{"total":189,"rows":[{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751,"area":null},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401,"area":null},{"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":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292,"area":null},{"id":"2311.08298","title":"A Survey of Confidence Estimation and Calibration in Large Language Models","created":"2023-11-14","cited_by_count":256,"area":null},{"id":"2307.03987","title":"A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation","created":"2023-07-08","cited_by_count":206,"area":null},{"id":"2402.00367","title":"Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration","created":"2024-02-01","cited_by_count":180,"area":null},{"id":"2305.13281","title":"LM vs LM: Detecting Factual Errors via Cross Examination","created":"2023-05-22","cited_by_count":156,"area":null},{"id":"2210.13701","title":"Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence","created":"2022-10-25","cited_by_count":144,"area":null},{"id":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135,"area":null},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121,"area":null},{"id":"2401.06730","title":"Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertainty","created":"2024-01-12","cited_by_count":106,"area":null},{"id":"2407.12043","title":"The Art of Saying No: Contextual Noncompliance in Language Models","created":"2024-07-02","cited_by_count":105,"area":null},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2311.09469","title":"Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs","created":"2023-11-16","cited_by_count":98,"area":null},{"id":"2302.13439","title":"Navigating the Grey Area: How Expressions of Uncertainty and Overconfidence Affect Language Models","created":"2023-02-26","cited_by_count":91,"area":null},{"id":"2204.13631","title":"Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly","created":"2022-04-28","cited_by_count":89,"area":null},{"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":"2112.05090","title":"Extending the WILDS Benchmark for Unsupervised Adaptation","created":"2021-12-09","cited_by_count":86,"area":null},{"id":"2403.20279","title":"LUQ: Long-text Uncertainty Quantification for LLMs","created":"2024-03-29","cited_by_count":81,"area":null},{"id":"2109.06827","title":"Types of Out-of-Distribution Texts and How to Detect Them","created":"2021-09-14","cited_by_count":80,"area":null},{"id":"2209.07661","title":"On the Relation between Sensitivity and Accuracy in In-context Learning","created":"2022-09-16","cited_by_count":72,"area":null},{"id":"2106.06600","title":"Break-It-Fix-It: Unsupervised Learning for Program Repair","created":"2021-06-11","cited_by_count":71,"area":null},{"id":"2101.03778","title":"Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection","created":"2021-01-11","cited_by_count":70,"area":null},{"id":"2401.00287","title":"The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness","created":"2023-12-30","cited_by_count":67,"area":null},{"id":"2410.13284","title":"Learning to Route LLMs with Confidence Tokens","created":"2024-10-17","cited_by_count":67,"area":null},{"id":"2203.00211","title":"Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settings","created":"2022-03-01","cited_by_count":66,"area":null},{"id":"2305.14613","title":"Selectively Answering Ambiguous Questions","created":"2023-05-24","cited_by_count":66,"area":null},{"id":"2107.02331","title":"Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering","created":"2021-07-06","cited_by_count":62,"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":"2405.01563","title":"Mitigating LLM Hallucinations via Conformal Abstention","created":"2024-04-04","cited_by_count":59,"area":null},{"id":"2211.15259","title":"A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification","created":"2022-11-28","cited_by_count":52,"area":null},{"id":"2106.01494","title":"Knowing More About Questions Can Help: Improving Calibration in Question Answering","created":"2021-06-02","cited_by_count":47,"area":null},{"id":"2402.03563","title":"Distinguishing the Knowable from the Unknowable with Language Models","created":"2024-02-05","cited_by_count":47,"area":null},{"id":"2104.08731","title":"Can NLI Models Verify QA Systems' Predictions?","created":"2021-04-18","cited_by_count":46,"area":null},{"id":"2402.18048","title":"Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension","created":"2024-02-28","cited_by_count":45,"area":null},{"id":"2306.04459","title":"Uncertainty in Natural Language Processing: Sources, Quantification, and Applications","created":"2023-06-05","cited_by_count":44,"area":null},{"id":"2110.07803","title":"Attacking Open-domain Question Answering by Injecting Misinformation","created":"2021-10-15","cited_by_count":41,"area":null},{"id":"2311.08877","title":"Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation","created":"2023-11-15","cited_by_count":39,"area":null},{"id":"2107.02153","title":"FaVIQ: FAct Verification from Information-seeking Questions","created":"2021-07-05","cited_by_count":36,"area":null},{"id":"2208.12084","title":"Calibrated Selective Classification","created":"2022-08-25","cited_by_count":33,"area":null},{"id":"2301.09044","title":"Learning to Reject with a Fixed Predictor: Application to Decontextualization","created":"2023-01-22","cited_by_count":32,"area":null},{"id":"2402.06544","title":"Calibrating Long-form Generations from Large Language Models","created":"2024-02-09","cited_by_count":32,"area":null},{"id":"2305.03236","title":"A Survey on Out-of-Distribution Detection in NLP","created":"2023-05-05","cited_by_count":31,"area":null},{"id":"2305.13282","title":"Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection","created":"2023-05-22","cited_by_count":29,"area":null},{"id":"2109.13986","title":"Symbolic Brittleness in Sequence Models: on Systematic Generalization in Symbolic Mathematics","created":"2021-09-28","cited_by_count":27,"area":null},{"id":"2207.07506","title":"Augmenting Softmax Information for Selective Classification with Out-of-Distribution Data","created":"2022-07-15","cited_by_count":27,"area":null},{"id":"2412.06676","title":"I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token","created":"2024-12-09","cited_by_count":26,"area":null},{"id":"2210.15452","title":"Exploring Predictive Uncertainty and Calibration in NLP: A Study on the Impact of Method & Data Scarcity","created":"2022-10-20","cited_by_count":25,"area":null},{"id":"2306.08751","title":"Improving Selective Visual Question Answering by Learning from Your Peers","created":"2023-06-14","cited_by_count":25,"area":null},{"id":"2106.05532","title":"How Robust are Model Rankings: A Leaderboard Customization Approach for Equitable Evaluation","created":"2021-06-10","cited_by_count":24,"area":null},{"id":"2410.13246","title":"Atomic Calibration of LLMs in Long-Form Generations","created":"2024-10-17","cited_by_count":24,"area":null},{"id":"2310.13544","title":"A Diachronic Perspective on User Trust in AI under Uncertainty","created":"2023-10-20","cited_by_count":23,"area":null},{"id":"2103.11263","title":"Self-Supervised Test-Time Learning for Reading Comprehension","created":"2021-03-20","cited_by_count":22,"area":null},{"id":"2312.04021","title":"A Study on the Calibration of In-context Learning","created":"2023-12-07","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":"2305.14824","title":"Mitigating Temporal Misalignment by Discarding Outdated Facts","created":"2023-05-24","cited_by_count":21,"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":"2108.13854","title":"Contrastive Domain Adaptation for Question Answering using Limited Text Corpora","created":"2021-08-31","cited_by_count":20,"area":null},{"id":"2109.03079","title":"GOLD: Improving Out-of-Scope Detection in Dialogues using Data Augmentation","created":"2021-09-07","cited_by_count":20,"area":null},{"id":"2110.07586","title":"Can Explanations Be Useful for Calibrating Black Box Models?","created":"2021-10-14","cited_by_count":20,"area":null},{"id":"2210.02498","title":"Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model","created":"2022-10-05","cited_by_count":20,"area":null},{"id":"2305.01812","title":"Post-Abstention: Towards Reliably Re-Attempting the Abstained Instances in QA","created":"2023-05-02","cited_by_count":20,"area":null},{"id":"2502.19110","title":"Conformal Linguistic Calibration: Trading-off between Factuality and Specificity","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2109.07009","title":"Will this Question be Answered? Question Filtering via Answer Model Distillation for Efficient Question Answering","created":"2021-09-14","cited_by_count":19,"area":null},{"id":"2204.12708","title":"On the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlations","created":"2022-04-27","cited_by_count":19,"area":null},{"id":"2401.04695","title":"Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answers","created":"2024-01-09","cited_by_count":18,"area":null},{"id":"2502.16820","title":"Uncertainty Quantification of Large Language Models through Multi-Dimensional Responses","created":"2025-02-24","cited_by_count":18,"area":null},{"id":"2309.07822","title":"CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration","created":"2023-09-14","cited_by_count":17,"area":null},{"id":"2311.15451","title":"Uncertainty-aware Language Modeling for Selective Question Answering","created":"2023-11-26","cited_by_count":16,"area":null},{"id":"2406.01806","title":"Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation","created":"2024-06-03","cited_by_count":16,"area":null},{"id":"2406.05213","title":"On Subjective Uncertainty Quantification and Calibration in Natural Language Generation","created":"2024-06-07","cited_by_count":16,"area":null},{"id":"2407.07950","title":"Rel-A.I.: An Interaction-Centered Approach To Measuring Human-LM Reliance","created":"2024-07-10","cited_by_count":16,"area":null},{"id":"2505.24858","title":"MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs","created":"2025-05-30","cited_by_count":16,"area":null},{"id":"2402.16102","title":"Interpreting Predictive Probabilities: Model Confidence or Human Label Variation?","created":"2024-02-25","cited_by_count":15,"area":null},{"id":"2406.15948","title":"Teaching LLMs to Abstain across Languages via Multilingual Feedback","created":"2024-06-22","cited_by_count":14,"area":null},{"id":"2407.01942","title":"Certainly Uncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness","created":"2024-07-02","cited_by_count":14,"area":null},{"id":"2503.14481","title":"Don't lie to your friends: Learning what you know from collaborative self-play","created":"2025-03-18","cited_by_count":14,"area":null},{"id":"2504.05278","title":"The challenge of uncertainty quantification of large language models in medicine","created":"2025-04-07","cited_by_count":14,"area":null},{"id":"2609.24052","title":"Calibrated Decisions at Scale: Converting Police Crash Narratives into Probabilistic Crash Variables with a System One Model (Jev)","created":"2026-09-21","cited_by_count":14,"area":null},{"id":"2212.10784","title":"Can NLI Provide Proper Indirect Supervision for Low-resource Biomedical Relation Extraction?","created":"2022-12-21","cited_by_count":13,"area":null},{"id":"2408.14141","title":"Crowd-Calibrator: Can Annotator Disagreement Inform Calibration in Subjective Tasks?","created":"2024-08-26","cited_by_count":13,"area":null},{"id":"2410.06615","title":"QA-Calibration of Language Model Confidence Scores","created":"2024-10-09","cited_by_count":13,"area":null},{"id":"2212.10002","title":"Defending Against Disinformation Attacks in Open-Domain Question Answering","created":"2022-12-20","cited_by_count":12,"area":null},{"id":"2405.05160","title":"Selective Classification Under Distribution Shifts","created":"2024-05-08","cited_by_count":12,"area":null},{"id":"2202.00254","title":"Active Learning Over Multiple Domains in Natural Language Tasks","created":"2022-02-01","cited_by_count":11,"area":null},{"id":"2203.10623","title":"Calibration of Machine Reading Systems at Scale","created":"2022-03-20","cited_by_count":11,"area":null},{"id":"2108.12731","title":"$k$Folden: $k$-Fold Ensemble for Out-Of-Distribution Detection","created":"2021-08-29","cited_by_count":10,"area":null},{"id":"2211.12707","title":"Can Open-Domain QA Reader Utilize External Knowledge Efficiently like Humans?","created":"2022-11-23","cited_by_count":10,"area":null},{"id":"2305.14802","title":"Estimating Large Language Model Capabilities without Labeled Test Data","created":"2023-05-24","cited_by_count":9,"area":null},{"id":"2105.14875","title":"Bangla Natural Language Processing: A Comprehensive Analysis of Classical, Machine Learning, and Deep Learning Based Methods","created":"2021-05-31","cited_by_count":8,"area":null},{"id":"2306.04974","title":"Conservative Prediction via Data-Driven Confidence Minimization","created":"2023-06-08","cited_by_count":8,"area":null},{"id":"2412.12527","title":"When to Speak, When to Abstain: Contrastive Decoding with Abstention","created":"2024-12-17","cited_by_count":8,"area":null},{"id":"2209.04998","title":"Domain Adaptation for Question Answering via Question Classification","created":"2022-09-12","cited_by_count":7,"area":null},{"id":"2602.13540","title":"On Calibration of Large Language Models: From Response To Capability","created":"2026-02-14","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":"2210.12865","title":"Knowledge Transfer from Answer Ranking to Answer Generation","created":"2022-10-23","cited_by_count":6,"area":null},{"id":"2311.08669","title":"On the Calibration of Multilingual Question Answering LLMs","created":"2023-11-15","cited_by_count":6,"area":null},{"id":"2606.00093","title":"Agreement Metrics for LLM-as-Judge Evaluation: What to Report and Why","created":"2026-05-25","cited_by_count":6,"area":null},{"id":"2402.16300","title":"Conformalized Selective Regression","created":"2024-02-26","cited_by_count":5,"area":null}],"next_cursor":"100"}