{"total":28,"rows":[{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916,"area":null},{"id":"2101.00436","title":"Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval","created":"2021-01-02","cited_by_count":63,"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":"2104.08731","title":"Can NLI Models Verify QA Systems' Predictions?","created":"2021-04-18","cited_by_count":46,"area":null},{"id":"2104.08445","title":"Joint Passage Ranking for Diverse Multi-Answer Retrieval","created":"2021-04-17","cited_by_count":43,"area":null},{"id":"2205.12665","title":"QAMPARI: An Open-domain Question Answering Benchmark for Questions with Many Answers from Multiple Paragraphs","created":"2022-05-25","cited_by_count":42,"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":"2104.08825","title":"Flexible Generation of Natural Language Deductions","created":"2021-04-18","cited_by_count":28,"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":"2103.03872","title":"Rissanen Data Analysis: Examining Dataset Characteristics via Description Length","created":"2021-03-05","cited_by_count":22,"area":null},{"id":"2203.11027","title":"Reasoning over Public and Private Data in Retrieval-Based Systems","created":"2022-03-14","cited_by_count":21,"area":null},{"id":"2104.04515","title":"Connecting Attributions and QA Model Behavior on Realistic Counterfactuals","created":"2021-04-09","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":"2111.04104","title":"Uncertainty Calibration for Ensemble-Based Debiasing Methods","created":"2021-11-07","cited_by_count":16,"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":"2501.17144","title":"FactCG: Enhancing Fact Checkers with Graph-Based Multi-Hop Data","created":"2025-01-28","cited_by_count":14,"area":null},{"id":"2107.03242","title":"Robustifying Multi-hop QA through Pseudo-Evidentiality Training","created":"2021-07-07","cited_by_count":13,"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":"2203.06342","title":"What Makes Reading Comprehension Questions Difficult?","created":"2022-03-12","cited_by_count":11,"area":null},{"id":"2305.14331","title":"What Else Do I Need to Know? The Effect of Background Information on Users' Reliance on QA Systems","created":"2023-05-23","cited_by_count":9,"area":null},{"id":"2210.06725","title":"Assessing Out-of-Domain Language Model Performance from Few Examples","created":"2022-10-13","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":"2210.08763","title":"ReasonChainQA: Text-based Complex Question Answering with Explainable Evidence Chains","created":"2022-10-17","cited_by_count":4,"area":null},{"id":"2102.03016","title":"Model Agnostic Answer Reranking System for Adversarial Question Answering","created":"2021-02-05","cited_by_count":2,"area":null},{"id":"2207.08943","title":"MRCLens: an MRC Dataset Bias Detection Toolkit","created":"2022-07-18","cited_by_count":0,"area":null},{"id":"2407.21049","title":"Evaluating Long Range Dependency Handling in Code Generation LLMs","created":"2024-07-23","cited_by_count":0,"area":null},{"id":"2512.12688","title":"How Prompts Move Language Model Behavior: Frames, Salience, and Construal as Semantic Control","created":"2025-12-14","cited_by_count":0,"area":null},{"id":"2607.09328","title":"WildTrace: Benchmarking Natural Evidence Trails in Long-Context Reasoning","created":"2026-07-10","cited_by_count":0,"area":null}],"next_cursor":null}