{"total":102,"rows":[{"id":"2104.08758","title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus","created":"2021-04-18","cited_by_count":492,"area":null},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478,"area":"wm"},{"id":"2403.12968","title":"LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression","created":"2024-03-19","cited_by_count":348,"area":"inference"},{"id":"2209.15558","title":"Out-of-Distribution Detection and Selective Generation for Conditional Language Models","created":"2022-09-30","cited_by_count":197,"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":"2201.07520","title":"CM3: A Causal Masked Multimodal Model of the Internet","created":"2022-01-19","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":"2210.00045","title":"Calibrating Sequence likelihood Improves Conditional Language Generation","created":"2022-09-30","cited_by_count":121,"area":null},{"id":"2207.00939","title":"An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics","created":"2022-07-03","cited_by_count":74,"area":null},{"id":"2112.12777","title":"Cross Modal Retrieval with Querybank Normalisation","created":"2021-12-23","cited_by_count":72,"area":null},{"id":"2203.06569","title":"SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization","created":"2022-03-13","cited_by_count":61,"area":"moe"},{"id":"2304.04193","title":"Extractive Summarization via ChatGPT for Faithful Summary Generation","created":"2023-04-09","cited_by_count":59,"area":null},{"id":"2107.06955","title":"HTLM: Hyper-Text Pre-Training and Prompting of Language Models","created":"2021-07-14","cited_by_count":58,"area":null},{"id":"2406.11289","title":"A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models","created":"2024-06-17","cited_by_count":52,"area":null},{"id":"2103.11332","title":"AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization","created":"2021-03-21","cited_by_count":51,"area":null},{"id":"2308.07968","title":"Teach LLMs to Personalize -- An Approach inspired by Writing Education","created":"2023-08-15","cited_by_count":48,"area":null},{"id":"2401.08295","title":"SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models","created":"2024-01-16","cited_by_count":38,"area":null},{"id":"2203.01670","title":"A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation","created":"2022-03-03","cited_by_count":32,"area":"inference"},{"id":"2105.11921","title":"Focus Attention: Promoting Faithfulness and Diversity in Summarization","created":"2021-05-25","cited_by_count":30,"area":null},{"id":"2303.03919","title":"Data Portraits: Recording Foundation Model Training Data","created":"2023-03-06","cited_by_count":30,"area":null},{"id":"2310.10570","title":"On Context Utilization in Summarization with Large Language Models","created":"2023-10-16","cited_by_count":30,"area":null},{"id":"2208.09770","title":"Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization","created":"2022-08-21","cited_by_count":29,"area":null},{"id":"2401.01989","title":"Revisiting Zero-Shot Abstractive Summarization in the Era of Large Language Models from the Perspective of Position Bias","created":"2024-01-03","cited_by_count":28,"area":null},{"id":"2407.08188","title":"Position: Measure Dataset Diversity, Don't Just Claim It","created":"2024-07-11","cited_by_count":26,"area":null},{"id":"2210.16732","title":"How Far are We from Robust Long Abstractive Summarization?","created":"2022-10-30","cited_by_count":25,"area":null},{"id":"2304.08653","title":"On Uncertainty Calibration and Selective Generation in Probabilistic Neural Summarization: A Benchmark Study","created":"2023-04-17","cited_by_count":25,"area":null},{"id":"2102.06272","title":"Unsupervised Extractive Summarization using Pointwise Mutual Information","created":"2021-02-11","cited_by_count":23,"area":null},{"id":"2101.06561","title":"GENIE: Toward Reproducible and Standardized Human Evaluation for Text Generation","created":"2021-01-17","cited_by_count":20,"area":null},{"id":"2109.10616","title":"Enriching and Controlling Global Semantics for Text Summarization","created":"2021-09-22","cited_by_count":20,"area":null},{"id":"2403.05303","title":"ACLSum: A New Dataset for Aspect-based Summarization of Scientific Publications","created":"2024-03-08","cited_by_count":20,"area":null},{"id":"2407.21530","title":"Data Contamination Report from the 2024 CONDA Shared Task","created":"2024-07-31","cited_by_count":20,"area":null},{"id":"2109.07943","title":"RetrievalSum: A Retrieval Enhanced Framework for Abstractive Summarization","created":"2021-09-16","cited_by_count":19,"area":null},{"id":"2107.03448","title":"Can Transformer Models Measure Coherence In Text? Re-Thinking the Shuffle Test","created":"2021-07-07","cited_by_count":17,"area":null},{"id":"2106.11388","title":"How well do you know your summarization datasets?","created":"2021-06-21","cited_by_count":16,"area":null},{"id":"2211.09783","title":"UniSumm and SummZoo: Unified Model and Diverse Benchmark for Few-Shot Summarization","created":"2022-11-17","cited_by_count":15,"area":null},{"id":"2502.02787","title":"SimMark: A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Models","created":"2025-02-05","cited_by_count":15,"area":"safety"},{"id":"2102.09397","title":"Meta-Transfer Learning for Low-Resource Abstractive Summarization","created":"2021-02-18","cited_by_count":14,"area":null},{"id":"2204.05512","title":"Make The Most of Prior Data: A Solution for Interactive Text Summarization with Preference Feedback","created":"2022-04-12","cited_by_count":13,"area":"alignment"},{"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":"2206.00856","title":"MentSum: A Resource for Exploring Summarization of Mental Health Online Posts","created":"2022-06-02","cited_by_count":11,"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":"2406.03993","title":"Assessing LLMs for Zero-shot Abstractive Summarization Through the Lens of Relevance Paraphrasing","created":"2024-06-06","cited_by_count":11,"area":null},{"id":"2110.01159","title":"TLDR9+: A Large Scale Resource for Extreme Summarization of Social Media Posts","created":"2021-10-04","cited_by_count":10,"area":null},{"id":"2210.13449","title":"Controlled Text Reduction","created":"2022-10-24","cited_by_count":10,"area":null},{"id":"2402.08644","title":"Tandem Transformers for Inference Efficient LLMs","created":"2024-02-13","cited_by_count":10,"area":"inference"},{"id":"2402.12566","title":"GenAudit: Fixing Factual Errors in Language Model Outputs with Evidence","created":"2024-02-19","cited_by_count":10,"area":null},{"id":"2208.04083","title":"Template-based Abstractive Microblog Opinion Summarisation","created":"2022-08-08","cited_by_count":9,"area":null},{"id":"2305.13083","title":"InheritSumm: A General, Versatile and Compact Summarizer by Distilling from GPT","created":"2023-05-22","cited_by_count":9,"area":null},{"id":"2408.12494","title":"GenderCARE: A Comprehensive Framework for Assessing and Reducing Gender Bias in Large Language Models","created":"2024-08-22","cited_by_count":9,"area":null},{"id":"2209.14569","title":"COLO: A Contrastive Learning based Re-ranking Framework for One-Stage Summarization","created":"2022-09-29","cited_by_count":8,"area":null},{"id":"2210.08779","title":"Towards Summary Candidates Fusion","created":"2022-10-17","cited_by_count":8,"area":null},{"id":"2404.07546","title":"Does In-Context Learning Really Learn? Rethinking How Large Language Models Respond and Solve Tasks via In-Context Learning","created":"2024-04-11","cited_by_count":8,"area":"lr"},{"id":"2505.23816","title":"A Course Correction in Steerability Evaluation: Revealing Miscalibration and Side Effects in LLMs","created":"2025-05-27","cited_by_count":7,"area":"lr"},{"id":"2509.23387","title":"No Loss, No Gain: Gated Refinement and Adaptive Compression for Prompt Optimization","created":"2025-09-27","cited_by_count":7,"area":null},{"id":"2202.07146","title":"NewsPod: Automatic and Interactive News Podcasts","created":"2022-02-15","cited_by_count":6,"area":null},{"id":"2301.00867","title":"Follow the Timeline! Generating Abstractive and Extractive Timeline Summary in Chronological Order","created":"2023-01-02","cited_by_count":6,"area":null},{"id":"2403.13780","title":"Information-Theoretic Distillation for Reference-less Summarization","created":"2024-03-20","cited_by_count":6,"area":null},{"id":"2505.15291","title":"Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization","created":"2025-05-21","cited_by_count":6,"area":null},{"id":"2506.06616","title":"Interpretable Depression Detection from Social Media Text Using LLM-Derived Embeddings","created":"2025-06-07","cited_by_count":6,"area":null},{"id":"2210.12531","title":"Why Do You Feel This Way? Summarizing Triggers of Emotions in Social Media Posts","created":"2022-10-22","cited_by_count":5,"area":null},{"id":"2212.01476","title":"NarraSum: A Large-Scale Dataset for Abstractive Narrative Summarization","created":"2022-12-02","cited_by_count":5,"area":null},{"id":"2305.14296","title":"USB: A Unified Summarization Benchmark Across Tasks and Domains","created":"2023-05-23","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":"2210.04029","title":"EDU-level Extractive Summarization with Varying Summary Lengths","created":"2022-10-08","cited_by_count":4,"area":null},{"id":"2212.09928","title":"Improving the Robustness of Summarization Models by Detecting and Removing Input Noise","created":"2022-12-20","cited_by_count":4,"area":null},{"id":"2301.03403","title":"A comprehensive review of automatic text summarization techniques: method, data, evaluation and coding","created":"2023-01-04","cited_by_count":4,"area":null},{"id":"2302.04054","title":"Towards Inferential Reproducibility of Machine Learning Research","created":"2023-02-08","cited_by_count":4,"area":null},{"id":"2310.08122","title":"Core-sets for Fair and Diverse Data Summarization","created":"2023-10-12","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":"2405.01790","title":"Understanding Position Bias Effects on Fairness in Social Multi-Document Summarization","created":"2024-05-03","cited_by_count":4,"area":null},{"id":"2410.15687","title":"DomainSum: A Hierarchical Benchmark for Fine-Grained Domain Shift in Abstractive Text Summarization","created":"2024-10-21","cited_by_count":4,"area":null},{"id":"2506.00637","title":"Improving the Calibration of Confidence Scores in Text Generation Using the Output Distribution's Characteristics","created":"2025-05-31","cited_by_count":4,"area":null},{"id":"2206.06383","title":"An Exploration of Post-Editing Effectiveness in Text Summarization","created":"2022-06-13","cited_by_count":3,"area":null},{"id":"2210.14606","title":"Analyzing Multi-Task Learning for Abstractive Text Summarization","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2411.04585","title":"The State and Fate of Summarization Datasets: A Survey","created":"2024-11-07","cited_by_count":3,"area":null},{"id":"2503.00867","title":"DUAL: Diversity and Uncertainty Active Learning for Text Summarization","created":"2025-03-02","cited_by_count":3,"area":null},{"id":"2109.14199","title":"Who speaks like a style of Vitamin: Towards Syntax-Aware DialogueSummarization using Multi-task Learning","created":"2021-09-29","cited_by_count":2,"area":null},{"id":"2305.06647","title":"PROM: A Phrase-level Copying Mechanism with Pre-training for Abstractive Summarization","created":"2023-05-11","cited_by_count":2,"area":null},{"id":"2306.11256","title":"GUMSum: Multi-Genre Data and Evaluation for English Abstractive Summarization","created":"2023-06-20","cited_by_count":2,"area":null},{"id":"2401.05883","title":"Generative Deduplication For Socia Media Data Selection","created":"2024-01-11","cited_by_count":2,"area":null},{"id":"2408.13959","title":"Bidirectional Awareness Induction in Autoregressive Seq2Seq Models","created":"2024-08-25","cited_by_count":2,"area":null},{"id":"2106.03953","title":"Neural Abstractive Unsupervised Summarization of Online News Discussions","created":"2021-06-07","cited_by_count":1,"area":null},{"id":"2206.10265","title":"KnowDA: All-in-One Knowledge Mixture Model for Data Augmentation in Low-Resource NLP","created":"2022-06-21","cited_by_count":1,"area":null},{"id":"2209.12714","title":"Text Summarization with Oracle Expectation","created":"2022-09-26","cited_by_count":1,"area":null},{"id":"2212.08775","title":"RISE: Leveraging Retrieval Techniques for Summarization Evaluation","created":"2022-12-17","cited_by_count":1,"area":null},{"id":"2303.14011","title":"SPEC: Summary Preference Decomposition for Low-Resource Abstractive Summarization","created":"2023-03-24","cited_by_count":1,"area":null},{"id":"2305.16820","title":"Domain Aligned Prefix Averaging for Domain Generalization in Abstractive Summarization","created":"2023-05-26","cited_by_count":1,"area":null},{"id":"2307.00135","title":"SMILE: Evaluation and Domain Adaptation for Social Media Language Understanding","created":"2023-06-30","cited_by_count":1,"area":null},{"id":"2507.00026","title":"RedTopic: Toward Topic-Diverse Red Teaming of Large Language Models","created":"2025-06-17","cited_by_count":1,"area":"safety"},{"id":"2602.06031","title":"AP-OOD: Attention Pooling for Out-of-Distribution Detection","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2204.09716","title":"Domain Specific Fine-tuning of Denoising Sequence-to-Sequence Models for Natural Language Summarization","created":"2022-04-06","cited_by_count":0,"area":null},{"id":"2302.01342","title":"Curriculum-Guided Abstractive Summarization","created":"2023-02-02","cited_by_count":0,"area":null},{"id":"2305.11231","title":"Recent Trends in Unsupervised Summarization","created":"2023-05-18","cited_by_count":0,"area":null},{"id":"2305.15138","title":"Topic-Guided Self-Introduction Generation for Social Media Users","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2306.10555","title":"Summarization from Leaderboards to Practice: Choosing A Representation Backbone and Ensuring Robustness","created":"2023-06-18","cited_by_count":0,"area":null},{"id":"2406.05361","title":"Write Summary Step-by-Step: A Pilot Study of Stepwise Summarization","created":"2024-06-08","cited_by_count":0,"area":null},{"id":"2408.07505","title":"Large Language Models Know What Makes Exemplary Contexts","created":"2024-08-14","cited_by_count":0,"area":null},{"id":"2409.11827","title":"Extract-and-Abstract: Unifying Extractive and Abstractive Summarization within Single Encoder-Decoder Framework","created":"2024-09-18","cited_by_count":0,"area":null},{"id":"2410.01183","title":"FastLexRank: Efficient Lexical Ranking for Structuring Social Media Posts","created":"2024-10-02","cited_by_count":0,"area":null},{"id":"2508.05469","title":"Let's Measure Information Step-by-Step: AI-Based Evaluation Beyond Vibes","created":"2025-08-07","cited_by_count":0,"area":null}],"next_cursor":"100"}