{"total":32,"rows":[{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459,"area":null},{"id":"2311.11944","title":"FinanceBench: A New Benchmark for Financial Question Answering","created":"2023-11-20","cited_by_count":270,"area":null},{"id":"2201.05966","title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","created":"2022-01-16","cited_by_count":231,"area":null},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157,"area":null},{"id":"2106.11455","title":"KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers","created":"2021-06-22","cited_by_count":106,"area":null},{"id":"2404.12241","title":"Introducing v0.5 of the AI Safety Benchmark from MLCommons","created":"2024-04-18","cited_by_count":62,"area":null},{"id":"2205.05256","title":"Evaluation Gaps in Machine Learning Practice","created":"2022-05-11","cited_by_count":49,"area":null},{"id":"2503.05336","title":"Toward an Evaluation Science for Generative AI Systems","created":"2025-03-07","cited_by_count":45,"area":null},{"id":"2407.16711","title":"Benchmarks as Microscopes: A Call for Model Metrology","created":"2024-07-22","cited_by_count":35,"area":null},{"id":"2506.07461","title":"From Calibration to Collaboration: LLM Uncertainty Quantification Should Be More Human-Centered","created":"2025-06-09","cited_by_count":21,"area":null},{"id":"2305.08195","title":"Learning to Simulate Natural Language Feedback for Interactive Semantic Parsing","created":"2023-05-14","cited_by_count":19,"area":null},{"id":"2211.08371","title":"Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approaches","created":"2022-11-15","cited_by_count":12,"area":null},{"id":"2212.03419","title":"JamPatoisNLI: A Jamaican Patois Natural Language Inference Dataset","created":"2022-12-07","cited_by_count":11,"area":null},{"id":"2210.04443","title":"Don't Copy the Teacher: Data and Model Challenges in Embodied Dialogue","created":"2022-10-10","cited_by_count":10,"area":null},{"id":"2105.14207","title":"Maintaining Common Ground in Dynamic Environments","created":"2021-05-29","cited_by_count":9,"area":null},{"id":"2311.04067","title":"Multitask Multimodal Prompted Training for Interactive Embodied Task Completion","created":"2023-11-07","cited_by_count":9,"area":null},{"id":"2110.08975","title":"Deep Transfer Learning & Beyond: Transformer Language Models in Information Systems Research","created":"2021-10-18","cited_by_count":7,"area":null},{"id":"2211.04534","title":"Going for GOAL: A Resource for Grounded Football Commentaries","created":"2022-11-08","cited_by_count":7,"area":null},{"id":"2503.19193","title":"Browsing Lost Unformed Recollections: A Benchmark for Tip-of-the-Tongue Search and Reasoning","created":"2025-03-24","cited_by_count":7,"area":null},{"id":"2304.01412","title":"The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents","created":"2023-04-03","cited_by_count":6,"area":null},{"id":"2601.07988","title":"From Word Sequences to Behavioral Sequences: Adapting Modeling and Evaluation Paradigms for Longitudinal NLP","created":"2026-01-12","cited_by_count":4,"area":null},{"id":"2106.07728","title":"Targeted Data Acquisition for Evolving Negotiation Agents","created":"2021-06-14","cited_by_count":3,"area":null},{"id":"2504.06549","title":"Societal Impacts Research Requires Benchmarks for Creative Composition Tasks","created":"2025-04-09","cited_by_count":3,"area":null},{"id":"2105.06457","title":"Conversational AI Systems for Social Good: Opportunities and Challenges","created":"2021-05-13","cited_by_count":2,"area":null},{"id":"2210.05038","title":"Fighting FIRe with FIRE: Assessing the Validity of Text-to-Video Retrieval Benchmarks","created":"2022-10-10","cited_by_count":1,"area":null},{"id":"2305.15130","title":"On Degrees of Freedom in Defining and Testing Natural Language Understanding","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2412.19490","title":"User Willingness-aware Sales Talk Dataset","created":"2024-12-27","cited_by_count":1,"area":null},{"id":"2407.19726","title":"Do Text-to-Vis Benchmarks Test Real Use of Visualisations?","created":"2024-07-29","cited_by_count":0,"area":null},{"id":"2606.18532","title":"AI Sandboxes: A Threat Model, Taxonomy, and Measurement Framework","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.31741","title":"STEB: Style Text Embedding Benchmark","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2609.08861","title":"API Benchmark Scores Do Not Reliably Transfer to Chatbot Interfaces","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2610.00606","title":"Where's Waldo? Query-language Preference under Cross-lingual Knowledge Disparities","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}