{"total":83,"rows":[{"id":"2406.15126","title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey","created":"2024-06-14","cited_by_count":244,"area":"synth"},{"id":"2402.05070","title":"A Roadmap to Pluralistic Alignment","created":"2024-02-07","cited_by_count":184,"area":"alignment"},{"id":"2405.14782","title":"Lessons from the Trenches on Reproducible Evaluation of Language Models","created":"2024-05-23","cited_by_count":179,"area":null},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157,"area":null},{"id":"2404.16019","title":"The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models","created":"2024-04-24","cited_by_count":144,"area":"alignment"},{"id":"2409.12822","title":"Language Models Learn to Mislead Humans via RLHF","created":"2024-09-19","cited_by_count":124,"area":"alignment"},{"id":"2407.11005","title":"RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems","created":"2024-06-25","cited_by_count":117,"area":"rag"},{"id":"2501.00274","title":"LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts","created":"2024-12-31","cited_by_count":87,"area":null},{"id":"2405.17977","title":"Aligning to Thousands of Preferences via System Message Generalization","created":"2024-05-28","cited_by_count":84,"area":"alignment"},{"id":"2406.20052","title":"Understanding and Mitigating Language Confusion in LLMs","created":"2024-06-28","cited_by_count":75,"area":null},{"id":"2410.03608","title":"TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generation","created":"2024-10-04","cited_by_count":68,"area":null},{"id":"2402.15018","title":"Unintended Impacts of LLM Alignment on Global Representation","created":"2024-02-22","cited_by_count":66,"area":"alignment"},{"id":"2408.17017","title":"Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling","created":"2024-08-30","cited_by_count":63,"area":"lr"},{"id":"2310.07629","title":"The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values","created":"2023-10-11","cited_by_count":54,"area":"alignment"},{"id":"2405.11804","title":"(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts","created":"2024-05-20","cited_by_count":49,"area":"agents"},{"id":"2405.01525","title":"FLAME: Factuality-Aware Alignment for Large Language Models","created":"2024-05-02","cited_by_count":47,"area":"alignment"},{"id":"2405.20850","title":"Improving Reward Models with Synthetic Critiques","created":"2024-05-31","cited_by_count":44,"area":"alignment"},{"id":"2406.06560","title":"Inverse Constitutional AI: Compressing Preferences into Principles","created":"2024-06-02","cited_by_count":41,"area":"alignment"},{"id":"2405.14394","title":"Instruction Tuning With Loss Over Instructions","created":"2024-05-23","cited_by_count":40,"area":null},{"id":"2406.15053","title":"PARIKSHA: A Large-Scale Investigation of Human-LLM Evaluator Agreement on Multilingual and Multi-Cultural Data","created":"2024-06-21","cited_by_count":37,"area":null},{"id":"2412.13091","title":"LMUnit: Fine-grained Evaluation with Natural Language Unit Tests","created":"2024-12-17","cited_by_count":33,"area":null},{"id":"2507.23751","title":"CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks","created":"2025-07-31","cited_by_count":32,"area":"lr"},{"id":"2310.13011","title":"Compositional preference models for aligning LMs","created":"2023-10-17","cited_by_count":26,"area":"alignment"},{"id":"2404.12318","title":"Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment","created":"2024-04-18","cited_by_count":26,"area":"alignment"},{"id":"2510.26202","title":"What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data","created":"2025-10-30","cited_by_count":26,"area":"alignment"},{"id":"2402.11253","title":"Aligning Large Language Models by On-Policy Self-Judgment","created":"2024-02-17","cited_by_count":20,"area":"alignment"},{"id":"2404.07900","title":"High-Dimension Human Value Representation in Large Language Models","created":"2024-04-11","cited_by_count":20,"area":null},{"id":"2402.13887","title":"Beyond Probabilities: Unveiling the Misalignment in Evaluating Large Language Models","created":"2024-02-21","cited_by_count":19,"area":null},{"id":"2406.09264","title":"Position: Towards Bidirectional Human-AI Alignment","created":"2024-06-13","cited_by_count":18,"area":"alignment"},{"id":"2409.10566","title":"Eureka: Evaluating and Understanding Large Foundation Models","created":"2024-09-13","cited_by_count":18,"area":null},{"id":"2402.11296","title":"Dissecting Human and LLM Preferences","created":"2024-02-17","cited_by_count":17,"area":"alignment"},{"id":"2606.04923","title":"Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning","created":"2026-06-03","cited_by_count":16,"area":"alignment"},{"id":"2311.13133","title":"LIMIT: Less Is More for Instruction Tuning Across Evaluation Paradigms","created":"2023-11-22","cited_by_count":14,"area":null},{"id":"2506.07326","title":"Reward Model Interpretability via Optimal and Pessimal Tokens","created":"2025-06-08","cited_by_count":10,"area":"alignment"},{"id":"2404.11288","title":"A Preference-driven Paradigm for Enhanced Translation with Large Language Models","created":"2024-04-17","cited_by_count":9,"area":null},{"id":"2507.17015","title":"Can External Validation Tools Improve Annotation Quality for LLM-as-a-Judge?","created":"2025-07-22","cited_by_count":9,"area":null},{"id":"2508.15218","title":"Are Checklists Really Useful for Automatic Evaluation of Generative Tasks?","created":"2025-08-21","cited_by_count":9,"area":null},{"id":"2509.03116","title":"Measuring Scalar Constructs in Social Science with LLMs","created":"2025-09-03","cited_by_count":9,"area":null},{"id":"2503.01894","title":"LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spaces","created":"2025-02-27","cited_by_count":8,"area":"alignment"},{"id":"2402.03469","title":"Rethinking the Role of Proxy Rewards in Language Model Alignment","created":"2024-02-02","cited_by_count":7,"area":"lr"},{"id":"2403.00435","title":"Hierarchical Indexing for Retrieval-Augmented Opinion Summarization","created":"2024-03-01","cited_by_count":7,"area":"rag"},{"id":"2409.18618","title":"Model-based Preference Optimization in Abstractive Summarization without Human Feedback","created":"2024-09-27","cited_by_count":7,"area":"alignment"},{"id":"2410.11677","title":"Understanding Likelihood Over-optimisation in Direct Alignment Algorithms","created":"2024-10-15","cited_by_count":7,"area":"alignment"},{"id":"2509.18632","title":"A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users","created":"2025-09-23","cited_by_count":6,"area":"alignment"},{"id":"2409.13641","title":"Beyond Accuracy Optimization: Computer Vision Losses for Large Language Model Fine-Tuning","created":"2024-09-20","cited_by_count":5,"area":null},{"id":"2505.11875","title":"J1: Exploring Simple Test-Time Scaling for LLM-as-a-Judge","created":"2025-05-17","cited_by_count":5,"area":"lr"},{"id":"2603.29791","title":"Reasoning-Driven Synthetic Data Generation and Evaluation","created":"2026-03-31","cited_by_count":5,"area":null},{"id":"2408.10270","title":"SEAL: Systematic Error Analysis for Value ALignment","created":"2024-08-16","cited_by_count":4,"area":"alignment"},{"id":"2412.20834","title":"Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment","created":"2024-12-30","cited_by_count":4,"area":"alignment"},{"id":"2507.13138","title":"Assessing the Reliability of LLMs Annotations in the Context of Demographic Bias and Model Explanation","created":"2025-07-17","cited_by_count":4,"area":null},{"id":"2311.07469","title":"InCA: Rethinking In-Car Conversational System Assessment Leveraging Large Language Models","created":"2023-11-13","cited_by_count":3,"area":"lr"},{"id":"2405.13541","title":"Annotation-Efficient Language Model Alignment via Diverse and Representative Response Texts","created":"2024-05-22","cited_by_count":3,"area":"alignment"},{"id":"2409.00696","title":"Polyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation","created":"2024-09-01","cited_by_count":3,"area":null},{"id":"2411.00005","title":"Mastering the Craft of Data Synthesis for CodeLLMs","created":"2024-10-16","cited_by_count":3,"area":"synth"},{"id":"2503.13102","title":"REPA: Russian Error Types Annotation for Evaluating Text Generation and Judgment Capabilities","created":"2025-03-17","cited_by_count":3,"area":null},{"id":"2603.04409","title":"Unpacking Human Preference for LLMs: Demographically Aware Evaluation with the HUMAINE Framework","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2605.30504","title":"Auditing LLM Benchmarks with Item Response Theory","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2403.09567","title":"Enhancing Trust in Autonomous Agents: An Architecture for Accountability and Explainability through Blockchain and Large Language Models","created":"2024-03-14","cited_by_count":2,"area":"agents"},{"id":"2406.12416","title":"Beyond Under-Alignment: Atomic Preference Enhanced Factuality Tuning for Large Language Models","created":"2024-06-18","cited_by_count":2,"area":"alignment"},{"id":"2408.08907","title":"What should I wear to a party in a Greek taverna? Evaluation for Conversational Agents in the Fashion Domain","created":"2024-08-13","cited_by_count":2,"area":"agents"},{"id":"2505.20088","title":"Multi-Domain Explainability of Preferences","created":"2025-05-26","cited_by_count":2,"area":"alignment"},{"id":"2601.18061","title":"Expert Evaluation and the Limits of Human Feedback in Mental Health AI Safety Testing","created":"2026-01-26","cited_by_count":2,"area":"alignment"},{"id":"2602.17185","title":"The Bots of Persuasion: Examining How Conversational Agents' Linguistic Expressions of Personality Affect User Perceptions and Decisions","created":"2026-02-19","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":"2603.16120","title":"Language Models Don't Know What You Want: Evaluating Personalization in Deep Research Needs Real Users","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2604.25224","title":"ValueBlindBench: Agreement-Gated Stress Testing of LLM-Judged Investment Rationales Before Returns Are Observable","created":"2026-04-28","cited_by_count":2,"area":null},{"id":"2606.04296","title":"The Saturation Trap and the Subjectivity of Intervention Timing: Why Affect-Based Triggers and LLM Judges Fail to Time Interventions on Autonomous Agents","created":"2026-06-02","cited_by_count":2,"area":"agents"},{"id":"2411.01245","title":"PMoL: Parameter Efficient MoE for Preference Mixing of LLM Alignment","created":"2024-11-02","cited_by_count":1,"area":"alignment"},{"id":"2504.01248","title":"Automated Factual Benchmarking for In-Car Conversational Systems using Large Language Models","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2509.15336","title":"Knowledge-Driven Hallucination in Large Language Models: An Empirical Study on Process Modeling","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2510.07892","title":"Metric Calculating Benchmark: Code-Verifiable Complicate Instruction Following Benchmark for Large Language Models","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2605.13307","title":"PRISM-X: Experiments on Personalised Fine-Tuning with Human and Simulated Users","created":"2026-05-13","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":"2508.09544","title":"SYNAPSE-G: Bridging Large Language Models and Graph Learning for Rare Event Classification","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2601.07229","title":"DiSCo: Making Absence Visible in Intelligent Summarization Interfaces","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2602.15338","title":"Discovering Implicit Large Language Model Alignment Objectives","created":"2026-02-17","cited_by_count":0,"area":"alignment"},{"id":"2605.00155","title":"Wasserstein Distributionally Robust Regret Optimization for Reinforcement Learning from Human Feedback","created":"2026-04-30","cited_by_count":0,"area":"alignment"},{"id":"2605.26840","title":"Optimising Factual Consistency in Summarisation via Preference Learning from Multiple Imperfect Metrics","created":"2026-05-26","cited_by_count":0,"area":"alignment"},{"id":"2607.05123","title":"ASSEMCAD: Production-Ready CAD Assembly Generation from Natural Language","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.22305","title":"A Roadmap to Impactful Pluralistic Alignment Research","created":"2026-07-24","cited_by_count":0,"area":"alignment"},{"id":"2608.02617","title":"Preferred, Not Safer: Pairwise Preference Is a Poor Proxy for Clinical Safety","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2608.23783","title":"Inter-dimension Dependence for Multi-Dimensional Evaluation of Open-Ended Text","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.16625","title":"AURA: Agentic Diagnosis and Refinement for Production Recommender Systems at Scale","created":"2026-09-15","cited_by_count":0,"area":"agents"}],"next_cursor":null}