{"total":31,"rows":[{"id":"2304.14399","title":"We're Afraid Language Models Aren't Modeling Ambiguity","created":"2023-04-27","cited_by_count":126,"area":null},{"id":"2210.16133","title":"Stop Measuring Calibration When Humans Disagree","created":"2022-10-28","cited_by_count":71,"area":null},{"id":"2201.06028","title":"Natural Language Deduction through Search over Statement Compositions","created":"2022-01-16","cited_by_count":35,"area":null},{"id":"2104.08676","title":"Distributed NLI: Learning to Predict Human Opinion Distributions for Language Reasoning","created":"2021-04-18","cited_by_count":31,"area":null},{"id":"2410.03775","title":"Beyond correlation: The Impact of Human Uncertainty in Measuring the Effectiveness of Automatic Evaluation and LLM-as-a-Judge","created":"2024-10-03","cited_by_count":31,"area":null},{"id":"2109.04408","title":"Learning with Different Amounts of Annotation: From Zero to Many Labels","created":"2021-09-09","cited_by_count":28,"area":null},{"id":"2305.17388","title":"MPCHAT: Towards Multimodal Persona-Grounded Conversation","created":"2023-05-27","cited_by_count":24,"area":null},{"id":"2106.03020","title":"Embracing Ambiguity: Shifting the Training Target of NLI Models","created":"2021-06-06","cited_by_count":23,"area":null},{"id":"2109.06987","title":"NOPE: A Corpus of Naturally-Occurring Presuppositions in English","created":"2021-09-14","cited_by_count":23,"area":null},{"id":"2112.04596","title":"Refined Commonsense Knowledge from Large-Scale Web Contents","created":"2021-11-30","cited_by_count":19,"area":null},{"id":"2404.12494","title":"BIRD: A Trustworthy Bayesian Inference Framework for Large Language Models","created":"2024-04-18","cited_by_count":18,"area":null},{"id":"2306.00824","title":"Zero and Few-shot Semantic Parsing with Ambiguous Inputs","created":"2023-06-01","cited_by_count":16,"area":null},{"id":"2304.00815","title":"Design Choices for Crowdsourcing Implicit Discourse Relations: Revealing the Biases Introduced by Task Design","created":"2023-04-03","cited_by_count":14,"area":null},{"id":"2210.03102","title":"Ambiguous Images With Human Judgments for Robust Visual Event Classification","created":"2022-10-06","cited_by_count":12,"area":null},{"id":"2305.14770","title":"Using Natural Language Explanations to Rescale Human Judgments","created":"2023-05-24","cited_by_count":11,"area":null},{"id":"2110.08355","title":"Clean or Annotate: How to Spend a Limited Data Collection Budget","created":"2021-10-15","cited_by_count":10,"area":null},{"id":"2307.07049","title":"MegaWika: Millions of reports and their sources across 50 diverse languages","created":"2023-07-13","cited_by_count":9,"area":null},{"id":"2505.01595","title":"Always Tell Me The Odds: Fine-grained Conditional Probability Estimation","created":"2025-05-02","cited_by_count":9,"area":null},{"id":"2308.04114","title":"Collective Human Opinions in Semantic Textual Similarity","created":"2023-08-08","cited_by_count":8,"area":null},{"id":"2211.03358","title":"Probing neural language models for understanding of words of estimative probability","created":"2022-11-07","cited_by_count":7,"area":null},{"id":"2102.06859","title":"Capturing Label Distribution: A Case Study in NLI","created":"2021-02-13","cited_by_count":6,"area":null},{"id":"2302.06976","title":"Investigating Multi-source Active Learning for Natural Language Inference","created":"2023-02-14","cited_by_count":6,"area":null},{"id":"2304.04726","title":"Uncertainty-Aware Natural Language Inference with Stochastic Weight Averaging","created":"2023-04-10","cited_by_count":4,"area":null},{"id":"2210.17238","title":"Pneg: Prompt-based Negative Response Generation for Dialogue Response Selection Task","created":"2022-10-31","cited_by_count":3,"area":null},{"id":"2412.16232","title":"Defeasible Visual Entailment: Benchmark, Evaluator, and Reward-Driven Optimization","created":"2024-12-19","cited_by_count":3,"area":null},{"id":"2406.04756","title":"Interpretable Multimodal Out-of-context Detection with Soft Logic Regularization","created":"2024-06-07","cited_by_count":2,"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":"2504.03640","title":"Bonsai: Interpretable Tree-Adaptive Grounded Reasoning","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2602.23546","title":"Humans and LLMs Diverge on Probabilistic Inferences","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2305.14091","title":"Revisiting Acceptability Judgements","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2510.22897","title":"Charting the Design Space of Neural Graph Representations for Subgraph Matching","created":"2025-10-27","cited_by_count":0,"area":null}],"next_cursor":null}