{"list":"other","total":67,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"id":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"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":"2212.10511","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","created":"2022-12-20","cited_by_count":1128},{"id":"2009.09025","title":"COMET: A Neural Framework for MT Evaluation","created":"2020-09-18","cited_by_count":1033},{"id":"1708.00055","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","created":"2017-07-31","cited_by_count":1001},{"id":"2005.00661","title":"On Faithfulness and Factuality in Abstractive Summarization","created":"2020-05-02","cited_by_count":900},{"id":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"id":"2305.11738","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","created":"2023-05-19","cited_by_count":783},{"id":"2007.12626","title":"SummEval: Re-evaluating Summarization Evaluation","created":"2020-07-24","cited_by_count":674},{"id":"1910.12840","title":"Evaluating the Factual Consistency of Abstractive Text Summarization","created":"2019-10-28","cited_by_count":584},{"id":"1909.02622","title":"MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance","created":"2019-09-05","cited_by_count":418},{"id":"2111.09525","title":"SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization","created":"2021-11-18","cited_by_count":407},{"id":"2004.10645","title":"AmbigQA: Answering Ambiguous Open-domain Questions","created":"2020-04-22","cited_by_count":390},{"id":"2004.04228","title":"Asking and Answering Questions to Evaluate the Factual Consistency of Summaries","created":"2020-04-08","cited_by_count":378},{"id":"2005.03754","title":"FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization","created":"2020-05-07","cited_by_count":293},{"id":"2104.13346","title":"Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics","created":"2021-04-27","cited_by_count":287},{"id":"2112.10668","title":"Few-shot Learning with Multilingual Language Models","created":"2021-12-20","cited_by_count":278},{"id":"2004.14373","title":"ToTTo: A Controlled Table-To-Text Generation Dataset","created":"2020-04-29","cited_by_count":268},{"id":"2210.07197","title":"Towards a Unified Multi-Dimensional Evaluator for Text Generation","created":"2022-10-13","cited_by_count":264},{"id":"2103.12693","title":"QuestEval: Summarization Asks for Fact-based Evaluation","created":"2021-03-23","cited_by_count":244},{"id":"2206.04624","title":"Factuality Enhanced Language Models for Open-Ended Text Generation","created":"2022-06-09","cited_by_count":202},{"id":"2105.08209","title":"BookSum: A Collection of Datasets for Long-form Narrative Summarization","created":"2021-05-18","cited_by_count":184},{"id":"2107.10821","title":"To Ship or Not to Ship: An Extensive Evaluation of Automatic Metrics for Machine Translation","created":"2021-07-22","cited_by_count":163},{"id":"2304.04675","title":"Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis","created":"2023-04-10","cited_by_count":160},{"id":"2307.16877","title":"Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering","created":"2023-07-31","cited_by_count":151},{"id":"2303.03915","title":"The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset","created":"2023-03-07","cited_by_count":148},{"id":"2204.08582","title":"MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages","created":"2022-04-18","cited_by_count":146},{"id":"2104.05596","title":"Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages","created":"2021-04-12","cited_by_count":136},{"id":"1811.00671","title":"Dialogue Natural Language Inference","created":"2018-11-01","cited_by_count":135},{"id":"2104.08202","title":"$Q^{2}$: Evaluating Factual Consistency in Knowledge-Grounded Dialogues via Question Generation and Question Answering","created":"2021-04-16","cited_by_count":132},{"id":"2102.09130","title":"Entity-level Factual Consistency of Abstractive Text Summarization","created":"2021-02-18","cited_by_count":118},{"id":"2305.06984","title":"Evaluating Open-Domain Question Answering in the Era of Large Language Models","created":"2023-05-11","cited_by_count":111},{"id":"1905.13322","title":"Assessing The Factual Accuracy of Generated Text","created":"2019-05-30","cited_by_count":103},{"id":"2309.07852","title":"ExpertQA: Expert-Curated Questions and Attributed Answers","created":"2023-09-14","cited_by_count":97},{"id":"2301.13298","title":"LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization","created":"2023-01-30","cited_by_count":96},{"id":"2106.15195","title":"Scientific Credibility of Machine Translation Research: A Meta-Evaluation of 769 Papers","created":"2021-06-29","cited_by_count":71},{"id":"2404.01261","title":"FABLES: Evaluating faithfulness and content selection in book-length summarization","created":"2024-04-01","cited_by_count":65},{"id":"2011.01536","title":"TransQuest: Translation Quality Estimation with Cross-lingual Transformers","created":"2020-11-01","cited_by_count":59},{"id":"2305.06590","title":"FactKG: Fact Verification via Reasoning on Knowledge Graphs","created":"2023-05-11","cited_by_count":57},{"id":"2205.11465","title":"SQuALITY: Building a Long-Document Summarization Dataset the Hard Way","created":"2022-05-23","cited_by_count":50},{"id":"2204.06508","title":"FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations","created":"2022-04-13","cited_by_count":41},{"id":"2405.11029","title":"Generative Artificial Intelligence: A Systematic Review and Applications","created":"2024-05-17","cited_by_count":37},{"id":"2305.12421","title":"Evaluating Open-QA Evaluation","created":"2023-05-21","cited_by_count":35},{"id":"2112.07924","title":"Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation","created":"2021-12-15","cited_by_count":32},{"id":"1907.12895","title":"MaSS: A Large and Clean Multilingual Corpus of Sentence-aligned Spoken Utterances Extracted from the Bible","created":"2019-07-30","cited_by_count":24},{"id":"2311.00681","title":"Are Large Language Models Reliable Judges? A Study on the Factuality Evaluation Capabilities of LLMs","created":"2023-11-01","cited_by_count":24},{"id":"2210.05035","title":"Not All Errors are Equal: Learning Text Generation Metrics using Stratified Error Synthesis","created":"2022-10-10","cited_by_count":18},{"id":"2406.03339","title":"The Challenges of Evaluating LLM Applications: An Analysis of Automated, Human, and LLM-Based Approaches","created":"2024-06-05","cited_by_count":18},{"id":"1309.5226","title":"DGT-TM: A freely Available Translation Memory in 22 Languages","created":"2013-09-20","cited_by_count":16},{"id":"2211.09039","title":"UniRel: Unified Representation and Interaction for Joint Relational Triple Extraction","created":"2022-11-16","cited_by_count":14},{"id":"2403.00998","title":"Predictions from language models for multiple-choice tasks are not robust under variation of scoring methods","created":"2024-03-01","cited_by_count":13},{"id":"2405.16702","title":"Accurate and Nuanced Open-QA Evaluation Through Textual Entailment","created":"2024-05-26","cited_by_count":13},{"id":"2210.11777","title":"Analyzing and Evaluating Faithfulness in Dialogue Summarization","created":"2022-10-21","cited_by_count":12},{"id":"2311.07878","title":"Evaluating LLMs on Document-Based QA: Exact Answer Selection and Numerical Extraction using Cogtale dataset","created":"2023-11-14","cited_by_count":11},{"id":"2406.06458","title":"Evaluating the Retrieval Component in LLM-Based Question Answering Systems","created":"2024-06-10","cited_by_count":11},{"id":"2406.09972","title":"A Better LLM Evaluator for Text Generation: The Impact of Prompt Output Sequencing and Optimization","created":"2024-06-14","cited_by_count":11},{"id":"2407.06501","title":"STORYSUMM: Evaluating Faithfulness in Story Summarization","created":"2024-07-09","cited_by_count":9},{"id":"2409.15861","title":"A Zero-Shot Open-Vocabulary Pipeline for Dialogue Understanding","created":"2024-09-24","cited_by_count":2}],"next_cursor":null}