{"total":16,"rows":[{"id":"2506.05334","title":"Search Arena: Analyzing Search-Augmented LLMs","created":"2025-06-05","cited_by_count":34,"area":null},{"id":"2503.15620","title":"Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings","created":"2025-03-19","cited_by_count":24,"area":null},{"id":"2506.01829","title":"CiteEval: Principle-Driven Citation Evaluation for Source Attribution","created":"2025-06-02","cited_by_count":19,"area":null},{"id":"2506.07671","title":"GaRAGe: A Benchmark with Grounding Annotations for RAG Evaluation","created":"2025-06-09","cited_by_count":18,"area":null},{"id":"2508.17670","title":"CoCoA: Confidence and Context-Aware Adaptive Decoding for Resolving Knowledge Conflicts in Large Language Models","created":"2025-08-25","cited_by_count":10,"area":null},{"id":"2508.00709","title":"NyayaRAG: Realistic Legal Judgment Prediction with RAG under the Indian Common Law System","created":"2025-08-01","cited_by_count":6,"area":null},{"id":"2502.11962","title":"Balancing Truthfulness and Informativeness with Uncertainty-Aware Instruction Fine-Tuning","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2503.16575","title":"Extract, Match, and Score: An Evaluation Paradigm for Long Question-context-answer Triplets in Financial Analysis","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2506.09147","title":"LLM-as-a-qualitative-judge: automating error analysis in natural language generation","created":"2025-06-10","cited_by_count":3,"area":null},{"id":"2511.12142","title":"MAVIS: A Benchmark for Multimodal Source Attribution in Long-form Visual Question Answering","created":"2025-11-15","cited_by_count":3,"area":null},{"id":"2502.20315","title":"LangProBe: a Language Programs Benchmark","created":"2025-02-27","cited_by_count":2,"area":null},{"id":"2601.03669","title":"eTracer: Polarity-Aware Evidence Grounding","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2605.10168","title":"ASTRA-QA: A Benchmark for Abstract Question Answering over Documents","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2607.18825","title":"AILQA: Evaluating AI-Driven Legal Question Answering Systems for the Indian Legal System","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2607.22679","title":"DOSA: A Tree-Guided, Self-Regressive Framework for Long Document Structure Analysis","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2609.22248","title":"Checkpoints Are Not Enough: Trust Calibration in CoSLR, a Human-AI System for Systematic Literature Reviews","created":"2026-09-05","cited_by_count":0,"area":null}],"next_cursor":null}