{"total":58,"rows":[{"id":"2412.13663","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","created":"2024-12-18","cited_by_count":554,"area":null},{"id":"2407.12043","title":"The Art of Saying No: Contextual Noncompliance in Language Models","created":"2024-07-02","cited_by_count":105,"area":null},{"id":"2510.18874","title":"Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting","created":"2025-10-21","cited_by_count":94,"area":null},{"id":"2503.01807","title":"Large-Scale Data Selection for Instruction Tuning","created":"2025-03-03","cited_by_count":35,"area":null},{"id":"2505.10833","title":"MergeBench: A Benchmark for Merging Domain-Specialized LLMs","created":"2025-05-16","cited_by_count":33,"area":null},{"id":"2507.06187","title":"The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains","created":"2025-07-08","cited_by_count":28,"area":null},{"id":"2511.01805","title":"Accumulating Context Changes the Beliefs of Language Models","created":"2025-11-03","cited_by_count":28,"area":null},{"id":"2502.07077","title":"Multi-turn Evaluation of Anthropomorphic Behaviours in Large Language Models","created":"2025-02-10","cited_by_count":25,"area":null},{"id":"2503.06550","title":"BingoGuard: LLM Content Moderation Tools with Risk Levels","created":"2025-03-09","cited_by_count":21,"area":null},{"id":"2505.12025","title":"Spotlight Your Instructions: Instruction-following with Dynamic Attention Steering","created":"2025-05-17","cited_by_count":21,"area":null},{"id":"2505.14633","title":"Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas","created":"2025-05-20","cited_by_count":18,"area":null},{"id":"2508.03121","title":"RegMean++: Enhancing Effectiveness and Generalization of Regression Mean for Model Merging","created":"2025-08-05","cited_by_count":11,"area":null},{"id":"2410.16665","title":"SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior","created":"2024-10-22","cited_by_count":10,"area":null},{"id":"2505.17441","title":"Discovering Forbidden Topics in Language Models","created":"2025-05-23","cited_by_count":9,"area":null},{"id":"2511.17408","title":"The Impact of Off-Policy Training Data on Probe Generalisation","created":"2025-11-21","cited_by_count":9,"area":null},{"id":"2509.21155","title":"Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models","created":"2025-09-25","cited_by_count":6,"area":null},{"id":"2602.03429","title":"DiscoverLLM: From Executing Intents to Discovering Them","created":"2026-02-03","cited_by_count":6,"area":null},{"id":"2601.08951","title":"PluriHarms: Benchmarking the Full Spectrum of Human Judgments on AI Harm","created":"2026-01-13","cited_by_count":5,"area":null},{"id":"2511.07482","title":"Alignment-Constrained Dynamic Pruning for LLMs: Identifying and Preserving Alignment-Critical Circuits","created":"2025-11-09","cited_by_count":4,"area":null},{"id":"2602.05943","title":"Orthogonal Model Merging","created":"2026-02-05","cited_by_count":4,"area":null},{"id":"2605.28591","title":"Models That Know How Evaluations Are Designed Score Safer","created":"2026-05-27","cited_by_count":4,"area":null},{"id":"2606.32038","title":"Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision","created":"2026-06-30","cited_by_count":4,"area":null},{"id":"2607.07916","title":"Persona Cartography: Charting Language Model Personality Traits in Weight Space","created":"2026-07-08","cited_by_count":4,"area":null},{"id":"2502.17541","title":"Dataset Featurization: Uncovering Natural Language Features through Unsupervised Data Reconstruction","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2506.00741","title":"Data Swarms: Optimizable Generation of Synthetic Evaluation Data","created":"2025-05-31","cited_by_count":2,"area":null},{"id":"2512.11986","title":"Learning to Extract Context for Context-Aware LLM Inference","created":"2025-12-12","cited_by_count":2,"area":null},{"id":"2601.01739","title":"K-EXAONE Technical Report","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2606.12360","title":"Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2609.15994","title":"Latent Undertow: How Ordinary Typos Break Probes","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2506.01266","title":"Detoxification of Large Language Models through Output-layer Fusion with a Calibration Model","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2506.19140","title":"Command-V: Pasting LLM Behaviors via Activation Profiles","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2509.05608","title":"BinaryShield: Cross-Service Threat Intelligence in LLM Services using Privacy-Preserving Fingerprints","created":"2025-09-06","cited_by_count":1,"area":null},{"id":"2509.10682","title":"LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems","created":"2025-09-12","cited_by_count":1,"area":null},{"id":"2602.04521","title":"$C$-$\\Delta\\Theta$: Circuit-Restricted Weight Arithmetic for Selective Refusal","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.21267","title":"A Systematic Review of Algorithmic Red Teaming Methodologies for Assurance and Security of AI Applications","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2605.09875","title":"Cross-Family Universality of Behavioral Axes via Anchor-Projected Representations","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2606.00160","title":"DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.03344","title":"RogueMerge: Robust and Unified Attacks against LLM Model Merging","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.16501","title":"Post-Hoc Merging is Not Enough: Many-Shot Model Merging with Loss-Gap Balancing","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2608.13482","title":"Synthetic Persona Pretraining: Alignment from Token Zero","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2609.00092","title":"Safin-1: Safety from Within through Memory-Native State Evolution","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2510.16005","title":"Breaking Guardrails, Facing Walls: Insights on Adversarial AI for Defenders & Researchers","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2602.11717","title":"Beyond Parameter Arithmetic: Sparse Complementary Fusion for Distribution-Aware Model Merging","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.07286","title":"Taiwan Safety Benchmark and Breeze Guard: Toward Trustworthy AI for Taiwanese Mandarin","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2603.13318","title":"Residual Stream Analysis of Overfitting And Structural Disruptions","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2604.17614","title":"Characterizing Model-Native Skills","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2605.05630","title":"One Turn Too Late: Learning When to Intervene Against Multi-Turn Malicious Intent","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.06632","title":"Crafting Reversible SFT Behaviors in Large Language Models","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.12843","title":"ReForge: Refining Merged Models with Anchor-Regularized Regression","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.20241","title":"Geometry-Lite: Interpretable Safety Probing via Layer-Wise Margin Geometry","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2607.01104","title":"CausalMix: Data Mixture as Causal Inference for Language Model Training","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.02510","title":"Online Safety Monitoring for LLMs","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.20791","title":"Refusal-Gated Decoding: Preserving Refusal Behavior Under High-Temperature Sampling","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2608.21570","title":"A Reproducible, License-Aware Distillation Recipe for CPUDeployable Safety Classification","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.02771","title":"From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.22153","title":"SafeTune: A Unified Faithful Library for Auditing and Repairing Safety Drift in Fine-Tuned LLMs","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.33638","title":"Quantifying Behavioral Tails in Black-Box Language Models","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.38379","title":"Aligned Data Can Induce Misalignment via Context Confusion","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}