{"total":96,"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":"2402.17753","title":"Evaluating Very Long-Term Conversational Memory of LLM Agents","created":"2024-02-27","cited_by_count":830,"area":"agents"},{"id":"2306.01693","title":"Fine-Grained Human Feedback Gives Better Rewards for Language Model Training","created":"2023-06-02","cited_by_count":401,"area":"alignment"},{"id":"2311.09476","title":"ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems","created":"2023-11-16","cited_by_count":265,"area":"rag"},{"id":"2307.10928","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","created":"2023-07-20","cited_by_count":201,"area":"alignment"},{"id":"2402.14207","title":"Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models","created":"2024-02-22","cited_by_count":154,"area":null},{"id":"2507.21504","title":"Evaluation and Benchmarking of LLM Agents: A Survey","created":"2025-07-29","cited_by_count":152,"area":"agents"},{"id":"2410.02660","title":"How to Train Long-Context Language Models (Effectively)","created":"2024-10-03","cited_by_count":146,"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":"2309.07852","title":"ExpertQA: Expert-Curated Questions and Attributed Answers","created":"2023-09-14","cited_by_count":97,"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":"2407.01370","title":"Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems","created":"2024-07-01","cited_by_count":87,"area":"rag"},{"id":"2309.13633","title":"EvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteria","created":"2023-09-24","cited_by_count":74,"area":null},{"id":"2407.10817","title":"Foundational Autoraters: Taming Large Language Models for Better Automatic Evaluation","created":"2024-07-15","cited_by_count":74,"area":null},{"id":"2405.02559","title":"A Framework for Human Evaluation of Large Language Models in Healthcare Derived from Literature Review","created":"2024-05-04","cited_by_count":66,"area":null},{"id":"2501.03200","title":"The FACTS Grounding Leaderboard: Benchmarking LLMs' Ability to Ground Responses to Long-Form Input","created":"2025-01-06","cited_by_count":52,"area":null},{"id":"2311.01477","title":"FaithScore: Fine-grained Evaluations of Hallucinations in Large Vision-Language Models","created":"2023-11-02","cited_by_count":46,"area":"mllm"},{"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":"2412.13091","title":"LMUnit: Fine-grained Evaluation with Natural Language Unit Tests","created":"2024-12-17","cited_by_count":33,"area":null},{"id":"2311.09198","title":"Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Training","created":"2023-11-15","cited_by_count":32,"area":null},{"id":"2307.15770","title":"CHATREPORT: Democratizing Sustainability Disclosure Analysis through LLM-based Tools","created":"2023-07-28","cited_by_count":29,"area":null},{"id":"2309.07382","title":"Less is More for Long Document Summary Evaluation by LLMs","created":"2023-09-14","cited_by_count":28,"area":null},{"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,"area":null},{"id":"2404.12318","title":"Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment","created":"2024-04-18","cited_by_count":26,"area":"alignment"},{"id":"2410.03227","title":"ALR$^2$: A Retrieve-then-Reason Framework for Long-context Question Answering","created":"2024-10-04","cited_by_count":26,"area":"lr"},{"id":"2310.13189","title":"Fast and Accurate Factual Inconsistency Detection Over Long Documents","created":"2023-10-19","cited_by_count":23,"area":null},{"id":"2410.21545","title":"CARMO: Dynamic Criteria Generation for Context-Aware Reward Modelling","created":"2024-10-28","cited_by_count":22,"area":"alignment"},{"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":"2502.10709","title":"An Empirical Analysis of Uncertainty in Large Language Model Evaluations","created":"2025-02-15","cited_by_count":20,"area":null},{"id":"2403.01061","title":"Reading Subtext: Evaluating Large Language Models on Short Story Summarization with Writers","created":"2024-03-02","cited_by_count":19,"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":"2309.12455","title":"LongDocFACTScore: Evaluating the Factuality of Long Document Abstractive Summarisation","created":"2023-09-21","cited_by_count":16,"area":null},{"id":"2407.03572","title":"Core: Robust Factual Precision with Informative Sub-Claim Identification","created":"2024-07-04","cited_by_count":16,"area":null},{"id":"2505.14279","title":"YESciEval: Robust LLM-as-a-Judge for Scientific Question Answering","created":"2025-05-20","cited_by_count":16,"area":null},{"id":"2305.14341","title":"APPLS: Evaluating Evaluation Metrics for Plain Language Summarization","created":"2023-05-23","cited_by_count":15,"area":null},{"id":"2507.23276","title":"How Far Are AI Scientists from Changing the World?","created":"2025-07-31","cited_by_count":15,"area":null},{"id":"2402.05629","title":"Merging Facts, Crafting Fallacies: Evaluating the Contradictory Nature of Aggregated Factual Claims in Long-Form Generations","created":"2024-02-08","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":"2403.03823","title":"A Modular Approach for Multimodal Summarization of TV Shows","created":"2024-03-06","cited_by_count":13,"area":null},{"id":"2506.10341","title":"Formalizing Learning from Language Feedback with Provable Guarantees","created":"2025-06-12","cited_by_count":13,"area":null},{"id":"2403.06754","title":"ALaRM: Align Language Models via Hierarchical Rewards Modeling","created":"2024-03-11","cited_by_count":11,"area":"alignment"},{"id":"2506.00549","title":"Towards Multi-dimensional Evaluation of LLM Summarization across Domains and Languages","created":"2025-05-31","cited_by_count":11,"area":null},{"id":"2305.14625","title":"KNN-LM Does Not Improve Open-ended Text Generation","created":"2023-05-24","cited_by_count":10,"area":"rag"},{"id":"2508.09853","title":"STREAM (ChemBio): A Standard for Transparently Reporting Evaluations in AI Model Reports","created":"2025-08-13","cited_by_count":10,"area":null},{"id":"2407.06501","title":"STORYSUMM: Evaluating Faithfulness in Story Summarization","created":"2024-07-09","cited_by_count":9,"area":null},{"id":"2501.00269","title":"A review of faithfulness metrics for hallucination assessment in Large Language Models","created":"2024-12-31","cited_by_count":9,"area":null},{"id":"2502.00977","title":"Context-Aware Hierarchical Merging for Long Document Summarization","created":"2025-02-03","cited_by_count":9,"area":null},{"id":"2504.04713","title":"Sequential-NIAH: A Needle-In-A-Haystack Benchmark for Extracting Sequential Needles from Long Contexts","created":"2025-04-07","cited_by_count":9,"area":null},{"id":"2311.06534","title":"Translating Legalese: Enhancing Public Understanding of Court Opinions with Legal Summarizers","created":"2023-11-11","cited_by_count":8,"area":null},{"id":"2402.10979","title":"SportsMetrics: Blending Text and Numerical Data to Understand Information Fusion in LLMs","created":"2024-02-15","cited_by_count":8,"area":null},{"id":"2403.14238","title":"Reinforcement Learning from Reflective Feedback (RLRF): Aligning and Improving LLMs via Fine-Grained Self-Reflection","created":"2024-03-21","cited_by_count":8,"area":"alignment"},{"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":"2501.14883","title":"Verify with Caution: The Pitfalls of Relying on Imperfect Factuality Metrics","created":"2025-01-24","cited_by_count":8,"area":null},{"id":"2502.06185","title":"Discourse-Driven Evaluation: Unveiling Factual Inconsistency in Long Document Summarization","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2404.12041","title":"A Survey of Automatic Hallucination Evaluation on Natural Language Generation","created":"2024-04-18","cited_by_count":7,"area":null},{"id":"2502.17163","title":"MEMERAG: A Multilingual End-to-End Meta-Evaluation Benchmark for Retrieval Augmented Generation","created":"2025-02-24","cited_by_count":7,"area":"rag"},{"id":"2311.14652","title":"One Pass Streaming Algorithm for Super Long Token Attention Approximation in Sublinear Space","created":"2023-11-24","cited_by_count":6,"area":null},{"id":"2405.01930","title":"OARelatedWork: A Large-Scale Dataset of Related Work Sections with Full-texts from Open Access Sources","created":"2024-05-03","cited_by_count":6,"area":null},{"id":"2408.03325","title":"CoverBench: A Challenging Benchmark for Complex Claim Verification","created":"2024-08-06","cited_by_count":6,"area":null},{"id":"2510.20941","title":"Do LLMs Truly Understand When a Precedent Is Overruled?","created":"2025-10-23","cited_by_count":6,"area":null},{"id":"2512.21577","title":"A Unified Definition of Hallucination: It's The World Model, Stupid!","created":"2025-12-25","cited_by_count":6,"area":"wm"},{"id":"2402.12821","title":"Identifying Factual Inconsistencies in Summaries: Grounding LLM Inference via Task Taxonomy","created":"2024-02-20","cited_by_count":5,"area":null},{"id":"2405.19094","title":"Faithful Chart Summarization with ChaTS-Pi","created":"2024-05-29","cited_by_count":5,"area":null},{"id":"2410.19809","title":"ScreenWriter: Automatic Screenplay Generation and Movie Summarisation","created":"2024-10-17","cited_by_count":5,"area":null},{"id":"2501.00097","title":"CaseSumm: A Large-Scale Dataset for Long-Context Summarization from U.S. Supreme Court Opinions","created":"2024-12-30","cited_by_count":5,"area":null},{"id":"2412.08268","title":"LCFO: Long Context and Long Form Output Dataset and Benchmarking","created":"2024-12-11","cited_by_count":4,"area":null},{"id":"2506.11104","title":"DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration","created":"2025-06-06","cited_by_count":4,"area":"inference"},{"id":"2506.16024","title":"From General to Targeted Rewards: Surpassing GPT-4 in Open-Ended Long-Context Generation","created":"2025-06-19","cited_by_count":4,"area":null},{"id":"2507.06415","title":"PERK: Long-Context Reasoning as Test-Time Learning","created":"2025-07-08","cited_by_count":4,"area":"lr"},{"id":"2406.14099","title":"Let Guidelines Guide You: A Prescriptive Guideline-Centered Data Annotation Methodology","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2410.10372","title":"BookWorm: A Dataset for Character Description and Analysis","created":"2024-10-14","cited_by_count":3,"area":null},{"id":"2503.01201","title":"Parameter-free Video Segmentation for Vision and Language Understanding","created":"2025-03-03","cited_by_count":3,"area":null},{"id":"2505.23654","title":"ARC: Argument Representation and Coverage Analysis for Zero-Shot Long Document Summarization with Instruction Following LLMs","created":"2025-05-29","cited_by_count":3,"area":null},{"id":"2512.08936","title":"A Principle-based Framework for the Development and Evaluation of Large Language Models for Health and Wellness","created":"2025-10-23","cited_by_count":3,"area":null},{"id":"2605.26667","title":"MemFail: Stress-Testing Failure Modes of LLM Memory Systems","created":"2026-05-26","cited_by_count":3,"area":null},{"id":"2404.13246","title":"ISQA: Informative Factuality Feedback for Scientific Summarization","created":"2024-04-20","cited_by_count":2,"area":null},{"id":"2410.06965","title":"Uncovering Factor Level Preferences to Improve Human-Model Alignment","created":"2024-10-09","cited_by_count":2,"area":"alignment"},{"id":"2410.15859","title":"Mesa-Extrapolation: A Weave Position Encoding Method for Enhanced Extrapolation in LLMs","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2411.15387","title":"From Jack of All Trades to Master of One: Specializing LLM-based Autoraters to a Test Set","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2412.02819","title":"CNNSum: Exploring Long-Context Summarization with Large Language Models in Chinese Novels","created":"2024-12-03","cited_by_count":2,"area":null},{"id":"2504.05317","title":"On Synthesizing Data for Context Attribution in Question Answering","created":"2025-02-21","cited_by_count":2,"area":"synth"},{"id":"2511.07689","title":"Stress Testing Factual Consistency Metrics for Long-Document Summarization","created":"2025-11-10","cited_by_count":2,"area":null},{"id":"2606.22748","title":"AI Fiction in the Wild","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2310.16197","title":"Background Summarization of Event Timelines","created":"2023-10-24","cited_by_count":1,"area":null},{"id":"2407.01158","title":"Learning to Explore and Select for Coverage-Conditioned Retrieval-Augmented Generation","created":"2024-07-01","cited_by_count":1,"area":"rag"},{"id":"2505.21859","title":"Principled Content Selection to Generate Diverse and Personalized Multi-Document Summaries","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2507.05965","title":"OpenFActScore: Open-Source Atomic Evaluation of Factuality in Text Generation","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2510.10415","title":"CQA-Eval: Designing Reliable Evaluations of Multi-paragraph Clinical QA under Resource Constraints","created":"2025-10-12","cited_by_count":1,"area":null},{"id":"2512.08082","title":"Short-Context Dominance: How Much Local Context Natural Language Actually Needs?","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2602.11238","title":"SurveyLens: A Discipline-Aware Benchmark for Automatic Survey Generation","created":"2026-02-11","cited_by_count":1,"area":"agents"},{"id":"2602.18448","title":"INSURE-Dial: A Phase-Aware Conversational Dataset & Benchmark for Compliance Verification and Phase Detection","created":"2026-01-28","cited_by_count":1,"area":null},{"id":"2504.01132","title":"Is the Top Still Spinning? Evaluating Subjectivity in Narrative Understanding","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2505.06594","title":"Integrating Video and Text: A Balanced Approach to Multimodal Summary Generation and Evaluation","created":"2025-05-10","cited_by_count":0,"area":"mllm"},{"id":"2607.14673","title":"Project Kaleidoscope: Contextual, Human-Aligned Evaluation for Real-World AI Applications","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2609.06320","title":"FrankenReport: Early Exiting in Long-Form Generation Using Expected Value of Computation","created":"2026-09-06","cited_by_count":0,"area":"inference"}],"next_cursor":null}