{"total":108,"rows":[{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075,"area":null},{"id":"2101.06804","title":"What Makes Good In-Context Examples for GPT-$3$?","created":"2021-01-17","cited_by_count":1195,"area":null},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525,"area":null},{"id":"2303.04048","title":"Is ChatGPT a Good NLG Evaluator? A Preliminary Study","created":"2023-03-07","cited_by_count":422,"area":null},{"id":"2305.11747","title":"HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models","created":"2023-05-19","cited_by_count":341,"area":null},{"id":"2210.01241","title":"Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization","created":"2022-10-03","cited_by_count":246,"area":null},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239,"area":null},{"id":"2307.03987","title":"A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation","created":"2023-07-08","cited_by_count":206,"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":"2104.08704","title":"A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation","created":"2021-04-18","cited_by_count":138,"area":null},{"id":"2104.08455","title":"Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding","created":"2021-04-17","cited_by_count":106,"area":null},{"id":"2105.00071","title":"Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark","created":"2021-04-30","cited_by_count":77,"area":null},{"id":"2104.07606","title":"Planning with Learned Entity Prompts for Abstractive Summarization","created":"2021-04-15","cited_by_count":75,"area":null},{"id":"2208.11646","title":"Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation","created":"2022-08-24","cited_by_count":75,"area":null},{"id":"2306.00946","title":"Exposing Attention Glitches with Flip-Flop Language Modeling","created":"2023-06-01","cited_by_count":75,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2108.13740","title":"Plan-then-Generate: Controlled Data-to-Text Generation via Planning","created":"2021-08-31","cited_by_count":52,"area":null},{"id":"2109.05771","title":"Perturbation CheckLists for Evaluating NLG Evaluation Metrics","created":"2021-09-13","cited_by_count":50,"area":null},{"id":"2404.02904","title":"ALOHa: A New Measure for Hallucination in Captioning Models","created":"2024-04-03","cited_by_count":45,"area":null},{"id":"2407.04121","title":"Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models","created":"2024-07-04","cited_by_count":44,"area":null},{"id":"2102.02810","title":"Controlling Hallucinations at Word Level in Data-to-Text Generation","created":"2021-02-04","cited_by_count":41,"area":null},{"id":"2310.14564","title":"Language Models Hallucinate, but May Excel at Fact Verification","created":"2023-10-23","cited_by_count":37,"area":null},{"id":"2310.18362","title":"SoK: Memorization in General-Purpose Large Language Models","created":"2023-10-24","cited_by_count":37,"area":null},{"id":"2203.03131","title":"Input-Tuning: Adapting Unfamiliar Inputs to Frozen Pretrained Models","created":"2022-03-07","cited_by_count":34,"area":null},{"id":"2205.03972","title":"Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning","created":"2022-05-08","cited_by_count":32,"area":null},{"id":"2105.11921","title":"Focus Attention: Promoting Faithfulness and Diversity in Summarization","created":"2021-05-25","cited_by_count":30,"area":null},{"id":"2310.12086","title":"FactCHD: Benchmarking Fact-Conflicting Hallucination Detection","created":"2023-10-18","cited_by_count":29,"area":null},{"id":"2203.15108","title":"A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation","created":"2022-03-28","cited_by_count":28,"area":null},{"id":"2203.05227","title":"Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods","created":"2022-03-10","cited_by_count":27,"area":null},{"id":"2210.01877","title":"Towards Improving Faithfulness in Abstractive Summarization","created":"2022-10-04","cited_by_count":27,"area":null},{"id":"2102.08585","title":"Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View","created":"2021-02-17","cited_by_count":24,"area":null},{"id":"2104.07555","title":"Data-QuestEval: A Referenceless Metric for Data-to-Text Semantic Evaluation","created":"2021-04-15","cited_by_count":21,"area":null},{"id":"2105.14778","title":"Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation","created":"2021-05-31","cited_by_count":21,"area":null},{"id":"2205.14690","title":"CoNT: Contrastive Neural Text Generation","created":"2022-05-29","cited_by_count":21,"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":"2411.08516","title":"Tree-of-Table: Unleashing the Power of LLMs for Enhanced Large-Scale Table Understanding","created":"2024-11-13","cited_by_count":20,"area":null},{"id":"2111.06467","title":"SynthBio: A Case Study in Human-AI Collaborative Curation of Text Datasets","created":"2021-11-11","cited_by_count":18,"area":null},{"id":"2210.04325","title":"ASDOT: Any-Shot Data-to-Text Generation with Pretrained Language Models","created":"2022-10-09","cited_by_count":14,"area":null},{"id":"2404.04722","title":"PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamics","created":"2024-04-06","cited_by_count":14,"area":null},{"id":"2401.01183","title":"Unifying Structured Data as Graph for Data-to-Text Pre-Training","created":"2024-01-02","cited_by_count":13,"area":null},{"id":"2404.03745","title":"Fakes of Varying Shades: How Warning Affects Human Perception and Engagement Regarding LLM Hallucinations","created":"2024-04-04","cited_by_count":12,"area":null},{"id":"2105.08021","title":"Stage-wise Fine-tuning for Graph-to-Text Generation","created":"2021-05-17","cited_by_count":11,"area":null},{"id":"2110.01839","title":"Truth-Conditional Captioning of Time Series Data","created":"2021-10-05","cited_by_count":11,"area":null},{"id":"2203.06063","title":"Active Evaluation: Efficient NLG Evaluation with Few Pairwise Comparisons","created":"2022-03-11","cited_by_count":10,"area":null},{"id":"2207.12571","title":"Innovations in Neural Data-to-text Generation: A Survey","created":"2022-07-25","cited_by_count":10,"area":null},{"id":"2211.00142","title":"TaTa: A Multilingual Table-to-Text Dataset for African Languages","created":"2022-10-31","cited_by_count":10,"area":null},{"id":"2211.02162","title":"Time-aware Prompting for Text Generation","created":"2022-11-03","cited_by_count":10,"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":"2405.05109","title":"QFMTS: Generating Query-Focused Summaries over Multi-Table Inputs","created":"2024-05-08","cited_by_count":9,"area":null},{"id":"2406.04113","title":"Uncovering Limitations of Large Language Models in Information Seeking from Tables","created":"2024-06-06","cited_by_count":9,"area":null},{"id":"2112.02770","title":"Search and Learn: Improving Semantic Coverage for Data-to-Text Generation","created":"2021-12-06","cited_by_count":8,"area":null},{"id":"2205.12467","title":"R2D2: Robust Data-to-Text with Replacement Detection","created":"2022-05-25","cited_by_count":8,"area":null},{"id":"2304.11791","title":"Directed Acyclic Transformer Pre-training for High-quality Non-autoregressive Text Generation","created":"2023-04-24","cited_by_count":8,"area":null},{"id":"2108.08485","title":"Language Model Augmented Relevance Score","created":"2021-08-19","cited_by_count":7,"area":null},{"id":"2305.14793","title":"Faithful Low-Resource Data-to-Text Generation through Cycle Training","created":"2023-05-24","cited_by_count":7,"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":"2309.11049","title":"Localize, Retrieve and Fuse: A Generalized Framework for Free-Form Question Answering over Tables","created":"2023-09-20","cited_by_count":6,"area":null},{"id":"2311.09808","title":"PixT3: Pixel-based Table-To-Text Generation","created":"2023-11-16","cited_by_count":6,"area":null},{"id":"2504.12314","title":"How to Detect and Defeat Molecular Mirage: A Metric-Driven Benchmark for Hallucination in LLM-based Molecular Comprehension","created":"2025-04-10","cited_by_count":6,"area":null},{"id":"2203.00732","title":"Attend, Memorize and Generate: Towards Faithful Table-to-Text Generation in Few Shots","created":"2022-03-01","cited_by_count":5,"area":null},{"id":"2306.07554","title":"HAUSER: Towards Holistic and Automatic Evaluation of Simile Generation","created":"2023-06-13","cited_by_count":5,"area":null},{"id":"2310.18794","title":"Sequence-Level Certainty Reduces Hallucination In Knowledge-Grounded Dialogue Generation","created":"2023-10-28","cited_by_count":5,"area":null},{"id":"2403.16347","title":"ChatGPT Incorrectness Detection in Software Reviews","created":"2024-03-25","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":"2101.08248","title":"Data-to-text Generation by Splicing Together Nearest Neighbors","created":"2021-01-20","cited_by_count":4,"area":null},{"id":"2306.00947","title":"EEL: Efficiently Encoding Lattices for Reranking","created":"2023-06-01","cited_by_count":4,"area":null},{"id":"2310.08764","title":"Calibrating Likelihoods towards Consistency in Summarization Models","created":"2023-10-12","cited_by_count":4,"area":null},{"id":"2310.16176","title":"Correction with Backtracking Reduces Hallucination in Summarization","created":"2023-10-24","cited_by_count":4,"area":null},{"id":"2310.20072","title":"Automatic Evaluation of Generative Models with Instruction Tuning","created":"2023-10-30","cited_by_count":4,"area":null},{"id":"2402.08496","title":"A Systematic Review of Data-to-Text NLG","created":"2024-02-13","cited_by_count":4,"area":null},{"id":"2205.06733","title":"Arithmetic-Based Pretraining -- Improving Numeracy of Pretrained Language Models","created":"2022-05-13","cited_by_count":3,"area":null},{"id":"2208.10709","title":"Few-Shot Table-to-Text Generation with Prefix-Controlled Generator","created":"2022-08-23","cited_by_count":3,"area":null},{"id":"2210.12367","title":"Precisely the Point: Adversarial Augmentations for Faithful and Informative Text Generation","created":"2022-10-22","cited_by_count":3,"area":null},{"id":"2212.01956","title":"Grounded Keys-to-Text Generation: Towards Factual Open-Ended Generation","created":"2022-12-04","cited_by_count":3,"area":null},{"id":"2305.11826","title":"ReTAG: Reasoning Aware Table to Analytic Text Generation","created":"2023-05-19","cited_by_count":3,"area":null},{"id":"2404.04103","title":"Improving Factual Accuracy of Neural Table-to-Text Output by Addressing Input Problems in ToTTo","created":"2024-04-05","cited_by_count":3,"area":null},{"id":"2405.10650","title":"SPOR: A Comprehensive and Practical Evaluation Method for Compositional Generalization in Data-to-Text Generation","created":"2024-05-17","cited_by_count":3,"area":null},{"id":"2109.10650","title":"MiRANews: Dataset and Benchmarks for Multi-Resource-Assisted News Summarization","created":"2021-09-22","cited_by_count":2,"area":null},{"id":"2209.07258","title":"Graph-to-Text Generation with Dynamic Structure Pruning","created":"2022-09-15","cited_by_count":2,"area":null},{"id":"2302.04415","title":"Few-Shot Table-to-Text Generation with Prompt Planning and Knowledge Memorization","created":"2023-02-09","cited_by_count":2,"area":null},{"id":"2302.05138","title":"Plan-then-Seam: Towards Efficient Table-to-Text Generation","created":"2023-02-10","cited_by_count":2,"area":null},{"id":"2302.12468","title":"Adapting Knowledge for Few-shot Table-to-Text Generation","created":"2023-02-24","cited_by_count":2,"area":null},{"id":"2308.05317","title":"Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning","created":"2023-08-10","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":"2407.13702","title":"ANHALTEN: Cross-Lingual Transfer for German Token-Level Reference-Free Hallucination Detection","created":"2024-07-18","cited_by_count":2,"area":null},{"id":"2411.19203","title":"An Extensive Evaluation of Factual Consistency in Large Language Models for Data-to-Text Generation","created":"2024-11-28","cited_by_count":2,"area":null},{"id":"2505.22176","title":"TabXEval: Why this is a Bad Table? An eXhaustive Rubric for Table Evaluation","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2209.11252","title":"XF2T: Cross-lingual Fact-to-Text Generation for Low-Resource Languages","created":"2022-09-22","cited_by_count":1,"area":null},{"id":"2212.14486","title":"Examining Political Rhetoric with Epistemic Stance Detection","created":"2022-12-29","cited_by_count":1,"area":null},{"id":"2303.12308","title":"XWikiGen: Cross-lingual Summarization for Encyclopedic Text Generation in Low Resource Languages","created":"2023-03-22","cited_by_count":1,"area":null},{"id":"2307.00470","title":"PatternGPT :A Pattern-Driven Framework for Large Language Model Text Generation","created":"2023-07-02","cited_by_count":1,"area":null},{"id":"2312.02748","title":"Compositional Generalization for Data-to-Text Generation","created":"2023-12-05","cited_by_count":1,"area":null},{"id":"2406.10560","title":"Facts-and-Feelings: Capturing both Objectivity and Subjectivity in Table-to-Text Generation","created":"2024-06-15","cited_by_count":1,"area":null},{"id":"2407.14088","title":"Impact of Model Size on Fine-tuned LLM Performance in Data-to-Text Generation: A State-of-the-Art Investigation","created":"2024-07-19","cited_by_count":1,"area":null},{"id":"2411.11344","title":"Mitigating Knowledge Conflicts in Language Model-Driven Question Answering","created":"2024-11-18","cited_by_count":1,"area":null},{"id":"2412.13484","title":"Curriculum Learning for Cross-Lingual Data-to-Text Generation With Noisy Data","created":"2024-12-18","cited_by_count":1,"area":null},{"id":"2606.09376","title":"Precision Is Not Faithfulness: Coverage-Aware Evaluation of Grounded Generation with a Complete Oracle","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2208.04558","title":"High Recall Data-to-text Generation with Progressive Edit","created":"2022-08-09","cited_by_count":0,"area":null},{"id":"2409.16707","title":"Probing Omissions and Distortions in Transformer-based RDF-to-Text Models","created":"2024-09-25","cited_by_count":0,"area":null},{"id":"2503.05935","title":"DETQUS: Decomposition-Enhanced Transformers for QUery-focused Summarization","created":"2025-03-07","cited_by_count":0,"area":null}],"next_cursor":"100"}