{"total":22,"rows":[{"id":"2204.06092","title":"ASQA: Factoid Questions Meet Long-Form Answers","created":"2022-04-12","cited_by_count":234,"area":null},{"id":"2407.09413","title":"SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers","created":"2024-07-12","cited_by_count":75,"area":null},{"id":"2402.04315","title":"Training Language Models to Generate Text with Citations via Fine-grained Rewards","created":"2024-02-06","cited_by_count":42,"area":null},{"id":"2407.10701","title":"DOCBENCH: A Benchmark for Evaluating LLM-based Document Reading Systems","created":"2024-07-15","cited_by_count":37,"area":null},{"id":"2212.10711","title":"Task Ambiguity in Humans and Language Models","created":"2022-12-20","cited_by_count":28,"area":null},{"id":"2207.00746","title":"INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactions","created":"2022-07-02","cited_by_count":27,"area":null},{"id":"2206.15030","title":"Modern Question Answering Datasets and Benchmarks: A Survey","created":"2022-06-30","cited_by_count":23,"area":null},{"id":"2502.13668","title":"PeerQA: A Scientific Question Answering Dataset from Peer Reviews","created":"2025-02-19","cited_by_count":22,"area":null},{"id":"2403.15879","title":"TrustSQL: Benchmarking Text-to-SQL Reliability with Penalty-Based Scoring","created":"2024-03-23","cited_by_count":17,"area":null},{"id":"2302.02601","title":"Learning Representations of Bi-level Knowledge Graphs for Reasoning beyond Link Prediction","created":"2023-02-06","cited_by_count":9,"area":null},{"id":"2407.10691","title":"$\\texttt{MixGR}$: Enhancing Retriever Generalization for Scientific Domain through Complementary Granularity","created":"2024-07-15","cited_by_count":9,"area":null},{"id":"2409.13879","title":"\"I Never Said That\": A dataset, taxonomy and baselines on response clarity classification","created":"2024-09-20","cited_by_count":9,"area":null},{"id":"2511.09008","title":"A Neurosymbolic Approach to Natural Language Formalization and Verification","created":"2025-11-12","cited_by_count":9,"area":null},{"id":"2308.08661","title":"Answering Ambiguous Questions with a Database of Questions, Answers, and Revisions","created":"2023-08-16","cited_by_count":4,"area":null},{"id":"2205.12898","title":"Reasoning over Logically Interacted Conditions for Question Answering","created":"2022-05-25","cited_by_count":3,"area":null},{"id":"2312.01143","title":"Towards leveraging LLMs for Conditional QA","created":"2023-12-02","cited_by_count":2,"area":null},{"id":"2403.04314","title":"Can Your Model Tell a Negation from an Implicature? Unravelling Challenges With Intent Encoders","created":"2024-03-07","cited_by_count":2,"area":null},{"id":"2509.03540","title":"Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction","created":"2025-08-31","cited_by_count":2,"area":null},{"id":"2408.05442","title":"Chain of Condition: Construct, Verify and Solve Conditions for Conditional Question Answering","created":"2024-08-10","cited_by_count":1,"area":null},{"id":"2404.08666","title":"Revealing Trends in Datasets from the 2022 ACL and EMNLP Conferences","created":"2024-03-31","cited_by_count":0,"area":null},{"id":"2410.03950","title":"Structured List-Grounded Question Answering","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2609.39608","title":"Is This Evidence Decision-Critical? Learning to Verify Rule-Governed Decisions","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}