{"total":72,"rows":[{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525,"area":null},{"id":"2201.05955","title":"WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation","created":"2022-01-16","cited_by_count":202,"area":null},{"id":"2406.04127","title":"Are We Done with MMLU?","created":"2024-06-06","cited_by_count":194,"area":null},{"id":"2202.07206","title":"Impact of Pretraining Term Frequencies on Few-Shot Reasoning","created":"2022-02-15","cited_by_count":142,"area":"lr"},{"id":"2201.05320","title":"CommonsenseQA 2.0: Exposing the Limits of AI through Gamification","created":"2022-01-14","cited_by_count":109,"area":null},{"id":"2104.08646","title":"Competency Problems: On Finding and Removing Artifacts in Language Data","created":"2021-04-17","cited_by_count":91,"area":null},{"id":"2402.16842","title":"Asymmetry in Low-Rank Adapters of Foundation Models","created":"2024-02-26","cited_by_count":86,"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":"2310.01382","title":"Compressing LLMs: The Truth is Rarely Pure and Never Simple","created":"2023-10-02","cited_by_count":62,"area":null},{"id":"2203.12942","title":"Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets","created":"2022-03-24","cited_by_count":54,"area":null},{"id":"2106.01024","title":"Why Machine Reading Comprehension Models Learn Shortcuts?","created":"2021-06-02","cited_by_count":40,"area":null},{"id":"2112.09062","title":"Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistants","created":"2021-12-16","cited_by_count":31,"area":null},{"id":"2305.04990","title":"Explanation-based Finetuning Makes Models More Robust to Spurious Cues","created":"2023-05-08","cited_by_count":25,"area":null},{"id":"2407.11239","title":"From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications","created":"2024-07-15","cited_by_count":25,"area":null},{"id":"2404.03865","title":"FFN-SkipLLM: A Hidden Gem for Autoregressive Decoding with Adaptive Feed Forward Skipping","created":"2024-04-05","cited_by_count":23,"area":"inference"},{"id":"2202.07280","title":"Saving Dense Retriever from Shortcut Dependency in Conversational Search","created":"2022-02-15","cited_by_count":19,"area":null},{"id":"2110.08555","title":"On the Robustness of Reading Comprehension Models to Entity Renaming","created":"2021-10-16","cited_by_count":17,"area":null},{"id":"2204.07721","title":"TVShowGuess: Character Comprehension in Stories as Speaker Guessing","created":"2022-04-16","cited_by_count":17,"area":null},{"id":"2102.11903","title":"Neural ranking models for document retrieval","created":"2021-02-23","cited_by_count":16,"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":"2209.07430","title":"Machine Reading, Fast and Slow: When Do Models \"Understand\" Language?","created":"2022-09-15","cited_by_count":13,"area":null},{"id":"2310.09107","title":"GLoRE: Evaluating Logical Reasoning of Large Language Models","created":"2023-10-13","cited_by_count":13,"area":"lr"},{"id":"2101.06980","title":"Mitigating the Position Bias of Transformer Models in Passage Re-Ranking","created":"2021-01-18","cited_by_count":10,"area":null},{"id":"2205.00299","title":"A Survey of Machine Narrative Reading Comprehension Assessments","created":"2022-04-30","cited_by_count":10,"area":null},{"id":"2406.17163","title":"Paraphrase and Aggregate with Large Language Models for Minimizing Intent Classification Errors","created":"2024-06-24","cited_by_count":9,"area":null},{"id":"2310.07830","title":"Does Synthetic Data Make Large Language Models More Efficient?","created":"2023-10-11","cited_by_count":8,"area":null},{"id":"2203.06096","title":"WLASL-LEX: a Dataset for Recognising Phonological Properties in American Sign Language","created":"2022-03-11","cited_by_count":6,"area":null},{"id":"2110.10874","title":"CNewSum: A Large-scale Chinese News Summarization Dataset with Human-annotated Adequacy and Deducibility Level","created":"2021-10-21","cited_by_count":5,"area":null},{"id":"2204.04711","title":"Data Augmentation for Biomedical Factoid Question Answering","created":"2022-04-10","cited_by_count":5,"area":null},{"id":"2306.12550","title":"On Evaluation of Document Classification using RVL-CDIP","created":"2023-06-21","cited_by_count":5,"area":null},{"id":"2404.17194","title":"TIGQA:An Expert Annotated Question Answering Dataset in Tigrinya","created":"2024-04-26","cited_by_count":5,"area":null},{"id":"2506.02279","title":"ImpRAG: Retrieval-Augmented Generation with Implicit Queries","created":"2025-06-02","cited_by_count":5,"area":"rag"},{"id":"2105.10334","title":"Fact-driven Logical Reasoning for Machine Reading Comprehension","created":"2021-05-21","cited_by_count":4,"area":null},{"id":"2505.09825","title":"KRISTEVA: Close Reading as a Novel Task for Benchmarking Interpretive Reasoning","created":"2025-05-14","cited_by_count":4,"area":"lr"},{"id":"2107.05799","title":"Human Attention during Goal-directed Reading Comprehension Relies on Task Optimization","created":"2021-07-13","cited_by_count":3,"area":null},{"id":"2107.08582","title":"Bridging the Gap between Language Model and Reading Comprehension: Unsupervised MRC via Self-Supervision","created":"2021-07-19","cited_by_count":3,"area":null},{"id":"2308.07937","title":"Automated Testing and Improvement of Named Entity Recognition Systems","created":"2023-08-14","cited_by_count":3,"area":null},{"id":"2606.15453","title":"A Spatio-Temporal Expert Prefetching Framework for Efficient MoE-based LLM Inference","created":"2026-06-13","cited_by_count":3,"area":"moe"},{"id":"2102.03016","title":"Model Agnostic Answer Reranking System for Adversarial Question Answering","created":"2021-02-05","cited_by_count":2,"area":null},{"id":"2104.10139","title":"Towards Solving Multimodal Comprehension","created":"2021-04-20","cited_by_count":2,"area":null},{"id":"2106.00257","title":"A Coarse to Fine Question Answering System based on Reinforcement Learning","created":"2021-06-01","cited_by_count":2,"area":null},{"id":"2109.00077","title":"Interactive Machine Comprehension with Dynamic Knowledge Graphs","created":"2021-08-31","cited_by_count":2,"area":null},{"id":"2207.01450","title":"Discourse-Aware Graph Networks for Textual Logical Reasoning","created":"2022-07-04","cited_by_count":2,"area":"lr"},{"id":"2512.11912","title":"Robustness of Probabilistic Models to Low-Quality Data: A Multi-Perspective Analysis","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2105.05744","title":"Building a Question and Answer System for News Domain","created":"2021-05-12","cited_by_count":1,"area":null},{"id":"2105.08244","title":"PoBRL: Optimizing Multi-Document Summarization by Blending Reinforcement Learning Policies","created":"2021-05-18","cited_by_count":1,"area":null},{"id":"2110.11899","title":"Challenges in Procedural Multimodal Machine Comprehension:A Novel Way To Benchmark","created":"2021-10-22","cited_by_count":1,"area":null},{"id":"2201.13230","title":"POTATO: exPlainable infOrmation exTrAcTion framewOrk","created":"2022-01-31","cited_by_count":1,"area":null},{"id":"2212.04070","title":"A Comprehensive Survey on Multi-hop Machine Reading Comprehension Datasets and Metrics","created":"2022-12-08","cited_by_count":1,"area":null},{"id":"2212.04072","title":"A Comprehensive Survey on Multi-hop Machine Reading Comprehension Approaches","created":"2022-12-08","cited_by_count":1,"area":null},{"id":"2303.10328","title":"Revisiting Automatic Question Summarization Evaluation in the Biomedical Domain","created":"2023-03-18","cited_by_count":1,"area":null},{"id":"2503.05326","title":"Fine-Grained Evaluation for Implicit Discourse Relation Recognition","created":"2025-03-07","cited_by_count":1,"area":null},{"id":"2510.17001","title":"Vocab Diet: Reshaping the Vocabulary of LLMs via Vector Arithmetic","created":"2025-10-19","cited_by_count":1,"area":null},{"id":"2510.19265","title":"Difficulty-Controllable Multiple-Choice Question Generation Using Large Language Models and Direct Preference Optimization","created":"2025-10-22","cited_by_count":1,"area":"alignment"},{"id":"2605.23175","title":"Robust LLM Watermarking with Minimal Semantic Distortion for IP Protection","created":"2026-05-22","cited_by_count":1,"area":"safety"},{"id":"2606.14150","title":"Small LLMs: Pruning vs. Training from Scratch","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2606.26036","title":"Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning","created":"2026-06-24","cited_by_count":1,"area":"safety"},{"id":"2101.00606","title":"News Image Steganography: A Novel Architecture Facilitates the Fake News Identification","created":"2021-01-03","cited_by_count":0,"area":null},{"id":"2108.02561","title":"Sentence-level Online Handwritten Chinese Character Recognition","created":"2021-07-04","cited_by_count":0,"area":null},{"id":"2201.01706","title":"Multi Document Reading Comprehension","created":"2022-01-05","cited_by_count":0,"area":null},{"id":"2203.09424","title":"elBERto: Self-supervised Commonsense Learning for Question Answering","created":"2022-03-17","cited_by_count":0,"area":null},{"id":"2210.01734","title":"Text Characterization Toolkit","created":"2022-10-04","cited_by_count":0,"area":null},{"id":"2305.08433","title":"EMBRACE: Evaluation and Modifications for Boosting RACE","created":"2023-05-15","cited_by_count":0,"area":null},{"id":"2306.07994","title":"MSSRNet: Manipulating Sequential Style Representation for Unsupervised Text Style Transfer","created":"2023-06-12","cited_by_count":0,"area":null},{"id":"2311.12298","title":"Noise in Relation Classification Dataset TACRED: Characterization and Reduction","created":"2023-11-21","cited_by_count":0,"area":null},{"id":"2407.19947","title":"Inference acceleration for large language models using \"stairs\" assisted greedy generation","created":"2024-07-29","cited_by_count":0,"area":"inference"},{"id":"2502.08904","title":"MIH-TCCT: Mitigating Inconsistent Hallucinations in LLMs via Event-Driven Text-Code Cyclic Training","created":"2025-02-13","cited_by_count":0,"area":null},{"id":"2506.06930","title":"DiscoSum: Discourse-aware News Summarization","created":"2025-06-07","cited_by_count":0,"area":null},{"id":"2509.07311","title":"Does This Look Familiar to You? Knowledge Analysis via Model Internal Representations","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2605.00440","title":"Role-Aware Artificial Intelligence Across Augmentation and Automation in Human-Machine Symbiosis","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.25486","title":"RAG-Match: Retrieval-Augmented Knowledge Injection and Hierarchical Reasoning for Calibrated Semantic Relevance","created":"2026-05-25","cited_by_count":0,"area":"lr"},{"id":"2610.17747","title":"Auditing Failure Attribution: Label Predictability and Judge Behavior","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}