{"list":"other","total":51,"rows":[{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2305.14251","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","created":"2023-05-23","cited_by_count":1282},{"id":"2506.05176","title":"Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models","created":"2025-06-05","cited_by_count":1261},{"id":"2402.17753","title":"Evaluating Very Long-Term Conversational Memory of LLM Agents","created":"2024-02-27","cited_by_count":830},{"id":"2305.10250","title":"MemoryBank: Enhancing Large Language Models with Long-Term Memory","created":"2023-05-17","cited_by_count":556},{"id":"2212.10496","title":"Precise Zero-Shot Dense Retrieval without Relevance Labels","created":"2022-12-20","cited_by_count":517},{"id":"2405.01535","title":"Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models","created":"2024-05-02","cited_by_count":446},{"id":"2412.15204","title":"LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks","created":"2024-12-19","cited_by_count":379},{"id":"2104.05938","title":"QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization","created":"2021-04-13","cited_by_count":365},{"id":"2107.07567","title":"Beyond Goldfish Memory: Long-Term Open-Domain Conversation","created":"2021-07-15","cited_by_count":267},{"id":"2406.12624","title":"Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges","created":"2024-06-18","cited_by_count":205},{"id":"2009.08553","title":"Generation-Augmented Retrieval for Open-domain Question Answering","created":"2020-09-17","cited_by_count":186},{"id":"2501.17399","title":"MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs","created":"2025-01-29","cited_by_count":180},{"id":"2402.18013","title":"A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems","created":"2024-02-28","cited_by_count":170},{"id":"2403.18802","title":"Long-form factuality in large language models","created":"2024-03-27","cited_by_count":155},{"id":"2303.07678","title":"Query2doc: Query Expansion with Large Language Models","created":"2023-03-14","cited_by_count":149},{"id":"2406.05925","title":"Hello Again! LLM-powered Personalized Agent for Long-term Dialogue","created":"2024-06-09","cited_by_count":123},{"id":"2503.08026","title":"In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents","created":"2025-03-11","cited_by_count":106},{"id":"2502.05589","title":"On Memory Construction and Retrieval for Personalized Conversational Agents","created":"2025-02-08","cited_by_count":105},{"id":"2407.00908","title":"FineSurE: Fine-grained Summarization Evaluation using LLMs","created":"2024-07-01","cited_by_count":83},{"id":"2406.10996","title":"Towards Lifelong Dialogue Agents via Timeline-based Memory Management","created":"2024-06-16","cited_by_count":51},{"id":"2112.08713","title":"CONFIT: Toward Faithful Dialogue Summarization with Linguistically-Informed Contrastive Fine-tuning","created":"2021-12-16","cited_by_count":44},{"id":"2502.13270","title":"REALTALK: A 21-Day Real-World Dataset for Long-Term Conversation","created":"2025-02-18","cited_by_count":35},{"id":"2106.08556","title":"Coreference-Aware Dialogue Summarization","created":"2021-06-16","cited_by_count":34},{"id":"2310.10570","title":"On Context Utilization in Summarization with Large Language Models","created":"2023-10-16","cited_by_count":30},{"id":"2109.04609","title":"An Exploratory Study on Long Dialogue Summarization: What Works and What's Next","created":"2021-09-10","cited_by_count":28},{"id":"2402.11827","title":"Ask Optimal Questions: Aligning Large Language Models with Retriever's Preference in Conversation","created":"2024-02-19","cited_by_count":23},{"id":"2409.19898","title":"UniSumEval: Towards Unified, Fine-Grained, Multi-Dimensional Summarization Evaluation for LLMs","created":"2024-09-30","cited_by_count":21},{"id":"2601.04463","title":"Beyond Static Summarization: Proactive Memory Extraction for LLM Agents","created":"2026-01-08","cited_by_count":21},{"id":"2406.13144","title":"DialSim: A Dialogue Simulator for Evaluating Long-Term Multi-Party Dialogue Understanding of Conversational Agents","created":"2024-06-19","cited_by_count":20},{"id":"2505.20231","title":"MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents","created":"2025-05-26","cited_by_count":17},{"id":"2506.00549","title":"Towards Multi-dimensional Evaluation of LLM Summarization across Domains and Languages","created":"2025-05-31","cited_by_count":11},{"id":"2603.16496","title":"AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents","created":"2026-03-17","cited_by_count":11},{"id":"2305.16548","title":"Annotating and Detecting Fine-grained Factual Errors for Dialogue Summarization","created":"2023-05-26","cited_by_count":10},{"id":"2505.24575","title":"NexusSum: Hierarchical LLM Agents for Long-Form Narrative Summarization","created":"2025-05-30","cited_by_count":10},{"id":"2108.09597","title":"Hierarchical Summarization for Longform Spoken Dialog","created":"2021-08-21","cited_by_count":9},{"id":"2404.11124","title":"What's under the hood: Investigating Automatic Metrics on Meeting Summarization","created":"2024-04-17","cited_by_count":9},{"id":"2502.00977","title":"Context-Aware Hierarchical Merging for Long Document Summarization","created":"2025-02-03","cited_by_count":9},{"id":"2401.15496","title":"Baichuan2-Sum: Instruction Finetune Baichuan2-7B Model for Dialogue Summarization","created":"2024-01-27","cited_by_count":7},{"id":"2406.14709","title":"Factual Dialogue Summarization via Learning from Large Language Models","created":"2024-06-20","cited_by_count":6},{"id":"2507.02145","title":"Reasoning or Not? A Comprehensive Evaluation of Reasoning LLMs for Dialogue Summarization","created":"2025-07-02","cited_by_count":6},{"id":"2403.19889","title":"Towards a Robust Retrieval-Based Summarization System","created":"2024-03-29","cited_by_count":5},{"id":"2407.15021","title":"Enhancing Incremental Summarization with Structured Representations","created":"2024-07-21","cited_by_count":4},{"id":"2510.06677","title":"Incremental Summarization for Customer Support via Progressive Note-Taking and Agent Feedback","created":"2025-10-08","cited_by_count":4},{"id":"2210.09894","title":"Taxonomy of Abstractive Dialogue Summarization: Scenarios, Approaches and Future Directions","created":"2022-10-18","cited_by_count":3},{"id":"2506.11857","title":"Post Persona Alignment for Multi-Session Dialogue Generation","created":"2025-06-13","cited_by_count":3},{"id":"2310.10981","title":"Instructive Dialogue Summarization with Query Aggregations","created":"2023-10-17","cited_by_count":2},{"id":"2503.04789","title":"Aligning Extraction and Generation for Robust Retrieval-Augmented Generation","created":"2025-02-28","cited_by_count":2},{"id":"2508.19578","title":"Towards a Holistic and Automated Evaluation Framework for Multi-Level Comprehension of LLMs in Book-Length Contexts","created":"2025-08-27","cited_by_count":2},{"id":"2509.26302","title":"QUARTZ : QA-based Unsupervised Abstractive Refinement for Task-oriented Dialogue Summarization","created":"2025-09-30","cited_by_count":2}],"next_cursor":null}