{"total":27,"rows":[{"id":"2509.14260","title":"Incomplete Tasks Induce Shutdown Resistance in Some Frontier LLMs","created":"2025-09-13","cited_by_count":22,"area":null},{"id":"2511.14342","title":"ConInstruct: Evaluating Large Language Models on Conflict Detection and Resolution in Instructions","created":"2025-11-18","cited_by_count":10,"area":null},{"id":"2603.04738","title":"IF-RewardBench: Benchmarking Judge Models for Instruction-Following Evaluation","created":"2026-03-05","cited_by_count":10,"area":null},{"id":"2603.12230","title":"Security Considerations for Artificial Intelligence Agents","created":"2026-03-12","cited_by_count":8,"area":null},{"id":"2604.25109","title":"Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills","created":"2026-04-28","cited_by_count":7,"area":null},{"id":"2603.23530","title":"Did You Forget What I Asked? Prospective Memory Failures in Large Language Models","created":"2026-03-07","cited_by_count":6,"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":"2508.15815","title":"User-Assistant Bias in LLMs","created":"2025-08-16","cited_by_count":3,"area":null},{"id":"2601.18554","title":"Deconstructing Instruction-Following: A New Benchmark for Granular Evaluation of Large Language Model Instruction Compliance Abilities","created":"2026-01-26","cited_by_count":2,"area":null},{"id":"2607.26228","title":"Steering Instruction Hierarchies at Inference Time","created":"2026-07-28","cited_by_count":2,"area":null},{"id":"2603.07886","title":"CCR-Bench: A Comprehensive Benchmark for Evaluating LLMs on Complex Constraints, Control Flows, and Real-World Cases","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2604.09075","title":"Hierarchical Alignment: Enforcing Hierarchical Instruction-Following in LLMs through Logical Consistency","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2604.19984","title":"Bias in the Tails: How Name-conditioned Evaluative Framing in Resume Summaries Destabilizes LLM-based Hiring","created":"2026-04-21","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":"2511.00166","title":"Study on Supply Chain Finance Decision-Making Model and Enterprise Economic Performance Prediction Based on Deep Reinforcement Learning","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2511.16209","title":"PSM: Prompt Sensitivity Minimization via LLM-Guided Black-Box Optimization","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2601.12983","title":"ChartAttack: Testing the Vulnerability of LLMs to Malicious Prompting in Chart Generation","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2603.13351","title":"Prompt Complexity Dilutes Structured Reasoning: A Follow-Up Study on the Car Wash Problem","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2605.30521","title":"Evaluating using Mock Tool Calls to Quarantine Untrusted Prompt Inputs","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.29960","title":"IHDec: Divergence-Steered Contrastive Decoding for Securing Multi-Turn Instruction Hierarchies","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.23545","title":"Language Shapes Instruction Hierarchy Compliance in Multilingual LLMs","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2607.29196","title":"Hy-MultiTurn: A Six-Dimensional Benchmark for Deep Multi-Turn Dialogue Understanding","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.28648","title":"How Language Models Choose Sides: Internal Representations of Instruction Hierarchy","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2609.08646","title":"Combating Instruction Conflict via Energy-Driven Latent Conflict Detection","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.13725","title":"IBBench-Light: A Paired Evaluation of Task-Conditioned Responses to External Directives","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.29333","title":"Where LLM Graders Succeed and Break: Evidence from Two Computer-Science Exams","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.04210","title":"Can LLMs Separate Pasted Artifacts from User Speech? Absorption at Unmarked Prompt Seams","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}