainable Growth","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.08657","title":"Two-Stage Data Synthesization: A Statistics-Driven Restricted Trade-off between Privacy and Prediction","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2603.17087","title":"Ensemble Self-Training for Unsupervised Machine Translation","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.12097","title":"Temporal Flattening in LLM-Generated Text: Comparing Human and LLM Writing Trajectories","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.17312","title":"A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2604.28075","title":"Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.16279","title":"Generative AI and Two-Tiered Online Mental Health Communities","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.17775","title":"Systematic Evaluation of the Quality of Synthetic Clinical Notes Rephrased by LLMs at Million-Note Scale","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.20602","title":"Self-Training Doesn't Flatten Language -- It Restructures It: Surface Markers Amplify While Deep Syntax Dies","created":"2026-05-20","cited_by_count":0,"area":"synth"},{"id":"2605.26492","title":"Elias in the Lighthouse, Again? Diagnosing Low Diversity in LLM Stories","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.01304","title":"When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.06674","title":"What Do People Actually Want From AI? Mapping Preference Plurality","created":"2026-06-04","cited_by_count":0,"area":"alignment"}],"next_cursor":"100"}