{"total":33,"rows":[{"id":"2102.07033","title":"PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them","created":"2021-02-13","cited_by_count":200,"area":null},{"id":"2212.08037","title":"Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models","created":"2022-12-15","cited_by_count":112,"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":"2106.02280","title":"Human-Adversarial Visual Question Answering","created":"2021-06-04","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":"2310.13544","title":"A Diachronic Perspective on User Trust in AI under Uncertainty","created":"2023-10-20","cited_by_count":23,"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":"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":"2502.19110","title":"Conformal Linguistic Calibration: Trading-off between Factuality and Specificity","created":"2025-02-26","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":"2204.01906","title":"Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks","created":"2022-04-05","cited_by_count":16,"area":null},{"id":"2311.15451","title":"Uncertainty-aware Language Modeling for Selective Question Answering","created":"2023-11-26","cited_by_count":16,"area":null},{"id":"2408.14141","title":"Crowd-Calibrator: Can Annotator Disagreement Inform Calibration in Subjective Tasks?","created":"2024-08-26","cited_by_count":13,"area":null},{"id":"2410.15512","title":"Reverse Question Answering: Can an LLM Write a Question so Hard (or Bad) that it Can't Answer?","created":"2024-10-20","cited_by_count":13,"area":null},{"id":"2210.17525","title":"Query Refinement Prompts for Closed-Book Long-Form Question Answering","created":"2022-10-31","cited_by_count":12,"area":null},{"id":"2205.09665","title":"Automated Crossword Solving","created":"2022-05-19","cited_by_count":9,"area":null},{"id":"2407.03545","title":"On Evaluating Explanation Utility for Human-AI Decision Making in NLP","created":"2024-07-03","cited_by_count":9,"area":null},{"id":"2306.12255","title":"Solving and Generating NPR Sunday Puzzles with Large Language Models","created":"2023-06-21","cited_by_count":7,"area":null},{"id":"2312.01308","title":"Bridging Background Knowledge Gaps in Translation with Automatic Explicitation","created":"2023-12-03","cited_by_count":7,"area":null},{"id":"2406.16342","title":"Is your benchmark truly adversarial? AdvScore: Evaluating Human-Grounded Adversarialness","created":"2024-06-24","cited_by_count":7,"area":null},{"id":"2502.19684","title":"GRACE: A Granular Benchmark for Evaluating Model Calibration against Human Calibration","created":"2025-02-27","cited_by_count":5,"area":null},{"id":"2210.03650","title":"Longtonotes: OntoNotes with Longer Coreference Chains","created":"2022-10-07","cited_by_count":4,"area":null},{"id":"2402.12291","title":"KARL: Knowledge-Aware Retrieval and Representations aid Retention and Learning in Students","created":"2024-02-19","cited_by_count":2,"area":null},{"id":"2210.06599","title":"Improving Question Answering with Generation of NQ-like Questions","created":"2022-10-12","cited_by_count":1,"area":null},{"id":"2305.14750","title":"Mastering the ABCDs of Complex Questions: Answer-Based Claim Decomposition for Fine-grained Self-Evaluation","created":"2023-05-24","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":"2604.21766","title":"AUDITA: A New Dataset to Audit Humans vs. AI Skill at Audio QA","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2606.07587","title":"The Routing Plateau: Understanding the Accuracy Limits of LLM Routers","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2205.12507","title":"Re-Examining Calibration: The Case of Question Answering","created":"2022-05-25","cited_by_count":0,"area":null},{"id":"2212.03296","title":"Cheater's Bowl: Human vs. Computer Search Strategies for Open-Domain Question Answering","created":"2022-11-15","cited_by_count":0,"area":null},{"id":"2605.28255","title":"AI, Take the Wheel: What Drives Delegation and Trust in Human-Computer Cooperative Question Answering?","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2605.30459","title":"Can LLM Teams Play What? Where? When?","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2610.01006","title":"Beyond Answer Confidence: A Controlled Audit of Self-Knowledge in a Black-Box Decision Model","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}