{"total":111,"rows":[{"id":"2406.08673","title":"HelpSteer2: Open-source dataset for training top-performing reward models","created":"2024-06-12","cited_by_count":236,"area":"alignment"},{"id":"2402.10207","title":"Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment","created":"2024-02-15","cited_by_count":175,"area":"alignment"},{"id":"2311.00176","title":"ChipNeMo: Domain-Adapted LLMs for Chip Design","created":"2023-10-31","cited_by_count":174,"area":null},{"id":"2402.18571","title":"Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards","created":"2024-02-28","cited_by_count":148,"area":"alignment"},{"id":"2311.09528","title":"HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM","created":"2023-11-16","cited_by_count":142,"area":null},{"id":"2404.05993","title":"AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts","created":"2024-04-09","cited_by_count":136,"area":null},{"id":"2410.09724","title":"Taming Overconfidence in LLMs: Reward Calibration in RLHF","created":"2024-10-13","cited_by_count":112,"area":"alignment"},{"id":"2402.19085","title":"Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment","created":"2024-02-29","cited_by_count":107,"area":"alignment"},{"id":"2404.10271","title":"Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback","created":"2024-04-16","cited_by_count":100,"area":"alignment"},{"id":"2406.18853","title":"Decoding-Time Language Model Alignment with Multiple Objectives","created":"2024-06-27","cited_by_count":94,"area":"alignment"},{"id":"2402.02030","title":"Panacea: Pareto Alignment via Preference Adaptation for LLMs","created":"2024-02-03","cited_by_count":80,"area":"alignment"},{"id":"2311.14736","title":"Data Diversity Matters for Robust Instruction Tuning","created":"2023-11-21","cited_by_count":76,"area":null},{"id":"2410.00847","title":"Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown","created":"2024-10-01","cited_by_count":74,"area":"alignment"},{"id":"2404.04925","title":"Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers","created":"2024-04-07","cited_by_count":51,"area":"lr"},{"id":"2311.04235","title":"Can LLMs Follow Simple Rules?","created":"2023-11-06","cited_by_count":46,"area":null},{"id":"2502.12446","title":"Multi-Attribute Steering of Language Models via Targeted Intervention","created":"2025-02-18","cited_by_count":46,"area":null},{"id":"2503.17003","title":"A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications","created":"2025-03-21","cited_by_count":42,"area":"alignment"},{"id":"2405.01481","title":"NeMo-Aligner: Scalable Toolkit for Efficient Model Alignment","created":"2024-05-02","cited_by_count":41,"area":"alignment"},{"id":"2410.12896","title":"A Survey on Data Synthesis and Augmentation for Large Language Models","created":"2024-10-16","cited_by_count":41,"area":"synth"},{"id":"2404.05875","title":"CodecLM: Aligning Language Models with Tailored Synthetic Data","created":"2024-04-08","cited_by_count":39,"area":"alignment"},{"id":"2410.08968","title":"Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements","created":"2024-10-11","cited_by_count":36,"area":"alignment"},{"id":"2408.15313","title":"Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models","created":"2024-08-27","cited_by_count":27,"area":"alignment"},{"id":"2402.10884","title":"Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language Models","created":"2024-02-16","cited_by_count":26,"area":"mllm"},{"id":"2406.11191","title":"A Survey on Human Preference Learning for Large Language Models","created":"2024-06-17","cited_by_count":24,"area":"alignment"},{"id":"2410.11718","title":"Converging to a Lingua Franca: Evolution of Linguistic Regions and Semantics Alignment in Multilingual Large Language Models","created":"2024-10-15","cited_by_count":23,"area":null},{"id":"2503.00295","title":"Robust Multi-Objective Preference Alignment with Online DPO","created":"2025-03-01","cited_by_count":22,"area":"alignment"},{"id":"2407.12858","title":"Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)","created":"2024-07-10","cited_by_count":20,"area":null},{"id":"2502.10441","title":"AI Alignment at Your Discretion","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2410.03837","title":"Learning Code Preference via Synthetic Evolution","created":"2024-10-04","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":"2505.18325","title":"Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary","created":"2025-05-23","cited_by_count":18,"area":"safety"},{"id":"2505.02666","title":"A Survey on Progress in LLM Alignment from the Perspective of Reward Design","created":"2025-05-05","cited_by_count":15,"area":"alignment"},{"id":"2406.06435","title":"Language Models are Alignable Decision-Makers: Dataset and Application to the Medical Triage Domain","created":"2024-06-10","cited_by_count":14,"area":null},{"id":"2412.06748","title":"Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models","created":"2024-12-09","cited_by_count":14,"area":null},{"id":"2412.10427","title":"Identifying and Manipulating Personality Traits in LLMs Through Activation Engineering","created":"2024-12-10","cited_by_count":14,"area":null},{"id":"2502.10762","title":"Bone Soups: A Seek-and-Soup Model Merging Approach for Controllable Multi-Objective Generation","created":"2025-02-15","cited_by_count":14,"area":null},{"id":"2510.20369","title":"Ask a Strong LLM Judge when Your Reward Model is Uncertain","created":"2025-10-23","cited_by_count":13,"area":"alignment"},{"id":"2410.01532","title":"Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language Models","created":"2024-10-02","cited_by_count":12,"area":"alignment"},{"id":"2411.02688","title":"On the Loss of Context-awareness in General Instruction Fine-tuning","created":"2024-11-05","cited_by_count":11,"area":null},{"id":"2505.24846","title":"MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning","created":"2025-05-30","cited_by_count":11,"area":"alignment"},{"id":"2410.08067","title":"Reward-Augmented Data Enhances Direct Preference Alignment of LLMs","created":"2024-10-10","cited_by_count":10,"area":"alignment"},{"id":"2501.18858","title":"BRiTE: Bootstrapping Reinforced Thinking Process to Enhance Language Model Reasoning","created":"2025-01-31","cited_by_count":10,"area":"lr"},{"id":"2504.10823","title":"CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectives","created":"2025-04-15","cited_by_count":10,"area":null},{"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":"2411.16502","title":"Interpreting Language Reward Models via Contrastive Explanations","created":"2024-11-25","cited_by_count":9,"area":"alignment"},{"id":"2503.08796","title":"Robust Multi-Objective Controlled Decoding of Large Language Models","created":"2025-03-11","cited_by_count":9,"area":null},{"id":"2508.05775","title":"Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM","created":"2025-08-07","cited_by_count":9,"area":"alignment"},{"id":"2605.20613","title":"HRM-Text: Efficient Pretraining Beyond Scaling","created":"2026-05-20","cited_by_count":9,"area":null},{"id":"2402.10453","title":"Steering Conversational Large Language Models for Long Emotional Support Conversations","created":"2024-02-16","cited_by_count":8,"area":null},{"id":"2410.14676","title":"SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment","created":"2024-10-18","cited_by_count":8,"area":"alignment"},{"id":"2505.20645","title":"STEER-BENCH: A Benchmark for Evaluating the Steerability of Large Language Models","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2405.07703","title":"OpenLLM-Ro -- Technical Report on Open-source Romanian LLMs","created":"2024-05-13","cited_by_count":7,"area":null},{"id":"2505.04993","title":"Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes","created":"2025-05-08","cited_by_count":7,"area":"alignment"},{"id":"2409.11212","title":"Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization","created":"2024-09-17","cited_by_count":6,"area":"alignment"},{"id":"2412.19819","title":"ChipAlign: Instruction Alignment in Large Language Models for Chip Design via Geodesic Interpolation","created":"2024-12-15","cited_by_count":6,"area":null},{"id":"2501.15453","title":"Data-adaptive Safety Rules for Training Reward Models","created":"2025-01-26","cited_by_count":6,"area":"alignment"},{"id":"2503.17482","title":"What's Producible May Not Be Reachable: Measuring the Steerability of Generative Models","created":"2025-03-21","cited_by_count":6,"area":null},{"id":"2604.07941","title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","created":"2026-04-09","cited_by_count":6,"area":null},{"id":"2407.16970","title":"Towards Aligning Language Models with Textual Feedback","created":"2024-07-24","cited_by_count":5,"area":"alignment"},{"id":"2410.22944","title":"Focus On This, Not That! Steering LLMs with Adaptive Feature Specification","created":"2024-10-30","cited_by_count":5,"area":null},{"id":"2504.11337","title":"REWARD CONSISTENCY: Improving Multi-Objective Alignment from a Data-Centric Perspective","created":"2025-04-15","cited_by_count":5,"area":"alignment"},{"id":"2603.12298","title":"Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency","created":"2026-03-12","cited_by_count":5,"area":"mechinterp"},{"id":"2603.13683","title":"Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation","created":"2026-03-14","cited_by_count":5,"area":null},{"id":"2405.17956","title":"Unified Preference Optimization: Language Model Alignment Beyond the Preference Frontier","created":"2024-05-28","cited_by_count":4,"area":"alignment"},{"id":"2504.16628","title":"ParetoHqD: Fast Offline Multiobjective Alignment of Large Language Models using Pareto High-quality Data","created":"2025-04-23","cited_by_count":4,"area":"alignment"},{"id":"2512.17093","title":"A Solver-in-the-Loop Framework for Improving LLMs on Answer Set Programming for Logic Puzzle Solving","created":"2025-12-18","cited_by_count":4,"area":null},{"id":"2602.12116","title":"P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling","created":"2026-02-12","cited_by_count":4,"area":"alignment"},{"id":"2604.12479","title":"Meet Dynamic Individual Preferences: Resolving Conflicting Human Value with Paired Fine-Tuning","created":"2026-04-14","cited_by_count":4,"area":"alignment"},{"id":"2405.00578","title":"The Real, the Better: Aligning Large Language Models with Online Human Behaviors","created":"2024-05-01","cited_by_count":3,"area":"alignment"},{"id":"2411.00524","title":"Comparison-based Active Preference Learning for Multi-dimensional Personalization","created":"2024-11-01","cited_by_count":3,"area":null},{"id":"2503.10927","title":"OASST-ETC Dataset: Alignment Signals from Eye-tracking Analysis of LLM Responses","created":"2025-03-13","cited_by_count":3,"area":"alignment"},{"id":"2410.06965","title":"Uncovering Factor Level Preferences to Improve Human-Model Alignment","created":"2024-10-09","cited_by_count":2,"area":"alignment"},{"id":"2410.19206","title":"Inference time LLM alignment in single and multidomain preference spectrum","created":"2024-10-24","cited_by_count":2,"area":"alignment"},{"id":"2503.10675","title":"Beyond One-Size-Fits-All Summarization: Customizing Summaries for Diverse Users","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2508.12622","title":"Consiglieres in the Shadow: Understanding the Use of Uncensored Large Language Models in Cybercrimes","created":"2025-08-18","cited_by_count":2,"area":"safety"},{"id":"2510.20498","title":"Robust Preference Alignment via Directional Neighborhood Consensus","created":"2025-10-23","cited_by_count":2,"area":"alignment"},{"id":"2601.14032","title":"RM-Distiller: Exploiting Generative LLM for Reward Model Distillation","created":"2026-01-20","cited_by_count":2,"area":"alignment"},{"id":"2604.04704","title":"IDIOLEX: Unified and Continuous Representations for Idiolectal and Stylistic Variation","created":"2026-04-06","cited_by_count":2,"area":null},{"id":"2607.01250","title":"Structuring the Space of Sociotechnical Alignment","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2505.04260","title":"Steerable Chatbots: Exploring Personalization Control Interfaces via LLM Activation Steering","created":"2025-05-07","cited_by_count":1,"area":"mechinterp"},{"id":"2510.20800","title":"Compress to Impress: Efficient LLM Adaptation Using a Single Gradient Step on 100 Samples","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2511.00220","title":"Iterative Foundation Model Fine-Tuning on Multiple Rewards","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2601.13669","title":"CommunityBench: Benchmarking Community-Level Alignment across Diverse Groups and Tasks","created":"2026-01-20","cited_by_count":1,"area":"alignment"},{"id":"2601.18483","title":"Funny or Persuasive, but Not Both: Evaluating Fine-Grained Multi-Concept Control in LLMs","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2602.01128","title":"Tangent Space Fine-Tuning for Directional Preference Alignment in Large Language Models","created":"2026-02-01","cited_by_count":1,"area":"alignment"},{"id":"2605.26442","title":"Alignment Tuning for Large Language Models: A Data-Centric Lens on Alignment Data Pipelines","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2607.14485","title":"Step-Level Preference Learning for Generative Agents in Social Simulations","created":"2026-07-16","cited_by_count":1,"area":"agents"},{"id":"2609.04738","title":"Aplaud: Adaptive Personalized Low-Rank Decomposition for User-Specific LLM","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2507.09060","title":"CALMA: A Process for Deriving Context-aligned Axes for Language Model Alignment","created":"2025-07-11","cited_by_count":0,"area":"alignment"},{"id":"2508.05165","title":"Aligning LLMs on a Budget: Inference-Time Alignment with Heuristic Reward Models","created":"2025-08-07","cited_by_count":0,"area":"alignment"},{"id":"2511.16209","title":"PSM: Prompt Sensitivity Minimization via LLM-Guided Black-Box Optimization","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2512.13714","title":"AI-Powered Annotation Pipelines for Stabilizing Large Language Models: A Human-AI Synergy Approach","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2604.01312","title":"Preference learning in shades of gray: Interpretable and bias-aware reward modeling for human preferences","created":"2026-04-01","cited_by_count":0,"area":"alignment"},{"id":"2604.01787","title":"DEFT: Distribution-guided Efficient Fine-Tuning for Human Alignment","created":"2026-04-02","cited_by_count":0,"area":"alignment"},{"id":"2604.15577","title":"Reward Weighted Classifier-Free Guidance as Policy Improvement in Autoregressive Models","created":"2026-04-16","cited_by_count":0,"area":"alignment"},{"id":"2604.23067","title":"Training a General Purpose Automated Red Teaming Model","created":"2026-04-24","cited_by_count":0,"area":"safety"},{"id":"2604.24996","title":"Sparse Personalized Text Generation with Multi-Trajectory Reasoning","created":"2026-04-27","cited_by_count":0,"area":"lr"},{"id":"2605.10202","title":"Task-Aware Calibration: Provably Optimal Decoding in LLMs","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.16345","title":"Goal-Conditioned Supervised Learning for LLM Fine-Tuning","created":"2026-05-08","cited_by_count":0,"area":"alignment"},{"id":"2605.26878","title":"Multi-Stakeholder LLM Alignment: Decomposing Estimation from Aggregation","created":"2026-05-26","cited_by_count":0,"area":"alignment"}],"next_cursor":"100"}