{"total":19,"rows":[{"id":"2603.04370","title":"$\\tau$-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge","created":"2026-03-04","cited_by_count":39,"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":"2504.12397","title":"Activated LoRA: Fine-tuned LLMs for Intrinsics","created":"2025-04-16","cited_by_count":12,"area":null},{"id":"2504.01509","title":"PROPHET: An Inferable Future Forecasting Benchmark with Causal Intervened Likelihood Estimation","created":"2025-04-02","cited_by_count":8,"area":null},{"id":"2506.10635","title":"Conversational Search: From Fundamentals to Frontiers in the LLM Era","created":"2025-06-12","cited_by_count":8,"area":null},{"id":"2508.21085","title":"Granite Embedding R2 Models","created":"2025-08-26","cited_by_count":8,"area":null},{"id":"2505.18148","title":"Hidden in the Haystack: Smaller Needles are More Difficult for LLMs to Find","created":"2025-05-23","cited_by_count":7,"area":null},{"id":"2510.11997","title":"SAGE: A Top-Down Bottom-Up Knowledge-Grounded User Simulator for Multi-turn AGent Evaluation","created":"2025-10-13","cited_by_count":6,"area":null},{"id":"2605.04523","title":"RaguTeam at SemEval-2026 Task 8: Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation","created":"2026-05-06","cited_by_count":3,"area":null},{"id":"2605.14175","title":"Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2511.15557","title":"B+ANN: A Fast Billion-Scale Disk-based Nearest-Neighbor Index","created":"2025-11-19","cited_by_count":2,"area":null},{"id":"2601.06426","title":"NC-Bench: An LLM Benchmark for Evaluating Conversational Competence","created":"2026-01-10","cited_by_count":1,"area":null},{"id":"2608.17605","title":"Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2505.09436","title":"CXMArena: Unified Dataset to benchmark performance in realistic CXM Scenarios","created":"2025-05-14","cited_by_count":0,"area":null},{"id":"2605.00964","title":"Seeking Information with RAG-Assistants: Does Model Size Matter in Human-AI Collaborations?","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.12028","title":"Caraman at SemEval-2026 Task 8: Three-Stage Multi-Turn Retrieval with Query Rewriting, Hybrid Search, and Cross-Encoder Reranking","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2608.11584","title":"EnterpriseRAG: Benchmarking LLM Instruction Adherence and Robustness under Non-Ideal Enterprise Retrieval","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2609.17081","title":"EviScope: Paired Counterfactual Evidence Diagnostics for Faithful and Efficient Grounded Language Models","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.36515","title":"Large-scale factor analysis shows machine intelligence is only partially interpretable","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}