{"total":71,"rows":[{"id":"2402.05070","title":"A Roadmap to Pluralistic Alignment","created":"2024-02-07","cited_by_count":184,"area":"alignment"},{"id":"2407.01219","title":"Searching for Best Practices in Retrieval-Augmented Generation","created":"2024-07-01","cited_by_count":83,"area":"rag"},{"id":"2406.05954","title":"Aligning Large Language Models with Representation Editing: A Control Perspective","created":"2024-06-10","cited_by_count":64,"area":"alignment"},{"id":"2406.14144","title":"Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons","created":"2024-06-20","cited_by_count":53,"area":"alignment"},{"id":"2402.15179","title":"Advancing Parameter Efficiency in Fine-tuning via Representation Editing","created":"2024-02-23","cited_by_count":37,"area":null},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33,"area":"alignment"},{"id":"2409.15360","title":"Reward-Robust RLHF in LLMs","created":"2024-09-18","cited_by_count":32,"area":"alignment"},{"id":"2502.12961","title":"Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger","created":"2025-02-18","cited_by_count":30,"area":"agents"},{"id":"2401.16332","title":"Tradeoffs Between Alignment and Helpfulness in Language Models with Steering Methods","created":"2024-01-29","cited_by_count":28,"area":"alignment"},{"id":"2505.13077","title":"Advancing Sequential Numerical Prediction in Autoregressive Models","created":"2025-05-19","cited_by_count":26,"area":null},{"id":"2402.18120","title":"Exploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?","created":"2024-02-28","cited_by_count":24,"area":"alignment"},{"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":"2402.10688","title":"Towards Uncovering How Large Language Model Works: An Explainability Perspective","created":"2024-02-16","cited_by_count":22,"area":"lr"},{"id":"2502.17601","title":"Representation Engineering for Large-Language Models: Survey and Research Challenges","created":"2025-02-24","cited_by_count":21,"area":"mechinterp"},{"id":"2602.03619","title":"Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation","created":"2026-02-03","cited_by_count":18,"area":"alignment"},{"id":"2510.11978","title":"Learning Dynamics of VLM Finetuning","created":"2025-10-13","cited_by_count":17,"area":"alignment"},{"id":"2405.20216","title":"Boost Your Human Image Generation Model via Direct Preference Optimization","created":"2024-05-30","cited_by_count":16,"area":"alignment"},{"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":"2505.19653","title":"Token-Importance Guided Direct Preference Optimization","created":"2025-05-26","cited_by_count":14,"area":"alignment"},{"id":"2602.01654","title":"Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models","created":"2026-02-02","cited_by_count":13,"area":"mechinterp"},{"id":"2505.15110","title":"RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversals","created":"2025-05-21","cited_by_count":10,"area":"lr"},{"id":"2505.16610","title":"From Generic Empathy to Personalized Emotional Support: A Self-Evolution Framework for User Preference Alignment","created":"2025-05-22","cited_by_count":9,"area":"alignment"},{"id":"2509.08486","title":"Too Helpful, Too Harmless, Too Honest or Just Right?","created":"2025-09-10","cited_by_count":9,"area":"moe"},{"id":"2508.08846","title":"Steering Towards Fairness: Mitigating Political Bias in LLMs","created":"2025-08-12","cited_by_count":7,"area":null},{"id":"2402.09320","title":"ICDPO: Effectively Borrowing Alignment Capability of Others via In-context Direct Preference Optimization","created":"2024-02-14","cited_by_count":6,"area":"alignment"},{"id":"2402.14760","title":"Generalizing Reward Modeling for Out-of-Distribution Preference Learning","created":"2024-02-22","cited_by_count":6,"area":"alignment"},{"id":"2502.13946","title":"Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region","created":"2025-02-19","cited_by_count":6,"area":"alignment"},{"id":"2504.05652","title":"Sugar-Coated Poison: Benign Generation Unlocks LLM Jailbreaking","created":"2025-04-08","cited_by_count":6,"area":"safety"},{"id":"2507.13236","title":"Enhancing Cross-task Transfer of Large Language Models via Activation Steering","created":"2025-07-17","cited_by_count":6,"area":"mechinterp"},{"id":"2405.16964","title":"Exploring the LLM Journey from Cognition to Expression with Linear Representations","created":"2024-05-27","cited_by_count":5,"area":"alignment"},{"id":"2407.01461","title":"Enhancing the Capability and Robustness of Large Language Models through Reinforcement Learning-Driven Query Refinement","created":"2024-07-01","cited_by_count":5,"area":"safety"},{"id":"2410.05097","title":"DreamSat: Towards a General 3D Model for Novel View Synthesis of Space Objects","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2508.16013","title":"Political Ideology Shifts in Large Language Models","created":"2025-08-22","cited_by_count":5,"area":null},{"id":"2508.15182","title":"SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks","created":"2025-08-21","cited_by_count":4,"area":"safety"},{"id":"2511.04341","title":"Monitor-Generate-Verify (MGV): Formalising Metacognitive Theory for Language Model Reasoning","created":"2025-11-06","cited_by_count":4,"area":"lr"},{"id":"2406.01931","title":"Dishonesty in Helpful and Harmless Alignment","created":"2024-06-04","cited_by_count":3,"area":"alignment"},{"id":"2409.16913","title":"Tell Me What You Don't Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2410.08442","title":"JurEE not Judges: safeguarding llm interactions with small, specialised Encoder Ensembles","created":"2024-10-11","cited_by_count":3,"area":null},{"id":"2506.17231","title":"Efficient and Stealthy Jailbreak Attacks via Adversarial Prompt Distillation from LLMs to SLMs","created":"2025-05-26","cited_by_count":3,"area":"safety"},{"id":"2509.22510","title":"We Think, Therefore We Align LLMs to Helpful, Harmless and Honest Before They Go Wrong","created":"2025-09-26","cited_by_count":3,"area":"lr"},{"id":"2509.23982","title":"Toward Preference-aligned Large Language Models via Residual-based Model Steering","created":"2025-09-28","cited_by_count":3,"area":"alignment"},{"id":"2510.16374","title":"Before you <think>, monitor: Implementing Flavell's metacognitive framework in LLMs","created":"2025-10-18","cited_by_count":3,"area":"lr"},{"id":"2511.00040","title":"Semi-Supervised Preference Optimization with Limited Feedback","created":"2025-10-28","cited_by_count":3,"area":"alignment"},{"id":"2505.19333","title":"Evaluating Steering Techniques using Human Similarity Judgments","created":"2025-05-25","cited_by_count":2,"area":null},{"id":"2509.23146","title":"Tree Reward-Aligned Search for TReASURe in Masked Diffusion Language Models","created":"2025-09-27","cited_by_count":2,"area":"diffusion"},{"id":"2510.12121","title":"Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2603.05773","title":"Knowing without Acting: The Disentangled Geometry of Safety Mechanisms in Large Language Models","created":"2026-03-06","cited_by_count":2,"area":"alignment"},{"id":"2604.04172","title":"GENFIG1: Visual Summaries of Scholarly Work as a Challenge for Vision-Language Models","created":"2026-04-05","cited_by_count":2,"area":"mllm"},{"id":"2604.19016","title":"AlignCultura: Towards Culturally Aligned Large Language Models?","created":"2026-04-21","cited_by_count":2,"area":"alignment"},{"id":"2607.01250","title":"Structuring the Space of Sociotechnical Alignment","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2502.13349","title":"Event Segmentation Applications in Large Language Model Enabled Automated Recall Assessments","created":"2025-02-19","cited_by_count":1,"area":null},{"id":"2505.17153","title":"Amplify Adjacent Token Differences: Enhancing Long Chain-of-Thought Reasoning with Shift-FFN","created":"2025-05-22","cited_by_count":1,"area":"lr"},{"id":"2511.10707","title":"Bias-Restrained Prefix Representation Finetuning for Mathematical Reasoning","created":"2025-11-13","cited_by_count":1,"area":"lr"},{"id":"2601.06596","title":"Are LLMs Vulnerable to Preference-Undermining Attacks (PUA)? A Factorial Analysis Methodology for Diagnosing the Trade-off between Preference Alignment and Real-World Validity","created":"2026-01-10","cited_by_count":1,"area":"alignment"},{"id":"2602.07381","title":"When the Model Said 'No Comment', We Knew Helpfulness Was Dead, Honesty Was Alive, and Safety Was Terrified","created":"2026-02-07","cited_by_count":1,"area":"moe"},{"id":"2603.14347","title":"Motivation in Large Language Models","created":"2026-03-15","cited_by_count":1,"area":null},{"id":"2603.21461","title":"DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment","created":"2026-03-23","cited_by_count":1,"area":"alignment"},{"id":"2606.03376","title":"P$^2$-DPO: Grounding Hallucination in Perceptual Processing via Calibration Direct Preference Optimization","created":"2026-06-02","cited_by_count":1,"area":"mllm"},{"id":"2609.12373","title":"Toward Robust Personalized Alignment for LLMs: Mitigating Persona Drift in Multi-Turn Dialogue","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2507.21584","title":"TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs","created":"2025-07-29","cited_by_count":0,"area":"mllm"},{"id":"2509.05605","title":"Icon$^{2}$: Aligning Large Language Models Using Self-Synthetic Preference Data via Inherent Regulation","created":"2025-09-06","cited_by_count":0,"area":"alignment"},{"id":"2510.23650","title":"Beyond Hidden-Layer Manipulation: Semantically-Aware Logit Interventions for Debiasing LLMs","created":"2025-10-25","cited_by_count":0,"area":null},{"id":"2601.05107","title":"Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human-Agent Interaction","created":"2026-01-08","cited_by_count":0,"area":"agents"},{"id":"2603.05928","title":"Addressing the Ecological Fallacy in Larger LMs with Human Context","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2603.06727","title":"Safe Transformer: An Explicit Safety Bit For Interpretable And Controllable Alignment","created":"2026-03-06","cited_by_count":0,"area":"alignment"},{"id":"2603.19325","title":"Target Concept Tuning Improves Extreme Weather Forecasting","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.24536","title":"Generating Place-Based Compromises Between Two Points of View","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.06196","title":"The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.25226","title":"From Automation to Collaboration: Human-in-the-Loop Methods for Safe and Trustworthy NLP","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2609.04409","title":"A Systematic Evaluation of Cross-Lingual Consistency Enhancement Methods in Multilingual Language Models","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.33298","title":"Direct Hidden-State Alignment: Mapping and Controlling Preference Expression in LLMs","created":"2026-09-27","cited_by_count":0,"area":"alignment"}],"next_cursor":null}