{"total":51,"rows":[{"id":"2305.19187","title":"Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models","created":"2023-05-30","cited_by_count":293,"area":null},{"id":"2311.09807","title":"The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text","created":"2023-11-16","cited_by_count":100,"area":null},{"id":"2503.15850","title":"Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey","created":"2025-03-20","cited_by_count":95,"area":"lr"},{"id":"2405.16908","title":"Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words?","created":"2024-05-27","cited_by_count":87,"area":null},{"id":"2412.14737","title":"On Verbalized Confidence Scores for LLMs","created":"2024-12-19","cited_by_count":83,"area":null},{"id":"2307.15703","title":"Uncertainty in Natural Language Generation: From Theory to Applications","created":"2023-07-28","cited_by_count":61,"area":null},{"id":"2412.10271","title":"Benchmarking Linguistic Diversity of Large Language Models","created":"2024-12-13","cited_by_count":38,"area":null},{"id":"2402.02896","title":"LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models","created":"2024-02-05","cited_by_count":33,"area":"agents"},{"id":"2403.00025","title":"On the Challenges and Opportunities in Generative AI","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2310.13676","title":"Information Value: Measuring Utterance Predictability as Distance from Plausible Alternatives","created":"2023-10-20","cited_by_count":23,"area":null},{"id":"2311.09799","title":"How Far Can We Extract Diverse Perspectives from Large Language Models?","created":"2023-11-16","cited_by_count":22,"area":null},{"id":"2410.15956","title":"Do Large Language Models Have an English Accent? Evaluating and Improving the Naturalness of Multilingual LLMs","created":"2024-10-21","cited_by_count":19,"area":null},{"id":"2510.01218","title":"Control the Temperature: Selective Sampling for Diverse and High-Quality LLM Outputs","created":"2025-09-20","cited_by_count":15,"area":null},{"id":"2403.00998","title":"Predictions from language models for multiple-choice tasks are not robust under variation of scoring methods","created":"2024-03-01","cited_by_count":13,"area":null},{"id":"2310.14840","title":"Transparency at the Source: Evaluating and Interpreting Language Models With Access to the True Distribution","created":"2023-10-23","cited_by_count":10,"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":"2412.13942","title":"A Rose by Any Other Name: LLM-Generated Explanations Are Good Proxies for Human Explanations to Collect Label Distributions on NLI","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2510.08460","title":"LeWiDi-2025 at NLPerspectives: Third Edition of the Learning with Disagreements Shared Task","created":"2025-10-09","cited_by_count":9,"area":null},{"id":"2406.16767","title":"The GPT-WritingPrompts Dataset: A Comparative Analysis of Character Portrayal in Short Stories","created":"2024-06-24","cited_by_count":8,"area":null},{"id":"2501.02020","title":"Enhancing Uncertainty Modeling with Semantic Graph for Hallucination Detection","created":"2025-01-02","cited_by_count":8,"area":null},{"id":"2401.10415","title":"Can Large Language Model Summarizers Adapt to Diverse Scientific Communication Goals?","created":"2024-01-18","cited_by_count":6,"area":null},{"id":"2407.04559","title":"Not (yet) the whole story: Evaluating Visual Storytelling Requires More than Measuring Coherence, Grounding, and Repetition","created":"2024-07-05","cited_by_count":5,"area":null},{"id":"2410.12057","title":"Large-scale cloze evaluation reveals that token prediction tasks are neither lexically nor semantically aligned","created":"2024-10-15","cited_by_count":5,"area":null},{"id":"2510.16458","title":"Agree, Disagree, Explain: Decomposing Human Label Variation in NLI through the Lens of Explanations","created":"2025-10-18","cited_by_count":5,"area":null},{"id":"2311.05020","title":"First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models","created":"2023-11-08","cited_by_count":4,"area":null},{"id":"2311.13061","title":"Attribution and Alignment: Effects of Local Context Repetition on Utterance Production and Comprehension in Dialogue","created":"2023-11-21","cited_by_count":4,"area":null},{"id":"2311.15180","title":"Benchmarking Large Language Model Volatility","created":"2023-11-26","cited_by_count":4,"area":null},{"id":"2402.17527","title":"Predict the Next Word: Humans exhibit uncertainty in this task and language models _____","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2407.01878","title":"Compare without Despair: Reliable Preference Evaluation with Generation Separability","created":"2024-07-02","cited_by_count":4,"area":null},{"id":"2502.11874","title":"VAQUUM: Are Vague Quantifiers Grounded in Visual Data?","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2505.22848","title":"LiTEx: A Linguistic Taxonomy of Explanations for Understanding Within-Label Variation in Natural Language Inference","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2505.23183","title":"Unsupervised Word-level Quality Estimation for Machine Translation Through the Lens of Annotators (Dis)agreement","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2509.23088","title":"The Geometry of Creative Variability: How Credal Sets Expose Calibration Gaps in Language Models","created":"2025-09-27","cited_by_count":4,"area":null},{"id":"2510.13709","title":"Training LLM Agents to Empower Humans","created":"2025-10-15","cited_by_count":3,"area":"agents"},{"id":"2506.14335","title":"References Matter: Investigating the Impact of Reference Set Variation on Summarization Evaluation","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2510.20700","title":"Structure-Conditional Minimum Bayes Risk Decoding","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2605.25358","title":"AI-Associated Lexical Shifts Across 34 Languages: Cross-Lingual Convergence and Diachronic Uptake in News Writing","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2506.16584","title":"Measuring Intent Comprehension in LLMs","created":"2025-06-19","cited_by_count":1,"area":null},{"id":"2508.09614","title":"How Persuasive Could LLMs Be? A First Study Combining Linguistic-Rhetorical Analysis and User Experiments","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2604.17323","title":"A Universal Avoidance Method for Diverse Multi-branch Generation","created":"2026-04-19","cited_by_count":1,"area":null},{"id":"2605.00506","title":"Surprisal Minimisation over Goal-directed Alternatives Predicts Production Choice in Dialogue","created":"2026-05-01","cited_by_count":1,"area":null},{"id":"2605.25831","title":"Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2605.28802","title":"Human Label Variation as Stable Signal: Learning Annotator-Specific Explanation Behavior via Cross-Annotator Preference Optimization","created":"2026-05-27","cited_by_count":1,"area":"alignment"},{"id":"2509.20088","title":"Causal Understanding by LLMs: The Role of Uncertainty","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2511.04754","title":"Surprisal reveals diversity gaps in image captioning and different scorers change the story","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2511.08949","title":"EVADE: LLM-Based Explanation Generation and Validation for Error Detection in NLI","created":"2025-11-12","cited_by_count":0,"area":null},{"id":"2602.17848","title":"On the scaling relationship between cloze probabilities and language model next-token prediction","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2606.00334","title":"Isolating LLM Lexical Bias: A Curation-Free Triangulated Metric for Preference-Stage Learning","created":"2026-05-29","cited_by_count":0,"area":"alignment"},{"id":"2606.03165","title":"Fully Automated Identification of Lexical Alignment and Preference-Stage Shifts in Large Language Models","created":"2026-06-02","cited_by_count":0,"area":"alignment"},{"id":"2609.26527","title":"A Semiotics-Aware Framework for Evaluating Fidelity and Coverage in Natural Language Generation","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.31506","title":"Evaluating Cultural Awareness of LLMs for Haitian Creole","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}