{"total":64,"rows":[{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326,"area":null},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780,"area":null},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075,"area":null},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843,"area":null},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295,"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":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235,"area":null},{"id":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161,"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":"2104.08835","title":"CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP","created":"2021-04-18","cited_by_count":142,"area":null},{"id":"2305.04320","title":"Unified Demonstration Retriever for In-Context Learning","created":"2023-05-07","cited_by_count":142,"area":null},{"id":"2210.17546","title":"Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy","created":"2022-10-31","cited_by_count":100,"area":null},{"id":"2405.14577","title":"Representation Noising: A Defence Mechanism Against Harmful Finetuning","created":"2024-05-23","cited_by_count":96,"area":"safety"},{"id":"2303.08518","title":"UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation","created":"2023-03-15","cited_by_count":75,"area":null},{"id":"2401.11624","title":"In-context Learning with Retrieved Demonstrations for Language Models: A Survey","created":"2024-01-21","cited_by_count":70,"area":null},{"id":"2312.17249","title":"Do Androids Know They're Only Dreaming of Electric Sheep?","created":"2023-12-28","cited_by_count":67,"area":"mechinterp"},{"id":"2310.07554","title":"A Multi-Task Embedder For Retrieval Augmented LLMs","created":"2023-10-11","cited_by_count":64,"area":"rag"},{"id":"2307.07164","title":"Learning to Retrieve In-Context Examples for Large Language Models","created":"2023-07-14","cited_by_count":60,"area":null},{"id":"2208.01448","title":"AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model","created":"2022-08-02","cited_by_count":57,"area":null},{"id":"2309.09530","title":"Adapting Large Language Models to Domains via Reading Comprehension","created":"2023-09-18","cited_by_count":50,"area":null},{"id":"2304.04052","title":"Decoder-Only or Encoder-Decoder? Interpreting Language Model as a Regularized Encoder-Decoder","created":"2023-04-08","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":"2206.11249","title":"GEMv2: Multilingual NLG Benchmarking in a Single Line of Code","created":"2022-06-22","cited_by_count":36,"area":null},{"id":"2401.06796","title":"AI Hallucinations: A Misnomer Worth Clarifying","created":"2024-01-09","cited_by_count":34,"area":null},{"id":"2204.10290","title":"Learning to Revise References for Faithful Summarization","created":"2022-04-13","cited_by_count":28,"area":null},{"id":"2110.07867","title":"Exploring Universal Intrinsic Task Subspace via Prompt Tuning","created":"2021-10-15","cited_by_count":25,"area":null},{"id":"2102.06749","title":"Structural Information Preserving for Graph-to-Text Generation","created":"2021-02-12","cited_by_count":24,"area":null},{"id":"2110.08329","title":"Control Prefixes for Parameter-Efficient Text Generation","created":"2021-10-15","cited_by_count":24,"area":null},{"id":"2108.01182","title":"Underreporting of errors in NLG output, and what to do about it","created":"2021-08-02","cited_by_count":19,"area":null},{"id":"2203.16279","title":"Neural Pipeline for Zero-Shot Data-to-Text Generation","created":"2022-03-30","cited_by_count":19,"area":null},{"id":"2106.09069","title":"Automatic Construction of Evaluation Suites for Natural Language Generation Datasets","created":"2021-06-16","cited_by_count":18,"area":null},{"id":"2305.13514","title":"Small Language Models Improve Giants by Rewriting Their Outputs","created":"2023-05-22","cited_by_count":18,"area":null},{"id":"2401.10186","title":"Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation","created":"2024-01-18","cited_by_count":16,"area":null},{"id":"2205.12701","title":"Eliciting and Understanding Cross-Task Skills with Task-Level Mixture-of-Experts","created":"2022-05-25","cited_by_count":12,"area":"moe"},{"id":"2212.10722","title":"Contrastive Error Attribution for Finetuned Language Models","created":"2022-12-21","cited_by_count":12,"area":null},{"id":"2302.08143","title":"Learning to Initialize: Can Meta Learning Improve Cross-task Generalization in Prompt Tuning?","created":"2023-02-16","cited_by_count":11,"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":"2403.06009","title":"Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations","created":"2024-03-09","cited_by_count":10,"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":"2205.11505","title":"What Makes Data-to-Text Generation Hard for Pretrained Language Models?","created":"2022-05-23","cited_by_count":8,"area":null},{"id":"2210.10599","title":"Self-supervised Graph Masking Pre-training for Graph-to-Text Generation","created":"2022-10-19","cited_by_count":8,"area":null},{"id":"2402.13874","title":"$Se^2$: Sequential Example Selection for In-Context Learning","created":"2024-02-21","cited_by_count":8,"area":null},{"id":"2106.05580","title":"AGGGEN: Ordering and Aggregating while Generating","created":"2021-06-10","cited_by_count":7,"area":null},{"id":"2302.14169","title":"TabGenie: A Toolkit for Table-to-Text Generation","created":"2023-02-27","cited_by_count":7,"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":"2503.18063","title":"Dynamic Task Vector Grouping for Efficient Multi-Task Prompt Tuning","created":"2025-03-23","cited_by_count":6,"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":"2312.17055","title":"Beyond Output Matching: Bidirectional Alignment for Enhanced In-Context Learning","created":"2023-12-28","cited_by_count":5,"area":null},{"id":"2502.13674","title":"SCOPE: A Self-supervised Framework for Improving Faithfulness in Conditional Text Generation","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2505.19966","title":"Learning to Select In-Context Demonstration Preferred by Large Language Model","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2112.05717","title":"Discourse-Aware Soft Prompting for Text Generation","created":"2021-12-10","cited_by_count":4,"area":null},{"id":"2307.14440","title":"Controllable Generation of Dialogue Acts for Dialogue Systems via Few-Shot Response Generation and Ranking","created":"2023-07-26","cited_by_count":4,"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":"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":"2302.11269","title":"Learning from Multiple Sources for Data-to-Text and Text-to-Data","created":"2023-02-22","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":"2606.11203","title":"LatticeBridge: Rare-Event Sequential Inference for Faithful Structured Sequence Synthesis","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2211.00513","title":"E2E Refined Dataset","created":"2022-11-01","cited_by_count":0,"area":null},{"id":"2608.29948","title":"XQDT: eXplainable and Quantitative Data-Text Alignment Metric with Feedback Signals","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2610.00833","title":"VERITYGATE: A Four-Gate Schema-Level Faithfulness Framework and Paired Benchmark for Grounded LLM Narrations over Structured Evidence","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}