{"list":"other","total":59,"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":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"id":"2404.16130","title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","created":"2024-04-24","cited_by_count":1453},{"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":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"id":"2003.07082","title":"Stanza: A Python Natural Language Processing Toolkit for Many Human Languages","created":"2020-03-16","cited_by_count":723},{"id":"2404.13076","title":"LLM Evaluators Recognize and Favor Their Own Generations","created":"2024-04-15","cited_by_count":686},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494},{"id":"2301.13848","title":"Benchmarking Large Language Models for News Summarization","created":"2023-01-31","cited_by_count":445},{"id":"2310.18018","title":"NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark","created":"2023-10-27","cited_by_count":348},{"id":"2209.12356","title":"News Summarization and Evaluation in the Era of GPT-3","created":"2022-09-26","cited_by_count":327},{"id":"2305.16739","title":"AlignScore: Evaluating Factual Consistency with a Unified Alignment Function","created":"2023-05-26","cited_by_count":288},{"id":"2212.07981","title":"Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation","created":"2022-12-15","cited_by_count":142},{"id":"2310.00785","title":"BooookScore: A systematic exploration of book-length summarization in the era of LLMs","created":"2023-10-01","cited_by_count":137},{"id":"2109.09784","title":"Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization","created":"2021-08-30","cited_by_count":129},{"id":"2406.19276","title":"VERISCORE: Evaluating the factuality of verifiable claims in long-form text generation","created":"2024-06-27","cited_by_count":117},{"id":"2211.08412","title":"Evaluating the Factual Consistency of Large Language Models Through News Summarization","created":"2022-11-15","cited_by_count":92},{"id":"2407.00908","title":"FineSurE: Fine-grained Summarization Evaluation using LLMs","created":"2024-07-01","cited_by_count":83},{"id":"2305.14239","title":"On Learning to Summarize with Large Language Models as References","created":"2023-05-23","cited_by_count":80},{"id":"2402.13249","title":"TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization","created":"2024-02-20","cited_by_count":66},{"id":"2404.01261","title":"FABLES: Evaluating faithfulness and content selection in book-length summarization","created":"2024-04-01","cited_by_count":65},{"id":"2412.17259","title":"LegalAgentBench: Evaluating LLM Agents in Legal Domain","created":"2024-12-23","cited_by_count":59},{"id":"2309.04269","title":"From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting","created":"2023-09-08","cited_by_count":52},{"id":"2306.07799","title":"ChatGPT vs Human-authored Text: Insights into Controllable Text Summarization and Sentence Style Transfer","created":"2023-06-13","cited_by_count":50},{"id":"2305.13632","title":"Detecting and Mitigating Hallucinations in Multilingual Summarisation","created":"2023-05-23","cited_by_count":48},{"id":"2309.09369","title":"Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articles","created":"2023-09-17","cited_by_count":45},{"id":"2210.13448","title":"EUR-Lex-Sum: A Multi- and Cross-lingual Dataset for Long-form Summarization in the Legal Domain","created":"2022-10-24","cited_by_count":40},{"id":"2205.06009","title":"Falsesum: Generating Document-level NLI Examples for Recognizing Factual Inconsistency in Summarization","created":"2022-05-12","cited_by_count":34},{"id":"2403.02270","title":"FENICE: Factuality Evaluation of summarization based on Natural language Inference and Claim Extraction","created":"2024-03-04","cited_by_count":28},{"id":"2410.23609","title":"On Positional Bias of Faithfulness for Long-form Summarization","created":"2024-10-31","cited_by_count":22},{"id":"2204.13761","title":"Faithful to the Document or to the World? Mitigating Hallucinations via Entity-linked Knowledge in Abstractive Summarization","created":"2022-04-28","cited_by_count":20},{"id":"2505.04847","title":"Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards","created":"2025-05-07","cited_by_count":20},{"id":"2503.09600","title":"MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System","created":"2025-03-12","cited_by_count":19},{"id":"2311.09212","title":"Controllable Text Summarization: Unraveling Challenges, Approaches, and Prospects -- A Survey","created":"2023-11-15","cited_by_count":18},{"id":"2305.16784","title":"Incorporating Distributions of Discourse Structure for Long Document Abstractive Summarization","created":"2023-05-26","cited_by_count":17},{"id":"2410.13961","title":"From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization","created":"2024-10-17","cited_by_count":17},{"id":"2311.09335","title":"Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization","created":"2023-11-15","cited_by_count":16},{"id":"2402.14182","title":"Do Machines and Humans Focus on Similar Code? Exploring Explainability of Large Language Models in Code Summarization","created":"2024-02-22","cited_by_count":16},{"id":"2212.07672","title":"Summary-Oriented Vision Modeling for Multimodal Abstractive Summarization","created":"2022-12-15","cited_by_count":14},{"id":"2508.03860","title":"Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Models","created":"2025-08-05","cited_by_count":13},{"id":"2210.04829","title":"Hierarchical3D Adapters for Long Video-to-text Summarization","created":"2022-10-10","cited_by_count":12},{"id":"2307.15793","title":"Summaries, Highlights, and Action items: Design, implementation and evaluation of an LLM-powered meeting recap system","created":"2023-07-28","cited_by_count":12},{"id":"2403.17768","title":"SciNews: From Scholarly Complexities to Public Narratives -- A Dataset for Scientific News Report Generation","created":"2024-03-26","cited_by_count":12},{"id":"2305.08828","title":"PMIndiaSum: Multilingual and Cross-lingual Headline Summarization for Languages in India","created":"2023-05-15","cited_by_count":11},{"id":"2405.00657","title":"RST-LoRA: A Discourse-Aware Low-Rank Adaptation for Long Document Abstractive Summarization","created":"2024-05-01","cited_by_count":11},{"id":"2502.08279","title":"What Is That Talk About? A Video-to-Text Summarization Dataset for Scientific Presentations","created":"2025-02-12","cited_by_count":11},{"id":"2506.00549","title":"Towards Multi-dimensional Evaluation of LLM Summarization across Domains and Languages","created":"2025-05-31","cited_by_count":11},{"id":"2402.03509","title":"Evaluating the Factuality of Zero-shot Summarizers Across Varied Domains","created":"2024-02-05","cited_by_count":10},{"id":"2507.11405","title":"DCR: Quantifying Data Contamination in LLMs Evaluation","created":"2025-07-15","cited_by_count":10},{"id":"2510.12839","title":"FaStfact: Faster, Stronger Long-Form Factuality Evaluations in LLMs","created":"2025-10-13","cited_by_count":8},{"id":"2401.10415","title":"Can Large Language Model Summarizers Adapt to Diverse Scientific Communication Goals?","created":"2024-01-18","cited_by_count":6},{"id":"2503.01670","title":"Evaluating LLMs' Assessment of Mixed-Context Hallucination Through the Lens of Summarization","created":"2025-03-03","cited_by_count":6},{"id":"2502.14409","title":"Unstructured Evidence Attribution for Long Context Query Focused Summarization","created":"2025-02-20","cited_by_count":5},{"id":"2502.00322","title":"MODS: Moderating a Mixture of Document Speakers to Summarize Debatable Queries in Document Collections","created":"2025-02-01","cited_by_count":4},{"id":"2504.19339","title":"Explanatory Summarization with Discourse-Driven Planning","created":"2025-04-27","cited_by_count":4},{"id":"2601.13649","title":"Fairness or Fluency? An Investigation into Language Bias of Pairwise LLM-as-a-Judge","created":"2026-01-20","cited_by_count":3},{"id":"2412.02819","title":"CNNSum: Exploring Long-Context Summarization with Large Language Models in Chinese Novels","created":"2024-12-03","cited_by_count":2}],"next_cursor":null}