{"total":60,"rows":[{"id":"2210.00720","title":"Complexity-Based Prompting for Multi-Step Reasoning","created":"2022-10-03","cited_by_count":388,"area":"lr"},{"id":"2104.05240","title":"Factual Probing Is [MASK]: Learning vs. Learning to Recall","created":"2021-04-12","cited_by_count":291,"area":null},{"id":"2110.08420","title":"Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information","created":"2021-10-16","cited_by_count":291,"area":null},{"id":"2310.15421","title":"FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions","created":"2023-10-24","cited_by_count":171,"area":null},{"id":"2304.09797","title":"Progressive-Hint Prompting Improves Reasoning in Large Language Models","created":"2023-04-19","cited_by_count":147,"area":"lr"},{"id":"2202.07206","title":"Impact of Pretraining Term Frequencies on Few-Shot Reasoning","created":"2022-02-15","cited_by_count":142,"area":"lr"},{"id":"2302.12822","title":"Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data","created":"2023-02-24","cited_by_count":119,"area":"lr"},{"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":"2106.00840","title":"Comparing Test Sets with Item Response Theory","created":"2021-06-01","cited_by_count":57,"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":"2502.14127","title":"Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above","created":"2025-02-19","cited_by_count":52,"area":null},{"id":"2107.11976","title":"One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval","created":"2021-07-26","cited_by_count":46,"area":null},{"id":"2106.01024","title":"Why Machine Reading Comprehension Models Learn Shortcuts?","created":"2021-06-02","cited_by_count":40,"area":null},{"id":"2406.13397","title":"MoreHopQA: More Than Multi-hop Reasoning","created":"2024-06-19","cited_by_count":37,"area":"lr"},{"id":"2109.01156","title":"Challenges in Generalization in Open Domain Question Answering","created":"2021-09-02","cited_by_count":30,"area":null},{"id":"2402.17019","title":"Leveraging Large Language Models for Learning Complex Legal Concepts through Storytelling","created":"2024-02-26","cited_by_count":23,"area":null},{"id":"2306.15261","title":"A Survey on Out-of-Distribution Evaluation of Neural NLP Models","created":"2023-06-27","cited_by_count":20,"area":null},{"id":"2109.07009","title":"Will this Question be Answered? Question Filtering via Answer Model Distillation for Efficient Question Answering","created":"2021-09-14","cited_by_count":19,"area":null},{"id":"2302.13959","title":"Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets","created":"2023-02-27","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":"2312.10126","title":"Do Text Simplification Systems Preserve Meaning? A Human Evaluation via Reading Comprehension","created":"2023-12-15","cited_by_count":16,"area":null},{"id":"2204.07408","title":"Towards Fine-grained Causal Reasoning and QA","created":"2022-04-15","cited_by_count":13,"area":"lr"},{"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":"2410.18588","title":"Knowledge Distillation Using Frontier Open-source LLMs: Generalizability and the Role of Synthetic Data","created":"2024-10-24","cited_by_count":12,"area":"synth"},{"id":"2205.09295","title":"Are Prompt-based Models Clueless?","created":"2022-05-19","cited_by_count":11,"area":null},{"id":"2402.02099","title":"Analyzing the Evaluation of Cross-Lingual Knowledge Transfer in Multilingual Language Models","created":"2024-02-03","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":"2109.11256","title":"Can Question Generation Debias Question Answering Models? A Case Study on Question-Context Lexical Overlap","created":"2021-09-23","cited_by_count":8,"area":null},{"id":"2211.05417","title":"Can Transformers Reason in Fragments of Natural Language?","created":"2022-11-10","cited_by_count":8,"area":"lr"},{"id":"2203.11400","title":"VLSP 2021 - ViMRC Challenge: Vietnamese Machine Reading Comprehension","created":"2022-03-22","cited_by_count":7,"area":null},{"id":"2210.14541","title":"Look to the Right: Mitigating Relative Position Bias in Extractive Question Answering","created":"2022-10-26","cited_by_count":7,"area":null},{"id":"2104.07571","title":"Toward Deconfounding the Influence of Entity Demographics for Question Answering Accuracy","created":"2021-04-15","cited_by_count":5,"area":null},{"id":"2312.04362","title":"PCoQA: Persian Conversational Question Answering Dataset","created":"2023-12-07","cited_by_count":5,"area":null},{"id":"2104.11514","title":"Learning to Learn to be Right for the Right Reasons","created":"2021-04-23","cited_by_count":4,"area":null},{"id":"2204.10176","title":"Probing Script Knowledge from Pre-Trained Models","created":"2022-04-16","cited_by_count":4,"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":"2210.13439","title":"Cascading Biases: Investigating the Effect of Heuristic Annotation Strategies on Data and Models","created":"2022-10-24","cited_by_count":4,"area":null},{"id":"2302.00094","title":"The Impacts of Unanswerable Questions on the Robustness of Machine Reading Comprehension Models","created":"2023-01-31","cited_by_count":4,"area":null},{"id":"2305.04859","title":"A Frustratingly Easy Improvement for Position Embeddings via Random Padding","created":"2023-05-08","cited_by_count":4,"area":null},{"id":"2111.09029","title":"Towards Interpretable and Reliable Reading Comprehension: A Pipeline Model with Unanswerability Prediction","created":"2021-11-17","cited_by_count":3,"area":null},{"id":"2203.02753","title":"Feeding What You Need by Understanding What You Learned","created":"2022-03-05","cited_by_count":3,"area":null},{"id":"2208.03030","title":"ChiQA: A Large Scale Image-based Real-World Question Answering Dataset for Multi-Modal Understanding","created":"2022-08-05","cited_by_count":3,"area":null},{"id":"2109.00077","title":"Interactive Machine Comprehension with Dynamic Knowledge Graphs","created":"2021-08-31","cited_by_count":2,"area":null},{"id":"2406.03666","title":"What Makes Language Models Good-enough?","created":"2024-06-06","cited_by_count":2,"area":null},{"id":"2409.02840","title":"R2GQA: Retriever-Reader-Generator Question Answering System to Support Students Understanding Legal Regulations in Higher Education","created":"2024-09-04","cited_by_count":2,"area":null},{"id":"2210.07566","title":"A Survey of Parameters Associated with the Quality of Benchmarks in NLP","created":"2022-10-14","cited_by_count":1,"area":null},{"id":"2302.08148","title":"Empirical Investigation of Neural Symbolic Reasoning Strategies","created":"2023-02-16","cited_by_count":1,"area":"lr"},{"id":"2305.04737","title":"SkillQG: Learning to Generate Question for Reading Comprehension Assessment","created":"2023-05-08","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":"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":"2311.06807","title":"On the Robustness of Question Rewriting Systems to Questions of Varying Hardness","created":"2023-11-12","cited_by_count":1,"area":null},{"id":"2401.01218","title":"Self-Supervised Position Debiasing for Large Language Models","created":"2024-01-02","cited_by_count":1,"area":null},{"id":"2503.18290","title":"When is dataset cartography ineffective? Using training dynamics does not improve robustness against Adversarial SQuAD","created":"2025-03-24","cited_by_count":1,"area":null},{"id":"2506.14587","title":"SCISSOR: Mitigating Semantic Bias through Cluster-Aware Siamese Networks for Robust Classification","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2110.11692","title":"ListReader: Extracting List-form Answers for Opinion Questions","created":"2021-10-22","cited_by_count":0,"area":null},{"id":"2207.08943","title":"MRCLens: an MRC Dataset Bias Detection Toolkit","created":"2022-07-18","cited_by_count":0,"area":null},{"id":"2211.16093","title":"Penalizing Confident Predictions on Largely Perturbed Inputs Does Not Improve Out-of-Distribution Generalization in Question Answering","created":"2022-11-29","cited_by_count":0,"area":null},{"id":"2403.14197","title":"Context Quality Matters in Training Fusion-in-Decoder for Extractive Open-Domain Question Answering","created":"2024-03-21","cited_by_count":0,"area":"rag"},{"id":"2408.05023","title":"Investigating a Benchmark for Training-set free Evaluation of Linguistic Capabilities in Machine Reading Comprehension","created":"2024-08-09","cited_by_count":0,"area":null},{"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}