{"total":58,"rows":[{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085,"area":null},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916,"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":"2104.06039","title":"MultiModalQA: Complex Question Answering over Text, Tables and Images","created":"2021-04-13","cited_by_count":179,"area":null},{"id":"2105.09680","title":"KLUE: Korean Language Understanding Evaluation","created":"2021-05-20","cited_by_count":114,"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":"2211.08073","title":"GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective","created":"2022-11-15","cited_by_count":72,"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":"2106.01024","title":"Why Machine Reading Comprehension Models Learn Shortcuts?","created":"2021-06-02","cited_by_count":40,"area":null},{"id":"2103.05568","title":"Select, Substitute, Search: A New Benchmark for Knowledge-Augmented Visual Question Answering","created":"2021-03-09","cited_by_count":33,"area":null},{"id":"2402.14116","title":"FanOutQA: A Multi-Hop, Multi-Document Question Answering Benchmark for Large Language Models","created":"2024-02-21","cited_by_count":29,"area":null},{"id":"2104.08825","title":"Flexible Generation of Natural Language Deductions","created":"2021-04-18","cited_by_count":28,"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":"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":"2102.01065","title":"Do Question Answering Modeling Improvements Hold Across Benchmarks?","created":"2021-02-01","cited_by_count":20,"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":"2412.17032","title":"MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledge","created":"2024-12-22","cited_by_count":20,"area":null},{"id":"2202.07280","title":"Saving Dense Retriever from Shortcut Dependency in Conversational Search","created":"2022-02-15","cited_by_count":19,"area":null},{"id":"2111.04104","title":"Uncertainty Calibration for Ensemble-Based Debiasing Methods","created":"2021-11-07","cited_by_count":16,"area":null},{"id":"2103.12876","title":"Complex Factoid Question Answering with a Free-Text Knowledge Graph","created":"2021-03-23","cited_by_count":14,"area":null},{"id":"2109.10604","title":"NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset","created":"2021-09-22","cited_by_count":14,"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":"2110.08542","title":"Hey AI, Can You Solve Complex Tasks by Talking to Agents?","created":"2021-10-16","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":"2105.01974","title":"Do Natural Language Explanations Represent Valid Logical Arguments? Verifying Entailment in Explainable NLI Gold Standards","created":"2021-05-05","cited_by_count":12,"area":null},{"id":"2205.11729","title":"From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answering","created":"2022-05-24","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":"2101.06980","title":"Mitigating the Position Bias of Transformer Models in Passage Re-Ranking","created":"2021-01-18","cited_by_count":10,"area":null},{"id":"2205.09665","title":"Automated Crossword Solving","created":"2022-05-19","cited_by_count":9,"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":"2108.12844","title":"Behind the Scenes: An Exploration of Trigger Biases Problem in Few-Shot Event Classification","created":"2021-08-29","cited_by_count":8,"area":null},{"id":"2112.10572","title":"General Greedy De-bias Learning","created":"2021-12-20","cited_by_count":7,"area":null},{"id":"2104.01759","title":"Paired Examples as Indirect Supervision in Latent Decision Models","created":"2021-04-05","cited_by_count":6,"area":null},{"id":"2111.03642","title":"Grounded Graph Decoding Improves Compositional Generalization in Question Answering","created":"2021-11-05","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":"2103.13496","title":"Similarity-Based Equational Inference in Physics","created":"2021-03-24","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":"2210.08763","title":"ReasonChainQA: Text-based Complex Question Answering with Explainable Evidence Chains","created":"2022-10-17","cited_by_count":4,"area":null},{"id":"2106.03973","title":"Generating Hypothetical Events for Abductive Inference","created":"2021-06-07","cited_by_count":3,"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":"2205.03685","title":"Better Retrieval May Not Lead to Better Question Answering","created":"2022-05-07","cited_by_count":3,"area":null},{"id":"2406.03592","title":"Measuring Retrieval Complexity in Question Answering Systems","created":"2024-06-05","cited_by_count":3,"area":null},{"id":"2601.08847","title":"Scalable and Reliable Evaluation of AI Knowledge Retrieval Systems: RIKER and the Coherent Simulated Universe","created":"2025-12-22","cited_by_count":3,"area":null},{"id":"2103.11643","title":"Complementary Evidence Identification in Open-Domain Question Answering","created":"2021-03-22","cited_by_count":2,"area":null},{"id":"2104.08744","title":"Generative Context Pair Selection for Multi-hop Question Answering","created":"2021-04-18","cited_by_count":2,"area":null},{"id":"2109.07102","title":"Can Edge Probing Tasks Reveal Linguistic Knowledge in QA Models?","created":"2021-09-15","cited_by_count":2,"area":null},{"id":"2211.13331","title":"Using Focal Loss to Fight Shallow Heuristics: An Empirical Analysis of Modulated Cross-Entropy in Natural Language Inference","created":"2022-11-23","cited_by_count":2,"area":null},{"id":"2505.15087","title":"HopWeaver: Cross-Document Synthesis of High-Quality and Authentic Multi-Hop Questions","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2203.11431","title":"Task-guided Disentangled Tuning for Pretrained Language Models","created":"2022-03-22","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":"2605.26663","title":"Evidence Absence Is Not Evidence Insufficiency: Diagnosing NEI Construction Artifacts in Fact Verification","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2210.01979","title":"GAPX: Generalized Autoregressive Paraphrase-Identification X","created":"2022-10-05","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":"2606.03179","title":"HyperPatch: Sequential Knowledge Editing Under n-ary Structural Drift","created":"2026-06-02","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}