{"total":76,"rows":[{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2309.07045","title":"SafetyBench: Evaluating the Safety of Large Language Models","created":"2023-09-13","cited_by_count":199,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2310.15851","title":"Self-Guard: Empower the LLM to Safeguard Itself","created":"2023-10-24","cited_by_count":54,"area":"safety"},{"id":"2402.16444","title":"ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors","created":"2024-02-26","cited_by_count":51,"area":null},{"id":"2305.04446","title":"Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks","created":"2023-05-08","cited_by_count":46,"area":null},{"id":"2308.16705","title":"Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis","created":"2023-08-31","cited_by_count":45,"area":null},{"id":"2311.06899","title":"Flames: Benchmarking Value Alignment of LLMs in Chinese","created":"2023-11-12","cited_by_count":37,"area":"alignment"},{"id":"2202.08011","title":"Towards Identifying Social Bias in Dialog Systems: Frame, Datasets, and Benchmarks","created":"2022-02-16","cited_by_count":36,"area":null},{"id":"2308.15399","title":"Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?","created":"2023-08-29","cited_by_count":36,"area":"lr"},{"id":"2203.09313","title":"EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training","created":"2022-03-17","cited_by_count":31,"area":null},{"id":"2310.03400","title":"Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning","created":"2023-10-05","cited_by_count":29,"area":null},{"id":"2408.03468","title":"MultiHateClip: A Multilingual Benchmark Dataset for Hateful Video Detection on YouTube and Bilibili","created":"2024-07-28","cited_by_count":25,"area":null},{"id":"2305.17701","title":"KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Application","created":"2023-05-28","cited_by_count":24,"area":null},{"id":"2308.15192","title":"Enhancing Psychological Counseling with Large Language Model: A Multifaceted Decision-Support System for Non-Professionals","created":"2023-08-29","cited_by_count":24,"area":null},{"id":"2306.16244","title":"CBBQ: A Chinese Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models","created":"2023-06-28","cited_by_count":23,"area":null},{"id":"2502.11090","title":"SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks","created":"2025-02-16","cited_by_count":23,"area":"safety"},{"id":"2303.17927","title":"Cross-Cultural Transfer Learning for Chinese Offensive Language Detection","created":"2023-03-31","cited_by_count":21,"area":null},{"id":"2310.06458","title":"Cultural Compass: Predicting Transfer Learning Success in Offensive Language Detection with Cultural Features","created":"2023-10-10","cited_by_count":18,"area":null},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2304.07849","title":"ChatPLUG: Open-Domain Generative Dialogue System with Internet-Augmented Instruction Tuning for Digital Human","created":"2023-04-16","cited_by_count":14,"area":null},{"id":"2308.04813","title":"CLEVA: Chinese Language Models EVAluation Platform","created":"2023-08-09","cited_by_count":13,"area":null},{"id":"2405.06996","title":"Quite Good, but Not Enough: Nationality Bias in Large Language Models -- A Case Study of ChatGPT","created":"2024-05-11","cited_by_count":13,"area":null},{"id":"2405.01842","title":"SGHateCheck: Functional Tests for Detecting Hate Speech in Low-Resource Languages of Singapore","created":"2024-05-03","cited_by_count":10,"area":null},{"id":"2505.24341","title":"Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings","created":"2025-05-30","cited_by_count":10,"area":null},{"id":"2507.07640","title":"Lost in Pronunciation: Detecting Chinese Offensive Language Disguised by Phonetic Cloaking Replacement","created":"2025-07-10","cited_by_count":10,"area":null},{"id":"2203.17090","title":"PanGu-Bot: Efficient Generative Dialogue Pre-training from Pre-trained Language Model","created":"2022-03-31","cited_by_count":9,"area":null},{"id":"2402.17982","title":"Collaborative decoding of critical tokens for boosting factuality of large language models","created":"2024-02-28","cited_by_count":9,"area":null},{"id":"2403.12316","title":"OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety","created":"2024-03-18","cited_by_count":9,"area":null},{"id":"2501.15451","title":"STATE ToxiCN: A Benchmark for Span-level Target-Aware Toxicity Extraction in Chinese Hate Speech Detection","created":"2025-01-26","cited_by_count":9,"area":null},{"id":"2212.01810","title":"Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation","created":"2022-12-04","cited_by_count":8,"area":null},{"id":"2305.17280","title":"Improved Instruction Ordering in Recipe-Grounded Conversation","created":"2023-05-26","cited_by_count":7,"area":null},{"id":"2411.01844","title":"DeMod: A Holistic Tool with Explainable Detection and Personalized Modification for Toxicity Censorship","created":"2024-11-04","cited_by_count":7,"area":null},{"id":"2501.15042","title":"SCCD: A Session-based Dataset for Chinese Cyberbullying Detection","created":"2025-01-25","cited_by_count":7,"area":null},{"id":"2406.14023","title":"Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective","created":"2024-06-20","cited_by_count":6,"area":null},{"id":"2407.01850","title":"Purple-teaming LLMs with Adversarial Defender Training","created":"2024-07-01","cited_by_count":6,"area":"safety"},{"id":"2403.18314","title":"Chinese Offensive Language Detection:Current Status and Future Directions","created":"2024-03-27","cited_by_count":5,"area":null},{"id":"2409.12739","title":"Edu-Values: Towards Evaluating the Chinese Education Values of Large Language Models","created":"2024-09-19","cited_by_count":5,"area":null},{"id":"2503.07237","title":"LLM-C3MOD: A Human-LLM Collaborative System for Cross-Cultural Hate Speech Moderation","created":"2025-03-10","cited_by_count":5,"area":null},{"id":"2505.15773","title":"ToxicTone: A Mandarin Audio Dataset Annotated for Toxicity and Toxic Utterance Tonality","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2506.06347","title":"Unified Game Moderation: Soft-Prompting and LLM-Assisted Label Transfer for Resource-Efficient Toxicity Detection","created":"2025-06-01","cited_by_count":5,"area":null},{"id":"2310.14557","title":"The Skipped Beat: A Study of Sociopragmatic Understanding in LLMs for 64 Languages","created":"2023-10-23","cited_by_count":3,"area":null},{"id":"2411.19668","title":"ChineseWebText 2.0: Large-Scale High-quality Chinese Web Text with Multi-dimensional and fine-grained information","created":"2024-11-29","cited_by_count":3,"area":null},{"id":"2504.19333","title":"Unified Multi-Task Learning & Model Fusion for Efficient Language Model Guardrailing","created":"2025-04-27","cited_by_count":3,"area":"safety"},{"id":"2604.18487","title":"Adversarial Humanities Benchmark: Results on Stylistic Robustness in Frontier Model Safety","created":"2026-04-20","cited_by_count":3,"area":"safety"},{"id":"2401.09244","title":"Cross-lingual Offensive Language Detection: A Systematic Review of Datasets, Transfer Approaches and Challenges","created":"2024-01-17","cited_by_count":2,"area":null},{"id":"2403.04770","title":"Social Orientation: A New Feature for Dialogue Analysis","created":"2024-02-26","cited_by_count":2,"area":null},{"id":"2501.00697","title":"PANDA -- Paired Anti-hate Narratives Dataset from Asia: Using an LLM-as-a-Judge to Create the First Chinese Counterspeech Dataset","created":"2025-01-01","cited_by_count":2,"area":null},{"id":"2505.15297","title":"Chinese Toxic Language Mitigation via Sentiment Polarity Consistent Rewrites","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2506.03458","title":"Culture Matters in Toxic Language Detection in Persian","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2506.04975","title":"Evaluating Chinese Large Language Models: The Influence of Persona Assignment on Stereotypes and Safeguards","created":"2025-06-05","cited_by_count":2,"area":"safety"},{"id":"2507.11292","title":"Fine-Grained Chinese Hate Speech Understanding: Span-Level Resources, Coded Term Lexicon, and Enhanced Detection Frameworks","created":"2025-07-15","cited_by_count":2,"area":null},{"id":"2508.00760","title":"MMBERT: Scaled Mixture-of-Experts Multimodal BERT for Robust Chinese Hate Speech Detection under Cloaking Perturbations","created":"2025-08-01","cited_by_count":2,"area":"moe"},{"id":"2508.20201","title":"Social Bias in Multilingual Language Models: A Survey","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2410.00361","title":"PclGPT: A Large Language Model for Patronizing and Condescending Language Detection","created":"2024-10-01","cited_by_count":1,"area":null},{"id":"2505.20654","title":"Chinese Cyberbullying Detection: Dataset, Method, and Validation","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2505.22184","title":"Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2306.17020","title":"Classifying Crime Types using Judgment Documents from Social Media","created":"2023-06-29","cited_by_count":0,"area":null},{"id":"2506.00583","title":"The Hidden Language of Harm: Examining the Role of Emojis in Harmful Online Communication and Content Moderation","created":"2025-05-31","cited_by_count":0,"area":null},{"id":"2508.04638","title":"Can NLP Tackle Hate Speech in the Real World? Stakeholder-Informed Feedback and Survey on Counterspeech","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2509.14712","title":"From Ground Trust to Truth: Disparities in Offensive Language Judgments on Contemporary Korean Political Discourse","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2510.16686","title":"Investigating the Impact of Rationales for LLMs on Natural Language Understanding","created":"2025-10-19","cited_by_count":0,"area":"lr"},{"id":"2512.09563","title":"System Report for CCL25-Eval Task 10: Prompt-Driven Large Language Model Merge for Fine-Grained Chinese Hate Speech Detection","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2602.15866","title":"NLP Privacy Risk Identification in Social Media (NLP-PRISM): A Survey","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2604.10504","title":"CARO: Chain-of-Analogy Reasoning Optimization for Robust Content Moderation","created":"2026-04-12","cited_by_count":0,"area":"lr"},{"id":"2604.12321","title":"ToxiTrace: Gradient-Aligned Training for Explainable Chinese Toxicity Detection","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.22258","title":"Harder to Defend: Towards Chinese Toxicity Attacks via Implicit Enhancement and Obfuscation Rewriting","created":"2026-05-21","cited_by_count":0,"area":"safety"},{"id":"2606.09114","title":"MAAM: Anchor-Preserving Compression and Contextual Calibration for Chinese Discriminatory Language Detection","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.27629","title":"Cross-Platform Chinese Offensive Comment Detection via Dual-Threshold Hard Example Mining","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.12612","title":"Translation as a Computationally Efficient Bridge: Feasibility of English BERT for Low-Resource Languages","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.16790","title":"Cascading versus Joint Modeling for Hierarchical Offensive Language Detection","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2607.23512","title":"The Cross-Domain Generalization Cost of Offensive Language Detection","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2608.12361","title":"New Terms, New Toxicity: Consensus-based Chinese Neologism Toxicity Detection via Search-Augmented LLMs","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2608.27844","title":"EvoHarmBench: Breaking Content Moderation with Iterative Human-Like Evasion","created":"2026-08-28","cited_by_count":0,"area":"safety"},{"id":"2609.05843","title":"SinoGlyphBench: A Diagnostic Benchmark for Chinese Glyph-Level Obfuscation in Language-Model Moderation","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2610.14464","title":"Evaluating Bias in Chinese Large Language Models across Tasks and Registers: Task Operationalization Effects and Irony Classification Risks","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}