{"total":21,"rows":[{"id":"2509.26072","title":"The Silent Judge: Unacknowledged Shortcut Bias in LLM-as-a-Judge","created":"2025-09-30","cited_by_count":15,"area":null},{"id":"2603.09970","title":"CREATE: Testing LLMs for Associative Creativity","created":"2026-03-10","cited_by_count":7,"area":null},{"id":"2603.11027","title":"Beyond the Illusion of Consensus: From Surface Heuristics to Knowledge-Grounded Evaluation in LLM-as-a-Judge","created":"2026-03-11","cited_by_count":4,"area":null},{"id":"2602.07996","title":"The Judge Who Never Admits: Hidden Shortcuts in LLM-based Evaluation","created":"2026-02-08","cited_by_count":3,"area":null},{"id":"2512.19012","title":"DramaBench: A Six-Dimensional Evaluation Framework for Drama Script Continuation","created":"2025-12-22","cited_by_count":2,"area":null},{"id":"2603.23129","title":"Polaris: A G\\\"odel Agent Framework for Small Language Models through Experience-Abstracted Policy Repair","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2608.19437","title":"Are LLMs becoming similarly creative? Evidence from three years of models","created":"2026-08-19","cited_by_count":2,"area":null},{"id":"2608.19893","title":"Interrupting the Loop: Periodic Subject Changes Raise Judged Surprise and Connection in Base Language Models","created":"2026-08-20","cited_by_count":2,"area":null},{"id":"2512.12209","title":"CineLOG: A Training Free Approach for Cinematic Long Video Generation","created":"2025-12-13","cited_by_count":1,"area":null},{"id":"2606.01736","title":"Argument Collapse: LLMs Flatten Long-Form Public Debate","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2608.18091","title":"Self- and Other-Labels Induce Bidirectional Bias in LLM Judges","created":"2026-06-06","cited_by_count":1,"area":null},{"id":"2606.04095","title":"POLARIS: Guiding Small Models to Write Long Stories","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.12790","title":"GENIE: A Fine-Grained Measure for Novelty","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2608.06967","title":"Can Language Models Imagine Without Seeing? Ekphrasis: Measuring Visual Creative Ideation in Text-Only LLMs","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.13947","title":"Scaling Creative Writing Beyond Story-Centric Data with Attribute-Guided Genre Expansion","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.30754","title":"CLIN: an Objective Framework for Evaluating Creativity in Short Persian Literary Text","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.33738","title":"The Effects of Incremental Instruction Delivery on Language-Model Creative Writing","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33905","title":"SlopBench: How Well Can We Rank Language Models by Slop? A Multi-Domain Benchmark of Repetitive AI Writing","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35759","title":"Scaling Long-Form Story Generation via Narrative State Tracking","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.17731","title":"Understanding Machine Taste: Aesthetic Agreement Across Foundation Models in K-pop","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.20272","title":"CSWBench: Evaluating Context-Sensitive Code-Switching in Creative Writing","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}