{"list":"other","total":65,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"1906.02530","title":"Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift","created":"2019-06-06","cited_by_count":1287},{"id":"2306.13063","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","created":"2023-06-22","cited_by_count":974},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"2305.14975","title":"Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback","created":"2023-05-24","cited_by_count":812},{"id":"2212.03827","title":"Discovering Latent Knowledge in Language Models Without Supervision","created":"2022-12-07","cited_by_count":767},{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"id":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712},{"id":"2304.13734","title":"The Internal State of an LLM Knows When It's Lying","created":"2023-04-26","cited_by_count":659},{"id":"2012.00955","title":"How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering","created":"2020-12-02","cited_by_count":445},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422},{"id":"2106.07998","title":"Revisiting the Calibration of Modern Neural Networks","created":"2021-06-15","cited_by_count":390},{"id":"2403.03853","title":"ShortGPT: Layers in Large Language Models are More Redundant Than You Expect","created":"2024-03-06","cited_by_count":383},{"id":"2402.10588","title":"Do Llamas Work in English? On the Latent Language of Multilingual Transformers","created":"2024-02-16","cited_by_count":281},{"id":"2311.08298","title":"A Survey of Confidence Estimation and Calibration in Large Language Models","created":"2023-11-14","cited_by_count":256},{"id":"2007.15207","title":"MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering","created":"2020-07-30","cited_by_count":153},{"id":"2402.18815","title":"How do Large Language Models Handle Multilingualism?","created":"2024-02-29","cited_by_count":150},{"id":"2310.10378","title":"Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models","created":"2023-10-16","cited_by_count":118},{"id":"2305.16339","title":"Don't Trust ChatGPT when Your Question is not in English: A Study of Multilingual Abilities and Types of LLMs","created":"2023-05-24","cited_by_count":104},{"id":"2404.02431","title":"On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons","created":"2024-04-03","cited_by_count":83},{"id":"2407.03282","title":"LLM Internal States Reveal Hallucination Risk Faced With a Query","created":"2024-07-03","cited_by_count":82},{"id":"2502.15603","title":"Do Multilingual LLMs Think In English?","created":"2025-02-21","cited_by_count":78},{"id":"2404.15993","title":"Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach","created":"2024-04-24","cited_by_count":76},{"id":"2311.13240","title":"On the Calibration of Large Language Models and Alignment","created":"2023-11-22","cited_by_count":73},{"id":"1909.02197","title":"Investigating Multilingual NMT Representations at Scale","created":"2019-09-05","cited_by_count":68},{"id":"2403.05973","title":"Calibrating Large Language Models Using Their Generations Only","created":"2024-03-09","cited_by_count":65},{"id":"2505.14489","title":"Reasoning Models Better Express Their Confidence","created":"2025-05-20","cited_by_count":65},{"id":"2402.16061","title":"How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study","created":"2024-02-25","cited_by_count":64},{"id":"2502.05795","title":"The Curse of Depth in Large Language Models","created":"2025-02-09","cited_by_count":62},{"id":"2307.15703","title":"Uncertainty in Natural Language Generation: From Theory to Applications","created":"2023-07-28","cited_by_count":61},{"id":"2501.06346","title":"Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages","created":"2025-01-10","cited_by_count":59},{"id":"2410.15326","title":"A Survey of Uncertainty Estimation in LLMs: Theory Meets Practice","created":"2024-10-20","cited_by_count":55},{"id":"2402.09733","title":"Do LLMs Know about Hallucination? An Empirical Investigation of LLM's Hidden States","created":"2024-02-15","cited_by_count":52},{"id":"2205.00403","title":"A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness","created":"2022-05-01","cited_by_count":49},{"id":"2503.14477","title":"Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations","created":"2025-03-18","cited_by_count":48},{"id":"2310.19208","title":"LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses","created":"2023-10-30","cited_by_count":44},{"id":"2401.08329","title":"Understanding User Experience in Large Language Model Interactions","created":"2024-01-16","cited_by_count":44},{"id":"2411.08745","title":"Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers","created":"2024-11-13","cited_by_count":44},{"id":"2507.02856","title":"Answer Matching Outperforms Multiple Choice for Language Model Evaluation","created":"2025-07-03","cited_by_count":41},{"id":"2406.13229","title":"Probing the Emergence of Cross-lingual Alignment during LLM Training","created":"2024-06-19","cited_by_count":39},{"id":"2406.09265","title":"Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs","created":"2024-06-13","cited_by_count":33},{"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},{"id":"2410.13246","title":"Atomic Calibration of LLMs in Long-Form Generations","created":"2024-10-17","cited_by_count":24},{"id":"2410.11718","title":"Converging to a Lingua Franca: Evolution of Linguistic Regions and Semantics Alignment in Multilingual Large Language Models","created":"2024-10-15","cited_by_count":23},{"id":"2504.12459","title":"On Linear Representations and Pretraining Data Frequency in Language Models","created":"2025-04-16","cited_by_count":23},{"id":"2505.21772","title":"Calibrating LLM Confidence by Probing Perturbed Representation Stability","created":"2025-05-27","cited_by_count":23},{"id":"2505.08200","title":"A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs","created":"2025-05-13","cited_by_count":21},{"id":"2210.12265","title":"On the Calibration of Massively Multilingual Language Models","created":"2022-10-21","cited_by_count":19},{"id":"2506.00823","title":"Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks","created":"2025-06-01","cited_by_count":18},{"id":"2502.14634","title":"CER: Confidence Enhanced Reasoning in LLMs","created":"2025-02-20","cited_by_count":17},{"id":"2507.10587","title":"Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing","created":"2025-07-11","cited_by_count":14},{"id":"2502.07424","title":"RomanLens: The Role Of Latent Romanization In Multilinguality In LLMs","created":"2025-02-11","cited_by_count":12},{"id":"2510.03136","title":"Beyond the Final Layer: Intermediate Representations for Better Multilingual Calibration in Large Language Models","created":"2025-10-03","cited_by_count":10},{"id":"2509.17030","title":"The Transfer Neurons Hypothesis: An Underlying Mechanism for Language Latent Space Transitions in Multilingual LLMs","created":"2025-09-21","cited_by_count":8},{"id":"2311.08669","title":"On the Calibration of Multilingual Question Answering LLMs","created":"2023-11-15","cited_by_count":6},{"id":"2502.10871","title":"Layerwise Recall and the Geometry of Interwoven Knowledge in LLMs","created":"2025-02-15","cited_by_count":6},{"id":"1701.05964","title":"Centered Isotonic Regression: Point and Interval Estimation for Dose-Response Studies","created":"2017-01-21","cited_by_count":5},{"id":"2602.17431","title":"Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study","created":"2026-02-19","cited_by_count":4},{"id":"2305.05098","title":"Who Needs Decoders? Efficient Estimation of Sequence-level Attributes","created":"2023-05-09","cited_by_count":3},{"id":"2604.15109","title":"IUQ: Interrogative Uncertainty Quantification for Long-Form Large Language Model Generation","created":"2026-04-16","cited_by_count":1}],"next_cursor":null}