{"total":50,"rows":[{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465,"area":null},{"id":"2601.20913","title":"Noisy but Valid: Robust Statistical Evaluation of LLMs with Imperfect Judges","created":"2026-01-28","cited_by_count":24,"area":null},{"id":"2502.10441","title":"AI Alignment at Your Discretion","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2501.10945","title":"Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond","created":"2025-01-19","cited_by_count":18,"area":null},{"id":"2602.13110","title":"SCOPE: Selective Conformal Optimized Pairwise LLM Judging","created":"2026-02-13","cited_by_count":14,"area":null},{"id":"2603.00039","title":"CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation","created":"2026-02-09","cited_by_count":13,"area":null},{"id":"2412.06134","title":"Evaluating and Mitigating Social Bias for Large Language Models in Open-ended Settings","created":"2024-12-09","cited_by_count":10,"area":null},{"id":"2409.02718","title":"\"Yes, My LoRD.\" Guiding Language Model Extraction with Locality Reinforced Distillation","created":"2024-09-04","cited_by_count":5,"area":null},{"id":"2511.18852","title":"FanarGuard: A Culturally-Aware Moderation Filter for Arabic Language Models","created":"2025-11-24","cited_by_count":5,"area":null},{"id":"2604.02045","title":"BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs","created":"2026-04-02","cited_by_count":5,"area":null},{"id":"2512.23573","title":"ProGuard: Towards Proactive Multimodal Safeguard","created":"2025-12-29","cited_by_count":4,"area":null},{"id":"2603.15423","title":"Invisible failures in human-AI interactions","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2604.04204","title":"How Does \"English (US)\" Become the Default? Triangulating Structural Bias Towards American English Across the LLM Pipeline","created":"2026-04-05","cited_by_count":3,"area":null},{"id":"2604.14932","title":"WavAlign: Enhancing Intelligence and Expressiveness in Spoken Dialogue Models via Adaptive Hybrid Post-Training","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2507.11544","title":"The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2510.08120","title":"Interpreting LLM-as-a-Judge Policies via Verifiable Global Explanations","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2512.03620","title":"SELF: A Robust Singular Value and Eigenvalue Approach for LLM Fingerprinting","created":"2025-12-03","cited_by_count":2,"area":null},{"id":"2602.01618","title":"SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asia","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2602.11318","title":"The Consensus Trap: Dissecting Subjectivity and the \"Ground Truth\" Illusion in Data Annotation","created":"2026-02-11","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":"2607.02047","title":"OpenSafeIntent: Evaluating Intent-Calibrated Safe Completion Across Dual-Use Prompt Sets","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2410.18114","title":"Bridging Today and the Future of Humanity: AI Safety in 2024 and Beyond","created":"2024-10-09","cited_by_count":1,"area":null},{"id":"2605.27117","title":"Position: AI Safety Requires Effective Controllability","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2606.09068","title":"Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.29243","title":"KrishokChat: A Provenance-Traceable Multi-Task Bengali Agricultural Benchmark with Safety-Critical Chemical Advisory","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2608.09490","title":"When Do Task Vectors Interfere? Mapping the Validity Boundaries of Weight-Space Composition","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2608.11797","title":"Reading the Gate, Not the Interference: Output-Side Interference Measurement Does Not Track Merge Collapse","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2609.22512","title":"Agreement Overstates Evidence: Error Dependence in LLM Judge Consensus","created":"2026-09-18","cited_by_count":1,"area":null},{"id":"2412.10257","title":"Targeted Angular Reversal of Weights (TARS) for Knowledge Removal in Large Language Models","created":"2024-12-13","cited_by_count":0,"area":null},{"id":"2507.11502","title":"HKGAI-V1: Towards Regional Sovereign Large Language Model for Hong Kong","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2511.20736","title":"Large Language Models' Complicit Responses to Illicit Instructions across Socio-Legal Contexts","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2604.03257","title":"Robust LLM Performance Certification via Constrained Maximum Likelihood Estimation","created":"2026-03-11","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":"2605.07925","title":"How Value Induction Reshapes LLM Behaviour","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.14746","title":"Selective Safety Steering via Value-Filtered Decoding","created":"2026-05-14","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":"2606.07631","title":"Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2607.03973","title":"MANCE: Manifold Aware Concept Erasure","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2607.25063","title":"Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.02940","title":"When Compression Scores Cannot Decide: Information Boundaries for Group-Robust LLM Pruning","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2609.01210","title":"Who Judges the Judges? A Chinese Safety QA Benchmark for Evaluating LLM Responses and Safety Judges","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.02089","title":"IDEEA: training-free Input-Dependent stEEring via Activation cluster matching","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.34240","title":"Coherence-Aware Distributional Evaluation of Open-Ended Text Generation","created":"2026-09-28","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},{"id":"2609.39788","title":"Safety of Latent Communication in Multi-Agent Systems","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01801","title":"A Safe Prototype Is Not a Safety Direction: Reference Dependence and Prompt Confounds in Response-Safety Embeddings","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.15322","title":"SuperAI: Merging Capabilities Across Heterogeneous Foundation Models","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.18108","title":"A CaLLM Judge is a Better Judge: Mitigating Bias in LLM-as-a-judge","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.18541","title":"Empathy Is Not the Scapegoat for Declines in Factuality and Reliability","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19968","title":"Safe-FCL: Continual Risk Awareness and Fine-Grained Safety Aggregation for Federated Continual Learning of LLMs","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}