{"total":184,"rows":[{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795,"area":null},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421,"area":null},{"id":"2109.05052","title":"Entity-Based Knowledge Conflicts in Question Answering","created":"2021-09-10","cited_by_count":356,"area":null},{"id":"2210.09150","title":"Prompting GPT-3 To Be Reliable","created":"2022-10-17","cited_by_count":260,"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":"2203.15827","title":"LinkBERT: Pretraining Language Models with Document Links","created":"2022-03-29","cited_by_count":211,"area":null},{"id":"2305.13169","title":"A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity","created":"2023-05-22","cited_by_count":182,"area":null},{"id":"2201.03533","title":"SCROLLS: Standardized CompaRison Over Long Language Sequences","created":"2022-01-10","cited_by_count":170,"area":null},{"id":"2307.11019","title":"Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation","created":"2023-07-20","cited_by_count":147,"area":null},{"id":"2405.07437","title":"Evaluation of Retrieval-Augmented Generation: A Survey","created":"2024-05-13","cited_by_count":146,"area":"rag"},{"id":"2210.13701","title":"Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence","created":"2022-10-25","cited_by_count":144,"area":null},{"id":"2303.02861","title":"Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning","created":"2023-03-06","cited_by_count":115,"area":null},{"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":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2306.04618","title":"Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations","created":"2023-06-07","cited_by_count":97,"area":null},{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2410.03727","title":"FaithEval: Can Your Language Model Stay Faithful to Context, Even If \"The Moon is Made of Marshmallows\"","created":"2024-09-30","cited_by_count":86,"area":"rag"},{"id":"2104.08815","title":"FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks","created":"2021-04-18","cited_by_count":85,"area":null},{"id":"2205.11961","title":"ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts","created":"2022-05-24","cited_by_count":85,"area":null},{"id":"2104.08678","title":"Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation","created":"2021-04-18","cited_by_count":79,"area":null},{"id":"2101.00438","title":"Few-Shot Question Answering by Pretraining Span Selection","created":"2021-01-02","cited_by_count":62,"area":null},{"id":"2106.00840","title":"Comparing Test Sets with Item Response Theory","created":"2021-06-01","cited_by_count":57,"area":null},{"id":"2106.06052","title":"Dynaboard: An Evaluation-As-A-Service Platform for Holistic Next-Generation Benchmarking","created":"2021-05-21","cited_by_count":53,"area":null},{"id":"2109.04655","title":"Zero-Shot Dialogue State Tracking via Cross-Task Transfer","created":"2021-09-10","cited_by_count":52,"area":null},{"id":"2310.00935","title":"Resolving Knowledge Conflicts in Large Language Models","created":"2023-10-02","cited_by_count":50,"area":null},{"id":"2301.03282","title":"Universal Information Extraction as Unified Semantic Matching","created":"2023-01-09","cited_by_count":48,"area":null},{"id":"2106.01494","title":"Knowing More About Questions Can Help: Improving Calibration in Question Answering","created":"2021-06-02","cited_by_count":47,"area":null},{"id":"2203.00343","title":"Read before Generate! Faithful Long Form Question Answering with Machine Reading","created":"2022-03-01","cited_by_count":47,"area":null},{"id":"2408.03094","title":"500xCompressor: Generalized Prompt Compression for Large Language Models","created":"2024-08-06","cited_by_count":47,"area":"inference"},{"id":"2104.08731","title":"Can NLI Models Verify QA Systems' Predictions?","created":"2021-04-18","cited_by_count":46,"area":null},{"id":"2310.12150","title":"Understanding Retrieval Augmentation for Long-Form Question Answering","created":"2023-10-18","cited_by_count":45,"area":null},{"id":"2105.11618","title":"TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference","created":"2021-05-25","cited_by_count":40,"area":"inference"},{"id":"2501.02497","title":"A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning","created":"2025-01-05","cited_by_count":40,"area":"lr"},{"id":"2403.08819","title":"Thermometer: Towards Universal Calibration for Large Language Models","created":"2024-02-20","cited_by_count":38,"area":null},{"id":"2309.05173","title":"DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning","created":"2023-09-11","cited_by_count":35,"area":null},{"id":"2101.08333","title":"Zero-shot Generalization in Dialog State Tracking through Generative Question Answering","created":"2021-01-20","cited_by_count":33,"area":null},{"id":"2106.00872","title":"On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study","created":"2021-06-02","cited_by_count":31,"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":"2109.01156","title":"Challenges in Generalization in Open Domain Question Answering","created":"2021-09-02","cited_by_count":30,"area":null},{"id":"2110.07596","title":"Retrieval-guided Counterfactual Generation for QA","created":"2021-10-14","cited_by_count":29,"area":null},{"id":"2101.00420","title":"Learning to Generate Task-Specific Adapters from Task Description","created":"2021-01-02","cited_by_count":28,"area":null},{"id":"2110.08175","title":"MixQG: Neural Question Generation with Mixed Answer Types","created":"2021-10-15","cited_by_count":28,"area":null},{"id":"2305.15387","title":"Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering","created":"2023-05-24","cited_by_count":28,"area":null},{"id":"2310.12516","title":"ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks","created":"2023-10-19","cited_by_count":28,"area":"rag"},{"id":"2404.16032","title":"Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documents","created":"2024-04-24","cited_by_count":27,"area":"rag"},{"id":"2109.01951","title":"FewshotQA: A simple framework for few-shot learning of question answering tasks using pre-trained text-to-text models","created":"2021-09-04","cited_by_count":26,"area":null},{"id":"2404.18848","title":"FeDeRA:Efficient Fine-tuning of Language Models in Federated Learning Leveraging Weight Decomposition","created":"2024-04-29","cited_by_count":26,"area":null},{"id":"2105.02590","title":"Reliability Testing for Natural Language Processing Systems","created":"2021-05-06","cited_by_count":25,"area":null},{"id":"2503.15620","title":"Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings","created":"2025-03-19","cited_by_count":24,"area":null},{"id":"2203.07653","title":"Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness","created":"2022-03-15","cited_by_count":23,"area":null},{"id":"2210.12517","title":"Exploring The Landscape of Distributional Robustness for Question Answering Models","created":"2022-10-22","cited_by_count":23,"area":null},{"id":"2109.04912","title":"ReasonBERT: Pre-trained to Reason with Distant Supervision","created":"2021-09-10","cited_by_count":22,"area":null},{"id":"2203.08304","title":"Hyperdecoders: Instance-specific decoders for multi-task NLP","created":"2022-03-15","cited_by_count":22,"area":null},{"id":"2205.02014","title":"On Continual Model Refinement in Out-of-Distribution Data Streams","created":"2022-05-04","cited_by_count":22,"area":null},{"id":"2109.07954","title":"Improving Unsupervised Question Answering via Summarization-Informed Question Generation","created":"2021-09-16","cited_by_count":21,"area":null},{"id":"2204.12755","title":"A Thorough Examination on Zero-shot Dense Retrieval","created":"2022-04-27","cited_by_count":21,"area":null},{"id":"2205.04040","title":"ProQA: Structural Prompt-based Pre-training for Unified Question Answering","created":"2022-05-09","cited_by_count":21,"area":null},{"id":"2102.01065","title":"Do Question Answering Modeling Improvements Hold Across Benchmarks?","created":"2021-02-01","cited_by_count":20,"area":null},{"id":"2108.13854","title":"Contrastive Domain Adaptation for Question Answering using Limited Text Corpora","created":"2021-08-31","cited_by_count":20,"area":null},{"id":"2110.07586","title":"Can Explanations Be Useful for Calibrating Black Box Models?","created":"2021-10-14","cited_by_count":20,"area":null},{"id":"2210.02498","title":"Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model","created":"2022-10-05","cited_by_count":20,"area":null},{"id":"2305.01812","title":"Post-Abstention: Towards Reliably Re-Attempting the Abstained Instances in QA","created":"2023-05-02","cited_by_count":20,"area":null},{"id":"2106.08190","title":"Question Answering Infused Pre-training of General-Purpose Contextualized Representations","created":"2021-06-15","cited_by_count":19,"area":null},{"id":"2110.04374","title":"A Few More Examples May Be Worth Billions of Parameters","created":"2021-10-08","cited_by_count":19,"area":null},{"id":"2502.08767","title":"SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidence","created":"2025-02-12","cited_by_count":18,"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":"2309.07822","title":"CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration","created":"2023-09-14","cited_by_count":17,"area":null},{"id":"2409.10790","title":"Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering","created":"2024-09-16","cited_by_count":17,"area":null},{"id":"2101.06779","title":"Few Shot Dialogue State Tracking using Meta-learning","created":"2021-01-17","cited_by_count":16,"area":null},{"id":"2109.13880","title":"Single-dataset Experts for Multi-dataset Question Answering","created":"2021-09-28","cited_by_count":15,"area":null},{"id":"2112.01922","title":"MetaQA: Combining Expert Agents for Multi-Skill Question Answering","created":"2021-12-03","cited_by_count":15,"area":null},{"id":"2210.15221","title":"TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack","created":"2022-10-27","cited_by_count":15,"area":null},{"id":"2410.02381","title":"MetaMetrics: Calibrating Metrics For Generation Tasks Using Human Preferences","created":"2024-10-03","cited_by_count":15,"area":null},{"id":"2203.10079","title":"Simulating Bandit Learning from User Feedback for Extractive Question Answering","created":"2022-03-18","cited_by_count":14,"area":null},{"id":"2510.08907","title":"Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors","created":"2025-10-10","cited_by_count":14,"area":"inference"},{"id":"2105.02692","title":"Learning to Perturb Word Embeddings for Out-of-distribution QA","created":"2021-05-06","cited_by_count":13,"area":null},{"id":"2207.02419","title":"BioTABQA: Instruction Learning for Biomedical Table Question Answering","created":"2022-07-06","cited_by_count":13,"area":null},{"id":"2301.11293","title":"Understanding Finetuning for Factual Knowledge Extraction from Language Models","created":"2023-01-26","cited_by_count":13,"area":null},{"id":"2203.08926","title":"Synthetic Question Value Estimation for Domain Adaptation of Question Answering","created":"2022-03-16","cited_by_count":12,"area":null},{"id":"2206.05658","title":"Improving Pre-trained Language Model Fine-tuning with Noise Stability Regularization","created":"2022-06-12","cited_by_count":12,"area":null},{"id":"2310.05007","title":"MinPrompt: Graph-based Minimal Prompt Data Augmentation for Few-shot Question Answering","created":"2023-10-08","cited_by_count":12,"area":null},{"id":"2202.00254","title":"Active Learning Over Multiple Domains in Natural Language Tasks","created":"2022-02-01","cited_by_count":11,"area":null},{"id":"2203.06342","title":"What Makes Reading Comprehension Questions Difficult?","created":"2022-03-12","cited_by_count":11,"area":null},{"id":"2203.07522","title":"Choose Your QA Model Wisely: A Systematic Study of Generative and Extractive Readers for Question Answering","created":"2022-03-14","cited_by_count":11,"area":null},{"id":"2502.15543","title":"ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation","created":"2025-02-21","cited_by_count":11,"area":"rag"},{"id":"2505.15807","title":"The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation","created":"2025-05-21","cited_by_count":11,"area":null},{"id":"2204.02123","title":"Improved and Efficient Conversational Slot Labeling through Question Answering","created":"2022-04-05","cited_by_count":10,"area":null},{"id":"2204.11458","title":"ED2LM: Encoder-Decoder to Language Model for Faster Document Re-ranking Inference","created":"2022-04-25","cited_by_count":9,"area":null},{"id":"2205.10714","title":"Interpretable Proof Generation via Iterative Backward Reasoning","created":"2022-05-22","cited_by_count":9,"area":"lr"},{"id":"2205.13722","title":"Can Foundation Models Help Us Achieve Perfect Secrecy?","created":"2022-05-27","cited_by_count":9,"area":null},{"id":"2210.06799","title":"Benchmarking Long-tail Generalization with Likelihood Splits","created":"2022-10-13","cited_by_count":9,"area":null},{"id":"2405.09335","title":"Prompting-based Synthetic Data Generation for Few-Shot Question Answering","created":"2024-05-15","cited_by_count":9,"area":"synth"},{"id":"2409.14364","title":"Position IDs Matter: An Enhanced Position Layout for Efficient Context Compression in Large Language Models","created":"2024-09-22","cited_by_count":9,"area":"inference"},{"id":"2501.01059","title":"Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models","created":"2025-01-02","cited_by_count":9,"area":null},{"id":"2506.05568","title":"Ravan: Multi-Head Low-Rank Adaptation for Federated Fine-Tuning","created":"2025-06-05","cited_by_count":9,"area":null},{"id":"2302.04618","title":"Robust Question Answering against Distribution Shifts with Test-Time Adaptation: An Empirical Study","created":"2023-02-09","cited_by_count":8,"area":null},{"id":"2305.14901","title":"Chain-of-Questions Training with Latent Answers for Robust Multistep Question Answering","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2412.12527","title":"When to Speak, When to Abstain: Contrastive Decoding with Abstention","created":"2024-12-17","cited_by_count":8,"area":null},{"id":"2106.04134","title":"Cheap and Good? Simple and Effective Data Augmentation for Low Resource Machine Reading","created":"2021-06-08","cited_by_count":7,"area":null},{"id":"2203.11400","title":"VLSP 2021 - ViMRC Challenge: Vietnamese Machine Reading Comprehension","created":"2022-03-22","cited_by_count":7,"area":null}],"next_cursor":"100"}