{"total":105,"rows":[{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868,"area":null},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743,"area":null},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459,"area":null},{"id":"2111.02840","title":"Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models","created":"2021-11-04","cited_by_count":232,"area":null},{"id":"2108.00941","title":"A Survey of Human-in-the-loop for Machine Learning","created":"2021-08-02","cited_by_count":215,"area":null},{"id":"2202.07922","title":"ZeroGen: Efficient Zero-shot Learning via Dataset Generation","created":"2022-02-16","cited_by_count":211,"area":null},{"id":"2112.08608","title":"QuALITY: Question Answering with Long Input Texts, Yes!","created":"2021-12-16","cited_by_count":208,"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":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177,"area":null},{"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":"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":"2201.05320","title":"CommonsenseQA 2.0: Exposing the Limits of AI through Gamification","created":"2022-01-14","cited_by_count":109,"area":null},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107,"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":"2212.09746","title":"Evaluating Human-Language Model Interaction","created":"2022-12-19","cited_by_count":92,"area":null},{"id":"2212.10947","title":"Parallel Context Windows for Large Language Models","created":"2022-12-21","cited_by_count":81,"area":null},{"id":"2302.03202","title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","created":"2023-02-07","cited_by_count":80,"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":"2106.00245","title":"Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Models","created":"2021-06-01","cited_by_count":75,"area":null},{"id":"2209.02128","title":"Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples","created":"2022-09-05","cited_by_count":69,"area":null},{"id":"2311.17295","title":"Elo Uncovered: Robustness and Best Practices in Language Model Evaluation","created":"2023-11-29","cited_by_count":61,"area":null},{"id":"2306.11987","title":"Training Transformers with 4-bit Integers","created":"2023-06-21","cited_by_count":60,"area":null},{"id":"2106.02280","title":"Human-Adversarial Visual Question Answering","created":"2021-06-04","cited_by_count":57,"area":null},{"id":"2202.12359","title":"UnifiedQA-v2: Stronger Generalization via Broader Cross-Format Training","created":"2022-02-23","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":"2101.00133","title":"NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned","created":"2021-01-01","cited_by_count":52,"area":null},{"id":"2104.04725","title":"Fool Me Twice: Entailment from Wikipedia Gamification","created":"2021-04-10","cited_by_count":50,"area":null},{"id":"2108.05921","title":"Hatemoji: A Test Suite and Adversarially-Generated Dataset for Benchmarking and Detecting Emoji-based Hate","created":"2021-08-12","cited_by_count":50,"area":null},{"id":"2306.14321","title":"RobuT: A Systematic Study of Table QA Robustness Against Human-Annotated Adversarial Perturbations","created":"2023-06-25","cited_by_count":43,"area":null},{"id":"2106.00969","title":"COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences","created":"2021-06-02","cited_by_count":40,"area":null},{"id":"2106.01024","title":"Why Machine Reading Comprehension Models Learn Shortcuts?","created":"2021-06-02","cited_by_count":40,"area":null},{"id":"2110.08300","title":"The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail","created":"2021-10-15","cited_by_count":38,"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":"2310.13486","title":"Mind the instructions: a holistic evaluation of consistency and interactions in prompt-based learning","created":"2023-10-20","cited_by_count":31,"area":null},{"id":"2303.18190","title":"Assessing Language Model Deployment with Risk Cards","created":"2023-03-31","cited_by_count":30,"area":null},{"id":"2310.13671","title":"Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models","created":"2023-10-20","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":"2110.07867","title":"Exploring Universal Intrinsic Task Subspace via Prompt Tuning","created":"2021-10-15","cited_by_count":25,"area":null},{"id":"2110.08514","title":"Analyzing Dynamic Adversarial Training Data in the Limit","created":"2021-10-16","cited_by_count":24,"area":null},{"id":"2210.04873","title":"CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation","created":"2022-10-10","cited_by_count":24,"area":null},{"id":"2106.00794","title":"What Ingredients Make for an Effective Crowdsourcing Protocol for Difficult NLU Data Collection Tasks?","created":"2021-06-01","cited_by_count":23,"area":null},{"id":"2302.07346","title":"ScatterShot: Interactive In-context Example Curation for Text Transformation","created":"2023-02-14","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":"2402.14147","title":"Wikibench: Community-Driven Data Curation for AI Evaluation on Wikipedia","created":"2024-02-21","cited_by_count":18,"area":null},{"id":"2211.01482","title":"RQUGE: Reference-Free Metric for Evaluating Question Generation by Answering the Question","created":"2022-11-02","cited_by_count":17,"area":null},{"id":"2204.01906","title":"Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks","created":"2022-04-05","cited_by_count":16,"area":null},{"id":"2404.01157","title":"Green AI: Exploring Carbon Footprints, Mitigation Strategies, and Trade Offs in Large Language Model Training","created":"2024-04-01","cited_by_count":15,"area":null},{"id":"2403.19559","title":"Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset","created":"2024-03-28","cited_by_count":13,"area":null},{"id":"2111.08181","title":"Adversarially Constructed Evaluation Sets Are More Challenging, but May Not Be Fair","created":"2021-11-16","cited_by_count":12,"area":null},{"id":"2203.06342","title":"What Makes Reading Comprehension Questions Difficult?","created":"2022-03-12","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":"2406.12928","title":"Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and Toolbox","created":"2024-06-15","cited_by_count":11,"area":null},{"id":"2211.16220","title":"Which Shortcut Solution Do Question Answering Models Prefer to Learn?","created":"2022-11-29","cited_by_count":9,"area":null},{"id":"2305.13342","title":"On the Limitations of Simulating Active Learning","created":"2023-05-21","cited_by_count":9,"area":null},{"id":"2206.14729","title":"longhorns at DADC 2022: How many linguists does it take to fool a Question Answering model? A systematic approach to adversarial attacks","created":"2022-06-29","cited_by_count":8,"area":null},{"id":"2307.02729","title":"Text Alignment Is An Efficient Unified Model for Massive NLP Tasks","created":"2023-07-06","cited_by_count":8,"area":null},{"id":"2305.06557","title":"Long-Tailed Question Answering in an Open World","created":"2023-05-11","cited_by_count":7,"area":null},{"id":"2305.14384","title":"Adversarial Nibbler: A Data-Centric Challenge for Improving the Safety of Text-to-Image Models","created":"2023-05-22","cited_by_count":7,"area":null},{"id":"2401.18001","title":"Desiderata for the Context Use of Question Answering Systems","created":"2024-01-31","cited_by_count":7,"area":null},{"id":"2212.10815","title":"ZEROTOP: Zero-Shot Task-Oriented Semantic Parsing using Large Language Models","created":"2022-12-21","cited_by_count":6,"area":null},{"id":"2311.07424","title":"Hallucination Augmented Recitations for Language Models","created":"2023-11-13","cited_by_count":6,"area":null},{"id":"2110.04889","title":"Distantly-Supervised Evidence Retrieval Enables Question Answering without Evidence Annotation","created":"2021-10-10","cited_by_count":5,"area":null},{"id":"2305.10928","title":"Multilingual Event Extraction from Historical Newspaper Adverts","created":"2023-05-18","cited_by_count":5,"area":null},{"id":"2305.18917","title":"Fighting Bias with Bias: Promoting Model Robustness by Amplifying Dataset Biases","created":"2023-05-30","cited_by_count":5,"area":null},{"id":"2310.16955","title":"Break it, Imitate it, Fix it: Robustness by Generating Human-Like Attacks","created":"2023-10-25","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":"2411.10163","title":"Compound-QA: A Benchmark for Evaluating LLMs on Compound Questions","created":"2024-11-15","cited_by_count":5,"area":null},{"id":"2209.01824","title":"A Survey on Measuring and Mitigating Reasoning Shortcuts in Machine Reading Comprehension","created":"2022-09-05","cited_by_count":4,"area":null},{"id":"2210.13778","title":"IDK-MRC: Unanswerable Questions for Indonesian Machine Reading Comprehension","created":"2022-10-25","cited_by_count":4,"area":null},{"id":"2305.08752","title":"A Matter of Annotation: An Empirical Study on In Situ and Self-Recall Activity Annotations from Wearable Sensors","created":"2023-05-15","cited_by_count":4,"area":null},{"id":"2406.16779","title":"It Is Not About What You Say, It Is About How You Say It: A Surprisingly Simple Approach for Improving Reading Comprehension","created":"2024-06-24","cited_by_count":4,"area":null},{"id":"2511.07659","title":"Revisiting NLI: Towards Cost-Effective and Human-Aligned Metrics for Evaluating LLMs in Question Answering","created":"2025-11-10","cited_by_count":4,"area":null},{"id":"2109.04385","title":"Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text Classification","created":"2021-09-09","cited_by_count":3,"area":null},{"id":"2504.08756","title":"MHTS: Multi-Hop Tree Structure Framework for Generating Difficulty-Controllable QA Datasets for RAG Evaluation","created":"2025-03-29","cited_by_count":3,"area":null},{"id":"2506.00773","title":"Dynamic Chunking and Selection for Reading Comprehension of Ultra-Long Context in Large Language Models","created":"2025-06-01","cited_by_count":3,"area":null},{"id":"2210.03029","title":"Efficiently Enhancing Zero-Shot Performance of Instruction Following Model via Retrieval of Soft Prompt","created":"2022-10-06","cited_by_count":2,"area":null},{"id":"2305.17197","title":"Entailment as Robust Self-Learner","created":"2023-05-26","cited_by_count":2,"area":null},{"id":"2308.00946","title":"Teaching Smaller Language Models To Generalise To Unseen Compositional Questions","created":"2023-08-02","cited_by_count":2,"area":null},{"id":"2406.17990","title":"Explicit Diversity Conditions for Effective Question Answer Generation with Large Language Models","created":"2024-06-26","cited_by_count":2,"area":null},{"id":"2407.11186","title":"Empowering Persian LLMs for Instruction Following: A Novel Dataset and Training Approach","created":"2024-07-15","cited_by_count":2,"area":null},{"id":"2502.16523","title":"Pay Attention to Real World Perturbations! Natural Robustness Evaluation in Machine Reading Comprehension","created":"2025-02-23","cited_by_count":2,"area":null},{"id":"2110.02052","title":"Transfer Learning for Multi-lingual Tasks -- a Survey","created":"2021-08-28","cited_by_count":1,"area":null},{"id":"2111.10497","title":"Combining Data-driven Supervision with Human-in-the-loop Feedback for Entity Resolution","created":"2021-11-20","cited_by_count":1,"area":null},{"id":"2203.15754","title":"Evaluating Prompts Across Multiple Choice Tasks In a Zero-Shot Setting","created":"2022-03-29","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":"2305.14104","title":"Out-of-Distribution Generalization in Text Classification: Past, Present, and Future","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2305.15130","title":"On Degrees of Freedom in Defining and Testing Natural Language Understanding","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2308.04566","title":"Single-Sentence Reader: A Novel Approach for Addressing Answer Position Bias","created":"2023-08-08","cited_by_count":1,"area":null},{"id":"2401.11185","title":"How the Advent of Ubiquitous Large Language Models both Stymie and Turbocharge Dynamic Adversarial Question Generation","created":"2024-01-20","cited_by_count":1,"area":null},{"id":"2411.05859","title":"Enhancing Financial Fraud Detection with Human-in-the-Loop Feedback and Feedback Propagation","created":"2024-11-07","cited_by_count":1,"area":null},{"id":"2509.01093","title":"Natural Context Drift Undermines the Natural Language Understanding of Large Language Models","created":"2025-09-01","cited_by_count":1,"area":null},{"id":"2206.14272","title":"Collecting high-quality adversarial data for machine reading comprehension tasks with humans and models in the loop","created":"2022-06-28","cited_by_count":0,"area":null},{"id":"2303.13355","title":"Revealing Weaknesses of Vietnamese Language Models Through Unanswerable Questions in Machine Reading Comprehension","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2310.12135","title":"Pseudointelligence: A Unifying Framework for Language Model Evaluation","created":"2023-10-18","cited_by_count":0,"area":null},{"id":"2310.19403","title":"A Lightweight Method to Generate Unanswerable Questions in English","created":"2023-10-30","cited_by_count":0,"area":null},{"id":"2311.03566","title":"Measuring Adversarial Datasets","created":"2023-11-06","cited_by_count":0,"area":null},{"id":"2406.06601","title":"A Human-in-the-Loop Approach to Improving Cross-Text Prosody Transfer","created":"2024-06-06","cited_by_count":0,"area":null},{"id":"2501.05962","title":"Effective faking of verbal deception detection with target-aligned adversarial attacks","created":"2025-01-10","cited_by_count":0,"area":null}],"next_cursor":"100"}