{"total":28,"rows":[{"id":"2508.20033","title":"DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis","created":"2025-08-27","cited_by_count":34,"area":null},{"id":"2409.16022","title":"AI Can Be Cognitively Biased: An Exploratory Study on Threshold Priming in LLM-Based Batch Relevance Assessment","created":"2024-09-24","cited_by_count":20,"area":null},{"id":"2411.08275","title":"A Large-Scale Study of Relevance Assessments with Large Language Models: An Initial Look","created":"2024-11-13","cited_by_count":18,"area":null},{"id":"2503.19092","title":"Rankers, Judges, and Assistants: Towards Understanding the Interplay of LLMs in Information Retrieval Evaluation","created":"2025-03-24","cited_by_count":15,"area":null},{"id":"2504.12408","title":"A Human-AI Comparative Analysis of Prompt Sensitivity in LLM-Based Relevance Judgment","created":"2025-04-16","cited_by_count":15,"area":null},{"id":"2504.13128","title":"FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents","created":"2025-04-17","cited_by_count":15,"area":null},{"id":"2504.12558","title":"Benchmarking LLM-based Relevance Judgment Methods","created":"2025-04-17","cited_by_count":14,"area":null},{"id":"2604.17906","title":"Bayesian Active Learning with Gaussian Processes Guided by LLM Relevance Scoring for Dense Passage Retrieval","created":"2026-04-20","cited_by_count":6,"area":null},{"id":"2509.03764","title":"LLM-based Relevance Assessment for Web-Scale Search Evaluation at Pinterest","created":"2025-09-03","cited_by_count":4,"area":null},{"id":"2506.07296","title":"HotelMatch-LLM: Joint Multi-Task Training of Small and Large Language Models for Efficient Multimodal Hotel Retrieval","created":"2025-06-08","cited_by_count":2,"area":null},{"id":"2512.00390","title":"Mitigating the Threshold Priming Effect in Large Language Model-Based Relevance Judgments via Personality Infusing","created":"2025-11-29","cited_by_count":2,"area":null},{"id":"2503.22973","title":"XL-Suite: Cross-Lingual Synthetic Training and Evaluation Data for Open-Ended Generation","created":"2025-03-29","cited_by_count":1,"area":null},{"id":"2505.07345","title":"QUPID: Quantified Understanding for Enhanced Performance, Insights, and Decisions in Korean Search Engines","created":"2025-05-12","cited_by_count":1,"area":null},{"id":"2601.01751","title":"Query-Document Dense Vectors for LLM Relevance Judgment Bias Analysis","created":"2026-01-05","cited_by_count":1,"area":null},{"id":"2601.01862","title":"Judging with Personality and Confidence: A Study on Personality-Conditioned LLM Relevance Assessment","created":"2026-01-05","cited_by_count":1,"area":null},{"id":"2606.13905","title":"ADORE: Iterative Query Expansion with Retrieval-Grounded Relevance Feedback","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2608.10385","title":"Persona Conditioning as an Assessor-Sensitivity Probe for LLM-Based IR Evaluation","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2609.29803","title":"SEEK: Skill-Routed Evaluation with Evolvable Knowledge for Industrial Search","created":"2026-09-24","cited_by_count":1,"area":null},{"id":"2510.00324","title":"Which Programming Language and Model Work Best With LLM-as-a-Judge For Code Retrieval?","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2512.05334","title":"The Effect of Document Summarization on LLM-Based Relevance Judgments","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2601.04455","title":"Re-Rankers as Relevance Judges","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2602.11941","title":"IncompeBench: A Permissively Licensed, Fine-Grained Benchmark for Music Information Retrieval","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.11008","title":"A Systematic Study of Pseudo-Relevance Feedback with LLMs","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2603.20513","title":"ReBOL: Retrieval via Bayesian Optimization with Batched LLM Relevance Observations and Query Reformulation","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2604.18122","title":"Decisive: Guiding User Decisions with Optimal Preference Elicitation from Unstructured Documents","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.01591","title":"Led to Mislead: Adversarial Content Injection for Attacks on Neural Ranking Models","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2608.28965","title":"From Location Phrases to Geographic Entities: Task-Adapted Retrieval for People Search","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2610.17841","title":"FASHION-RQ: Mining Hierarchical Semantic Structure for Automated Evaluation of Fashion Retrieval","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}