{"total":26,"rows":[{"id":"2210.09150","title":"Prompting GPT-3 To Be Reliable","created":"2022-10-17","cited_by_count":260,"area":null},{"id":"2104.02145","title":"What Will it Take to Fix Benchmarking in Natural Language Understanding?","created":"2021-04-05","cited_by_count":203,"area":null},{"id":"2208.11857","title":"Shortcut Learning of Large Language Models in Natural Language Understanding","created":"2022-08-25","cited_by_count":85,"area":null},{"id":"2103.06922","title":"Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models","created":"2021-03-11","cited_by_count":78,"area":null},{"id":"2106.01024","title":"Why Machine Reading Comprehension Models Learn Shortcuts?","created":"2021-06-02","cited_by_count":40,"area":null},{"id":"2105.11136","title":"Using Adversarial Attacks to Reveal the Statistical Bias in Machine Reading Comprehension Models","created":"2021-05-24","cited_by_count":29,"area":null},{"id":"2305.09022","title":"It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance","created":"2023-05-15","cited_by_count":26,"area":null},{"id":"2105.13471","title":"Inspecting the concept knowledge graph encoded by modern language models","created":"2021-05-27","cited_by_count":15,"area":null},{"id":"2109.11087","title":"BiRdQA: A Bilingual Dataset for Question Answering on Tricky Riddles","created":"2021-09-23","cited_by_count":10,"area":null},{"id":"2109.14017","title":"Shaking Syntactic Trees on the Sesame Street: Multilingual Probing with Controllable Perturbations","created":"2021-09-28","cited_by_count":10,"area":null},{"id":"2409.17455","title":"Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Models","created":"2024-09-26","cited_by_count":10,"area":null},{"id":"2410.11672","title":"Leaving the barn door open for Clever Hans: Simple features predict LLM benchmark answers","created":"2024-10-15","cited_by_count":9,"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":"2211.07040","title":"World Knowledge in Multiple Choice Reading Comprehension","created":"2022-11-13","cited_by_count":6,"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":"2307.01076","title":"Analyzing Multiple-Choice Reading and Listening Comprehension Tests","created":"2023-07-03","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":"2104.07623","title":"Sometimes We Want Translationese","created":"2021-04-15","cited_by_count":3,"area":null},{"id":"2106.12373","title":"PALRACE: Reading Comprehension Dataset with Human Data and Labeled Rationales","created":"2021-06-23","cited_by_count":3,"area":null},{"id":"2210.16298","title":"Investigating Ensemble Methods for Model Robustness Improvement of Text Classifiers","created":"2022-10-28","cited_by_count":2,"area":null},{"id":"2105.01192","title":"Unreasonable Effectiveness of Rule-Based Heuristics in Solving Russian SuperGLUE Tasks","created":"2021-05-03","cited_by_count":1,"area":null},{"id":"2107.01592","title":"Coarse-to-Careful: Seeking Semantic-related Knowledge for Open-domain Commonsense Question Answering","created":"2021-07-04","cited_by_count":0,"area":null},{"id":"2110.04620","title":"A Framework for Rationale Extraction for Deep QA models","created":"2021-10-09","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":"2405.20079","title":"Student Answer Forecasting: Transformer-Driven Answer Choice Prediction for Language Learning","created":"2024-05-30","cited_by_count":0,"area":null},{"id":"2609.37494","title":"Your Benchmark Is Not Saturated: Reviving Multiple-Choice Evaluation with Answer Pooling","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}