{"total":17,"rows":[{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465,"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":"2505.24040","title":"MedPAIR: Measuring Physicians and AI Relevance Alignment in Medical Question Answering","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2505.04209","title":"To Judge or not to Judge: Using LLM Judgements for Advertiser Keyphrase Relevance at eBay","created":"2025-05-07","cited_by_count":4,"area":null},{"id":"2508.03628","title":"LLMDistill4Ads: Using Cross-Encoders to Distill from LLM Signals for Advertiser Keyphrase Recommendations at eBay","created":"2025-08-05","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":"2601.04646","title":"Succeeding at Scale: Enterprise Retrieval Benchmark Construction and Index-Preserving Query Adaptation for Multi-Tenant Search","created":"2026-01-08","cited_by_count":2,"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":"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":"2507.02139","title":"When LLMs Disagree: Diagnosing Relevance Filtering Bias and Retrieval Divergence in SDG Search","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2507.04942","title":"SIGIR 2025 -- LiveRAG Challenge Report","created":"2025-07-07","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":"2605.26400","title":"Plans for Evaluating Structured Generative Search Summaries","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2607.24793","title":"Retrieval, not hallucinations, will be the limiting factor for LLM-based clinical AI tools","created":"2026-06-29","cited_by_count":0,"area":null}],"next_cursor":null}