{"total":30,"rows":[{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424,"area":null},{"id":"2202.06935","title":"Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text","created":"2022-02-14","cited_by_count":155,"area":null},{"id":"2304.06815","title":"Automatic Semantic Augmentation of Language Model Prompts (for Code Summarization)","created":"2023-04-13","cited_by_count":72,"area":null},{"id":"2310.12971","title":"CLAIR: Evaluating Image Captions with Large Language Models","created":"2023-10-19","cited_by_count":43,"area":null},{"id":"2301.03797","title":"Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models","created":"2023-01-10","cited_by_count":38,"area":null},{"id":"2205.13445","title":"Mutual Information Divergence: A Unified Metric for Multimodal Generative Models","created":"2022-05-25","cited_by_count":35,"area":null},{"id":"2404.14412","title":"AutoAD III: The Prequel -- Back to the Pixels","created":"2024-04-22","cited_by_count":35,"area":null},{"id":"2401.13810","title":"Automated Root Causing of Cloud Incidents using In-Context Learning with GPT-4","created":"2024-01-24","cited_by_count":28,"area":null},{"id":"2210.12814","title":"RuCoLA: Russian Corpus of Linguistic Acceptability","created":"2022-10-23","cited_by_count":26,"area":null},{"id":"2209.04889","title":"Chain of Explanation: New Prompting Method to Generate Higher Quality Natural Language Explanation for Implicit Hate Speech","created":"2022-09-11","cited_by_count":25,"area":null},{"id":"2412.09582","title":"Neptune: The Long Orbit to Benchmarking Long Video Understanding","created":"2024-12-12","cited_by_count":25,"area":null},{"id":"2412.19823","title":"A Survey on Large Language Models for Communication, Network, and Service Management: Application Insights, Challenges, and Future Directions","created":"2024-12-16","cited_by_count":25,"area":null},{"id":"2408.09169","title":"Automatic Metrics in Natural Language Generation: A Survey of Current Evaluation Practices","created":"2024-08-17","cited_by_count":20,"area":null},{"id":"2110.08559","title":"FrugalScore: Learning Cheaper, Lighter and Faster Evaluation Metricsfor Automatic Text Generation","created":"2021-10-16","cited_by_count":19,"area":null},{"id":"2404.03662","title":"X-lifecycle Learning for Cloud Incident Management using LLMs","created":"2024-02-15","cited_by_count":19,"area":null},{"id":"2106.01444","title":"SMURF: SeMantic and linguistic UndeRstanding Fusion for Caption Evaluation via Typicality Analysis","created":"2021-06-02","cited_by_count":18,"area":null},{"id":"2411.05375","title":"Ev2R: Evaluating Evidence Retrieval in Automated Fact-Checking","created":"2024-11-08","cited_by_count":18,"area":null},{"id":"2203.08259","title":"Better Quality Estimation for Low Resource Corpus Mining","created":"2022-03-15","cited_by_count":8,"area":null},{"id":"2110.09147","title":"BEAMetrics: A Benchmark for Language Generation Evaluation Evaluation","created":"2021-10-18","cited_by_count":6,"area":null},{"id":"2210.07373","title":"Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models","created":"2022-10-13","cited_by_count":6,"area":null},{"id":"2308.00399","title":"Tackling Hallucinations in Neural Chart Summarization","created":"2023-08-01","cited_by_count":6,"area":null},{"id":"2409.18170","title":"Evaluation of Large Language Models for Summarization Tasks in the Medical Domain: A Narrative Review","created":"2024-09-26","cited_by_count":3,"area":null},{"id":"2504.02118","title":"LLMPi: Optimizing LLMs for High-Throughput on Raspberry Pi","created":"2025-04-02","cited_by_count":3,"area":null},{"id":"2204.13848","title":"Repro: An Open-Source Library for Improving the Reproducibility and Usability of Publicly Available Research Code","created":"2022-04-29","cited_by_count":2,"area":null},{"id":"2304.13191","title":"Towards Explainable and Safe Conversational Agents for Mental Health: A Survey","created":"2023-04-25","cited_by_count":2,"area":null},{"id":"2310.17877","title":"ASPIRO: Any-shot Structured Parsing-error-Induced ReprOmpting for Consistent Data-to-Text Generation","created":"2023-10-27","cited_by_count":2,"area":null},{"id":"2408.04909","title":"Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy, Trends and Metrics Analysis","created":"2024-08-09","cited_by_count":1,"area":null},{"id":"2503.12556","title":"From Guessing to Asking: An Approach to Resolving the Persona Knowledge Gap in LLMs during Multi-Turn Conversations","created":"2025-03-16","cited_by_count":1,"area":null},{"id":"2108.12026","title":"Semantic-Based Self-Critical Training For Question Generation","created":"2021-08-26","cited_by_count":0,"area":null},{"id":"2406.15066","title":"Cross-lingual paraphrase identification","created":"2024-06-21","cited_by_count":0,"area":null}],"next_cursor":null}