{"total":122,"rows":[{"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,"area":null},{"id":"2301.13848","title":"Benchmarking Large Language Models for News Summarization","created":"2023-01-31","cited_by_count":445,"area":null},{"id":"2505.06120","title":"LLMs Get Lost In Multi-Turn Conversation","created":"2025-05-09","cited_by_count":429,"area":null},{"id":"2302.04166","title":"GPTScore: Evaluate as You Desire","created":"2023-02-08","cited_by_count":361,"area":null},{"id":"2307.13528","title":"FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios","created":"2023-07-25","cited_by_count":251,"area":null},{"id":"2307.11088","title":"L-Eval: Instituting Standardized Evaluation for Long Context Language Models","created":"2023-07-20","cited_by_count":233,"area":null},{"id":"2310.07521","title":"Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity","created":"2023-10-11","cited_by_count":206,"area":null},{"id":"2405.01724","title":"Large Language Models are Inconsistent and Biased Evaluators","created":"2024-05-02","cited_by_count":153,"area":null},{"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,"area":null},{"id":"2305.18486","title":"A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets","created":"2023-05-29","cited_by_count":123,"area":null},{"id":"2303.01432","title":"WiCE: Real-World Entailment for Claims in Wikipedia","created":"2023-03-02","cited_by_count":120,"area":null},{"id":"2305.18201","title":"A Critical Evaluation of Evaluations for Long-form Question Answering","created":"2023-05-29","cited_by_count":111,"area":null},{"id":"2305.11859","title":"Complex Claim Verification with Evidence Retrieved in the Wild","created":"2023-05-19","cited_by_count":110,"area":null},{"id":"2301.13298","title":"LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization","created":"2023-01-30","cited_by_count":96,"area":null},{"id":"2403.18771","title":"CheckEval: A reliable LLM-as-a-Judge framework for evaluating text generation using checklists","created":"2024-03-27","cited_by_count":94,"area":null},{"id":"2311.09766","title":"LLMs as Narcissistic Evaluators: When Ego Inflates Evaluation Scores","created":"2023-11-16","cited_by_count":90,"area":null},{"id":"2311.09000","title":"Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers","created":"2023-11-15","cited_by_count":87,"area":null},{"id":"2305.14239","title":"On Learning to Summarize with Large Language Models as References","created":"2023-05-23","cited_by_count":80,"area":null},{"id":"2311.09184","title":"Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarization","created":"2023-11-15","cited_by_count":69,"area":null},{"id":"2301.09790","title":"The Next Chapter: A Study of Large Language Models in Storytelling","created":"2023-01-24","cited_by_count":58,"area":null},{"id":"2305.08281","title":"FactKB: Generalizable Factuality Evaluation using Language Models Enhanced with Factual Knowledge","created":"2023-05-14","cited_by_count":55,"area":null},{"id":"2309.04269","title":"From Sparse to Dense: GPT-4 Summarization with Chain of Density Prompting","created":"2023-09-08","cited_by_count":52,"area":null},{"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,"area":null},{"id":"2310.12150","title":"Understanding Retrieval Augmentation for Long-Form Question Answering","created":"2023-10-18","cited_by_count":45,"area":null},{"id":"2406.20079","title":"Molecular Facts: Desiderata for Decontextualization in LLM Fact Verification","created":"2024-06-28","cited_by_count":44,"area":null},{"id":"2305.14889","title":"Evaluating Evaluation Metrics: A Framework for Analyzing NLG Evaluation Metrics using Measurement Theory","created":"2023-05-24","cited_by_count":43,"area":null},{"id":"2305.13194","title":"SEAHORSE: A Multilingual, Multifaceted Dataset for Summarization Evaluation","created":"2023-05-22","cited_by_count":42,"area":null},{"id":"2402.06544","title":"Calibrating Long-form Generations from Large Language Models","created":"2024-02-09","cited_by_count":32,"area":null},{"id":"2410.03775","title":"Beyond correlation: The Impact of Human Uncertainty in Measuring the Effectiveness of Automatic Evaluation and LLM-as-a-Judge","created":"2024-10-03","cited_by_count":31,"area":null},{"id":"2310.10570","title":"On Context Utilization in Summarization with Large Language Models","created":"2023-10-16","cited_by_count":30,"area":null},{"id":"2303.03608","title":"Towards Interpretable and Efficient Automatic Reference-Based Summarization Evaluation","created":"2023-03-07","cited_by_count":24,"area":null},{"id":"2404.08126","title":"Auctions with LLM Summaries","created":"2024-04-11","cited_by_count":24,"area":null},{"id":"2310.19792","title":"The Eval4NLP 2023 Shared Task on Prompting Large Language Models as Explainable Metrics","created":"2023-10-30","cited_by_count":23,"area":null},{"id":"2410.07069","title":"ReIFE: Re-evaluating Instruction-Following Evaluation","created":"2024-10-09","cited_by_count":22,"area":null},{"id":"2410.23609","title":"On Positional Bias of Faithfulness for Long-form Summarization","created":"2024-10-31","cited_by_count":22,"area":null},{"id":"2405.12701","title":"OLAPH: Improving Factuality in Biomedical Long-form Question Answering","created":"2024-05-21","cited_by_count":20,"area":null},{"id":"2507.01001","title":"SciArena: An Open Evaluation Platform for Non-Verifiable Scientific Literature-Grounded Tasks","created":"2025-07-01","cited_by_count":20,"area":null},{"id":"2305.13693","title":"Automated Metrics for Medical Multi-Document Summarization Disagree with Human Evaluations","created":"2023-05-23","cited_by_count":18,"area":null},{"id":"2310.01880","title":"AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrieval","created":"2023-10-03","cited_by_count":18,"area":null},{"id":"2310.08394","title":"Towards Better Evaluation of Instruction-Following: A Case-Study in Summarization","created":"2023-10-12","cited_by_count":18,"area":null},{"id":"2212.10449","title":"Socratic Pretraining: Question-Driven Pretraining for Controllable Summarization","created":"2022-12-20","cited_by_count":17,"area":null},{"id":"2310.17876","title":"TarGEN: Targeted Data Generation with Large Language Models","created":"2023-10-27","cited_by_count":17,"area":null},{"id":"2311.07884","title":"Fair Abstractive Summarization of Diverse Perspectives","created":"2023-11-14","cited_by_count":17,"area":null},{"id":"2410.13961","title":"From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization","created":"2024-10-17","cited_by_count":17,"area":null},{"id":"2305.14702","title":"DecipherPref: Analyzing Influential Factors in Human Preference Judgments via GPT-4","created":"2023-05-24","cited_by_count":16,"area":null},{"id":"2406.18528","title":"PrExMe! Large Scale Prompt Exploration of Open Source LLMs for Machine Translation and Summarization Evaluation","created":"2024-06-26","cited_by_count":16,"area":null},{"id":"2404.11184","title":"FIZZ: Factual Inconsistency Detection by Zoom-in Summary and Zoom-out Document","created":"2024-04-17","cited_by_count":15,"area":null},{"id":"2406.06125","title":"Verifiable Generation with Subsentence-Level Fine-Grained Citations","created":"2024-06-10","cited_by_count":15,"area":null},{"id":"2411.05338","title":"SciDQA: A Deep Reading Comprehension Dataset over Scientific Papers","created":"2024-11-08","cited_by_count":15,"area":null},{"id":"2311.09069","title":"How Well Do Large Language Models Truly Ground?","created":"2023-11-15","cited_by_count":14,"area":null},{"id":"2401.16475","title":"InfoLossQA: Characterizing and Recovering Information Loss in Text Simplification","created":"2024-01-29","cited_by_count":14,"area":null},{"id":"2410.07473","title":"Localizing Factual Inconsistencies in Attributable Text Generation","created":"2024-10-09","cited_by_count":14,"area":null},{"id":"2504.11972","title":"Reassessing Extractive QA Datasets at Scale: LLM-as-a-Judge and In-Depth Analyses","created":"2025-04-16","cited_by_count":14,"area":null},{"id":"2305.19204","title":"SWiPE: A Dataset for Document-Level Simplification of Wikipedia Pages","created":"2023-05-30","cited_by_count":12,"area":null},{"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,"area":null},{"id":"2311.04694","title":"Evaluating Generative Ad Hoc Information Retrieval","created":"2023-11-08","cited_by_count":11,"area":null},{"id":"2402.11176","title":"KnowTuning: Knowledge-aware Fine-tuning for Large Language Models","created":"2024-02-17","cited_by_count":11,"area":null},{"id":"2409.08435","title":"When Context Leads but Parametric Memory Follows in Large Language Models","created":"2024-09-13","cited_by_count":11,"area":null},{"id":"2305.17779","title":"Generating EDU Extracts for Plan-Guided Summary Re-Ranking","created":"2023-05-28","cited_by_count":9,"area":null},{"id":"2311.02271","title":"FaMeSumm: Investigating and Improving Faithfulness of Medical Summarization","created":"2023-11-03","cited_by_count":9,"area":null},{"id":"2302.02962","title":"LoFT: Enhancing Faithfulness and Diversity for Table-to-Text Generation via Logic Form Control","created":"2023-02-06","cited_by_count":8,"area":null},{"id":"2411.19655","title":"Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-Oasis","created":"2024-11-29","cited_by_count":8,"area":null},{"id":"2412.07096","title":"QAPyramid: Fine-grained Evaluation of Content Selection for Text Summarization","created":"2024-12-10","cited_by_count":8,"area":null},{"id":"2506.19352","title":"Spotting Out-of-Character Behavior: Atomic-Level Evaluation of Persona Fidelity in Open-Ended Generation","created":"2025-06-24","cited_by_count":8,"area":null},{"id":"2307.04018","title":"Revisiting Cross-Lingual Summarization: A Corpus-based Study and A New Benchmark with Improved Annotation","created":"2023-07-08","cited_by_count":7,"area":null},{"id":"2403.01774","title":"WebCiteS: Attributed Query-Focused Summarization on Chinese Web Search Results with Citations","created":"2024-03-04","cited_by_count":7,"area":null},{"id":"2406.05360","title":"Flexible and Adaptable Summarization via Expertise Separation","created":"2024-06-08","cited_by_count":7,"area":null},{"id":"2305.04853","title":"The Current State of Summarization","created":"2023-05-08","cited_by_count":6,"area":null},{"id":"2311.01949","title":"Hint-enhanced In-Context Learning wakes Large Language Models up for knowledge-intensive tasks","created":"2023-11-03","cited_by_count":6,"area":null},{"id":"2401.17974","title":"GUMsley: Evaluating Entity Salience in Summarization for 12 English Genres","created":"2024-01-31","cited_by_count":6,"area":null},{"id":"2406.19803","title":"Scalable and Domain-General Abstractive Proposition Segmentation","created":"2024-06-28","cited_by_count":6,"area":null},{"id":"2508.19221","title":"Evaluating the Evaluators: Are readability metrics good measures of readability?","created":"2025-08-26","cited_by_count":6,"area":null},{"id":"2310.01917","title":"Hierarchical Evaluation Framework: Best Practices for Human Evaluation","created":"2023-10-03","cited_by_count":5,"area":null},{"id":"2404.01701","title":"On the Role of Summary Content Units in Text Summarization Evaluation","created":"2024-04-02","cited_by_count":5,"area":null},{"id":"2410.10867","title":"Mitigating the Impact of Reference Quality on Evaluation of Summarization Systems with Reference-Free Metrics","created":"2024-10-08","cited_by_count":5,"area":null},{"id":"2504.08024","title":"Summarizing Speech: A Comprehensive Survey","created":"2025-04-10","cited_by_count":5,"area":null},{"id":"2403.01002","title":"Attribute Structuring Improves LLM-Based Evaluation of Clinical Text Summaries","created":"2024-03-01","cited_by_count":4,"area":null},{"id":"2407.11930","title":"Localizing and Mitigating Errors in Long-form Question Answering","created":"2024-07-16","cited_by_count":4,"area":null},{"id":"2409.09249","title":"NovAScore: A New Automated Metric for Evaluating Document Level Novelty","created":"2024-09-14","cited_by_count":4,"area":null},{"id":"2410.02741","title":"Salient Information Prompting to Steer Content in Prompt-based Abstractive Summarization","created":"2024-10-03","cited_by_count":4,"area":null},{"id":"2412.03589","title":"Human Evaluation of Procedural Knowledge Graph Extraction from Text with Large Language Models","created":"2024-11-27","cited_by_count":4,"area":null},{"id":"2504.17279","title":"Evaluating and Mitigating Bias in AI-Based Medical Text Generation","created":"2025-04-24","cited_by_count":4,"area":null},{"id":"2507.22752","title":"CUS-QA: Local-Knowledge-Oriented Open-Ended Question Answering Dataset","created":"2025-07-30","cited_by_count":4,"area":null},{"id":"2402.18756","title":"How Much Annotation is Needed to Compare Summarization Models?","created":"2024-02-28","cited_by_count":3,"area":null},{"id":"2406.16288","title":"PlagBench: Exploring the Duality of Large Language Models in Plagiarism Generation and Detection","created":"2024-06-24","cited_by_count":3,"area":null},{"id":"2502.06617","title":"Scaling Multi-Document Event Summarization: Evaluating Compression vs. Full-Text Approaches","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2306.11256","title":"GUMSum: Multi-Genre Data and Evaluation for English Abstractive Summarization","created":"2023-06-20","cited_by_count":2,"area":null},{"id":"2402.17008","title":"Benchmarking LLMs on the Semantic Overlap Summarization Task","created":"2024-02-26","cited_by_count":2,"area":null},{"id":"2409.19507","title":"A Critical Look at Meta-evaluating Summarisation Evaluation Metrics","created":"2024-09-29","cited_by_count":2,"area":null},{"id":"2410.14666","title":"DiscoGraMS: Enhancing Movie Screen-Play Summarization using Movie Character-Aware Discourse Graph","created":"2024-10-18","cited_by_count":2,"area":null},{"id":"2411.15993","title":"Investigating Factuality in Long-Form Text Generation: The Roles of Self-Known and Self-Unknown","created":"2024-11-24","cited_by_count":2,"area":null},{"id":"2502.17136","title":"Evaluating the Effectiveness of Large Language Models in Automated News Article Summarization","created":"2025-02-24","cited_by_count":2,"area":null},{"id":"2503.18526","title":"SciClaims: An End-to-End Generative System for Biomedical Claim Analysis","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2505.05406","title":"Frame In, Frame Out: Measuring Framing Bias in LLM-Generated News Summaries","created":"2025-05-08","cited_by_count":2,"area":null},{"id":"2507.01160","title":"Event-based evaluation of abstractive news summarization","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2509.00029","title":"From Sound to Sight: Towards AI-authored Music Videos","created":"2025-08-20","cited_by_count":2,"area":null},{"id":"2602.11318","title":"The Consensus Trap: Dissecting Subjectivity and the \"Ground Truth\" Illusion in Data Annotation","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2602.11908","title":"When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation","created":"2026-02-12","cited_by_count":2,"area":null},{"id":"2606.23989","title":"Attributable by Construction: Claim-Anchored Provenance for Multi-Document Summarization","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2308.02270","title":"Redundancy Aware Multi-Reference Based Gainwise Evaluation of Extractive Summarization","created":"2023-08-04","cited_by_count":1,"area":null}],"next_cursor":"100"}