{"total":21,"rows":[{"id":"2405.04760","title":"Large Language Models for Cyber Security: A Systematic Literature Review","created":"2024-05-08","cited_by_count":68,"area":null},{"id":"2503.11656","title":"TRUTH DECAY: Quantifying Multi-Turn Sycophancy in Language Models","created":"2025-02-04","cited_by_count":33,"area":null},{"id":"2510.09869","title":"NarraBench: A Comprehensive Framework for Narrative Benchmarking","created":"2025-10-10","cited_by_count":13,"area":null},{"id":"2402.19366","title":"Exploring the Potential of Large Language Models for Improving Digital Forensic Investigation Efficiency","created":"2024-02-29","cited_by_count":7,"area":null},{"id":"2412.15557","title":"MORTAR: Multi-turn Metamorphic Testing for LLM-based Dialogue Systems","created":"2024-12-20","cited_by_count":7,"area":null},{"id":"2604.09563","title":"Seven simple steps for log analysis in AI systems","created":"2026-02-13","cited_by_count":6,"area":null},{"id":"2402.10618","title":"Enhancing Role-playing Systems through Aggressive Queries: Evaluation and Improvement","created":"2024-02-16","cited_by_count":5,"area":null},{"id":"2504.13928","title":"LLM-Driven NPCs: Cross-Platform Dialogue System for Games and Social Platforms","created":"2025-04-14","cited_by_count":5,"area":null},{"id":"2508.20385","title":"CAPE: Context-Aware Personality Evaluation Framework for Large Language Models","created":"2025-08-28","cited_by_count":4,"area":null},{"id":"2604.04901","title":"FileGram: Grounding Agent Personalization in File-System Behavioral Traces","created":"2026-04-06","cited_by_count":3,"area":null},{"id":"2411.13779","title":"NewsInterview: a Dataset and a Playground to Evaluate LLMs' Ground Gap via Informational Interviews","created":"2024-11-21","cited_by_count":2,"area":null},{"id":"2508.06196","title":"EiCAP: Beyond Fluency, Probing and Improving Emotional Intelligence in LLMs via Psychologically Grounded Multi-Turn Dialogue","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2511.04133","title":"Testing the Testers: Human-Driven Quality Assessment of Voice AI Testing Platforms","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2410.03996","title":"On the Influence of Gender and Race in Romantic Relationship Prediction from Large Language Models","created":"2024-10-05","cited_by_count":0,"area":null},{"id":"2410.14145","title":"CAPE: A Chinese Dataset for Appraisal-based Emotional Generation using Large Language Models","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2507.13629","title":"Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniques","created":"2025-07-18","cited_by_count":0,"area":null},{"id":"2601.12208","title":"CoReflect: A Reflective Co-Evolution Framework for Improving Conversational Evaluation","created":"2026-01-18","cited_by_count":0,"area":null},{"id":"2602.11924","title":"Who Does What? Archetypes of Roles Assigned to LLMs During Human-AI Decision-Making","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2604.22306","title":"BLAST: Benchmarking LLMs with ASP-based Structured Testing","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2606.12332","title":"Measuring Semantic Progress in Multi-turn Dialogue via Information Gain","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2608.08868","title":"Conversation as Measurement in Clinical Encounters: Observable Phase Structure, Partially Observable Patient State","created":"2026-08-09","cited_by_count":0,"area":null}],"next_cursor":null}