{"total":45,"rows":[{"id":"2311.00176","title":"ChipNeMo: Domain-Adapted LLMs for Chip Design","created":"2023-10-31","cited_by_count":174,"area":null},{"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":"2311.14736","title":"Data Diversity Matters for Robust Instruction Tuning","created":"2023-11-21","cited_by_count":76,"area":null},{"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":"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":"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":"2406.06435","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":"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":"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":"2503.08796","title":"Robust Multi-Objective Controlled Decoding of Large Language Models","created":"2025-03-11","cited_by_count":9,"area":null},{"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":"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":"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":"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":"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":"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":"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":"2411.00524","title":"Comparison-based Active Preference Learning for Multi-dimensional Personalization","created":"2024-11-01","cited_by_count":3,"area":null},{"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":"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":"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":"2601.18483","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":"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":"2609.04738","title":"Aplaud: Adaptive Personalized Low-Rank Decomposition for User-Specific LLM","created":"2026-09-04","cited_by_count":1,"area":null},{"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":"2605.10202","title":"Task-Aware Calibration: Provably Optimal Decoding in LLMs","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2606.14695","title":"Persona-Pruner: Sculpting Lightweight Models for Role-Playing","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.16903","title":"A Method for Learning Value Systems in Generative AI","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2608.09507","title":"Learning Preference Adaptation for Large Language Model Personalization via Verbal Reinforcement Learning","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2610.04379","title":"AgentPersonaBench: Benchmarking Persona-Driven User Simulation","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.05898","title":"Collaborative Personalized Preference Alignment for LLMs under Data Deficiency","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}