{"list":"other","total":78,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2211.12588","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","created":"2022-11-22","cited_by_count":1076},{"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":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"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":"2303.08896","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","created":"2023-03-15","cited_by_count":810},{"id":"2205.14334","title":"Teaching Models to Express Their Uncertainty in Words","created":"2022-05-28","cited_by_count":751},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680},{"id":"2305.12295","title":"Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning","created":"2023-05-20","cited_by_count":391},{"id":"2006.10108","title":"Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness","created":"2020-06-17","cited_by_count":389},{"id":"2009.03393","title":"Generative Language Modeling for Automated Theorem Proving","created":"2020-09-07","cited_by_count":388},{"id":"2002.06715","title":"BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning","created":"2020-02-17","cited_by_count":371},{"id":"2210.01240","title":"Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought","created":"2022-10-03","cited_by_count":337},{"id":"2012.13048","title":"ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language","created":"2020-12-24","cited_by_count":324},{"id":"2305.19187","title":"Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models","created":"2023-05-30","cited_by_count":293},{"id":"2210.12283","title":"Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs","created":"2022-10-21","cited_by_count":291},{"id":"2301.13867","title":"Mathematical Capabilities of ChatGPT","created":"2023-01-31","cited_by_count":268},{"id":"2205.12615","title":"Autoformalization with Large Language Models","created":"2022-05-25","cited_by_count":263},{"id":"2209.00840","title":"FOLIO: Natural Language Reasoning with First-Order Logic","created":"2022-09-02","cited_by_count":235},{"id":"2405.14333","title":"DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data","created":"2024-05-23","cited_by_count":234},{"id":"2205.11491","title":"HyperTree Proof Search for Neural Theorem Proving","created":"2022-05-23","cited_by_count":197},{"id":"2310.15164","title":"LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers","created":"2023-10-23","cited_by_count":168},{"id":"2311.07383","title":"LM-Polygraph: Uncertainty Estimation for Language Models","created":"2023-11-13","cited_by_count":131},{"id":"2209.03302","title":"Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?","created":"2022-09-07","cited_by_count":125},{"id":"2308.16175","title":"Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness","created":"2023-08-30","cited_by_count":122},{"id":"2402.12348","title":"GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations","created":"2024-02-19","cited_by_count":120},{"id":"2303.04910","title":"Baldur: Whole-Proof Generation and Repair with Large Language Models","created":"2023-03-08","cited_by_count":119},{"id":"2311.08718","title":"Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling","created":"2023-11-15","cited_by_count":114},{"id":"2310.00656","title":"LEGO-Prover: Neural Theorem Proving with Growing Libraries","created":"2023-10-01","cited_by_count":109},{"id":"2305.09656","title":"SatLM: Satisfiability-Aided Language Models Using Declarative Prompting","created":"2023-05-16","cited_by_count":102},{"id":"2205.10893","title":"Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers","created":"2022-05-22","cited_by_count":98},{"id":"2311.01740","title":"SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency","created":"2023-11-03","cited_by_count":90},{"id":"2310.04353","title":"An In-Context Learning Agent for Formal Theorem-Proving","created":"2023-10-06","cited_by_count":82},{"id":"1811.07253","title":"Quantifying Uncertainties in Natural Language Processing Tasks","created":"2018-11-18","cited_by_count":79},{"id":"2205.12910","title":"NaturalProver: Grounded Mathematical Proof Generation with Language Models","created":"2022-05-25","cited_by_count":72},{"id":"2305.14613","title":"Selectively Answering Ambiguous Questions","created":"2023-05-24","cited_by_count":66},{"id":"2309.04295","title":"FIMO: A Challenge Formal Dataset for Automated Theorem Proving","created":"2023-09-08","cited_by_count":55},{"id":"2403.18120","title":"Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization","created":"2024-03-26","cited_by_count":55},{"id":"2305.14264","title":"Active Learning Principles for In-Context Learning with Large Language Models","created":"2023-05-23","cited_by_count":54},{"id":"2405.02917","title":"Overconfidence is Key: Verbalized Uncertainty Evaluation in Large Language and Vision-Language Models","created":"2024-05-05","cited_by_count":54},{"id":"1805.06502","title":"First Experiments with Neural Translation of Informal to Formal Mathematics","created":"2018-05-10","cited_by_count":53},{"id":"1901.02731","title":"A Comprehensive guide to Bayesian Convolutional Neural Network with Variational Inference","created":"2019-01-08","cited_by_count":51},{"id":"1806.00608","title":"GamePad: A Learning Environment for Theorem Proving","created":"2018-06-02","cited_by_count":48},{"id":"1701.06972","title":"Deep Network Guided Proof Search","created":"2017-01-24","cited_by_count":47},{"id":"2402.08957","title":"MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data","created":"2024-02-14","cited_by_count":43},{"id":"1912.02636","title":"Exploration of Neural Machine Translation in Autoformalization of Mathematics in Mizar","created":"2019-12-05","cited_by_count":40},{"id":"2102.09756","title":"TacticZero: Learning to Prove Theorems from Scratch with Deep Reinforcement Learning","created":"2021-02-19","cited_by_count":37},{"id":"2405.01379","title":"Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving","created":"2024-05-02","cited_by_count":35},{"id":"1608.02644","title":"Holophrasm: a neural Automated Theorem Prover for higher-order logic","created":"2016-08-08","cited_by_count":29},{"id":"2403.13312","title":"LeanReasoner: Boosting Complex Logical Reasoning with Lean","created":"2024-03-20","cited_by_count":28},{"id":"2405.17216","title":"Autoformalizing Euclidean Geometry","created":"2024-05-27","cited_by_count":27},{"id":"2405.14414","title":"Proving Theorems Recursively","created":"2024-05-23","cited_by_count":26},{"id":"2309.15806","title":"Lyra: Orchestrating Dual Correction in Automated Theorem Proving","created":"2023-09-27","cited_by_count":25},{"id":"1903.03182","title":"ENIGMA-NG: Efficient Neural and Gradient-Boosted Inference Guidance for E","created":"2019-03-07","cited_by_count":24},{"id":"2211.07524","title":"Towards a Mathematics Formalisation Assistant using Large Language Models","created":"2022-11-14","cited_by_count":22},{"id":"2409.17270","title":"Proof of Thought : Neurosymbolic Program Synthesis allows Robust and Interpretable Reasoning","created":"2024-09-25","cited_by_count":19},{"id":"1909.11851","title":"Mathematical Reasoning in Latent Space","created":"2019-09-26","cited_by_count":17},{"id":"2405.15880","title":"HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis","created":"2024-05-24","cited_by_count":15},{"id":"2409.02976","title":"Hallucination Detection in LLMs: Fast and Memory-Efficient Fine-Tuned Models","created":"2024-09-04","cited_by_count":15},{"id":"1707.05922","title":"Improving Output Uncertainty Estimation and Generalization in Deep Learning via Neural Network Gaussian Processes","created":"2017-07-19","cited_by_count":14},{"id":"2401.07663","title":"Selene: Pioneering Automated Proof in Software Verification","created":"2024-01-15","cited_by_count":12},{"id":"2404.07382","title":"Learn from Failure: Fine-Tuning LLMs with Trial-and-Error Data for Intuitionistic Propositional Logic Proving","created":"2024-04-10","cited_by_count":11},{"id":"2403.03997","title":"Guiding Enumerative Program Synthesis with Large Language Models","created":"2024-03-06","cited_by_count":9},{"id":"2410.01322","title":"Forte : Finding Outliers with Representation Typicality Estimation","created":"2024-10-02","cited_by_count":9},{"id":"1811.00796","title":"Automated Theorem Proving in Intuitionistic Propositional Logic by Deep Reinforcement Learning","created":"2018-11-02","cited_by_count":7},{"id":"2312.04556","title":"Large Language Models for Mathematicians","created":"2023-12-07","cited_by_count":7},{"id":"2102.05547","title":"Learning Equational Theorem Proving","created":"2021-02-10","cited_by_count":5},{"id":"2311.07618","title":"Large Language Models' Understanding of Math: Source Criticism and Extrapolation","created":"2023-11-12","cited_by_count":4},{"id":"2305.12196","title":"Experimental results from applying GPT-4 to an unpublished formal language","created":"2023-05-20","cited_by_count":3},{"id":"1402.7150","title":"Synthesizing Finite-state Protocols from Scenarios and Requirements","created":"2014-02-28","cited_by_count":2}],"next_cursor":null}