{"list":"other","total":81,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"2305.14251","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","created":"2023-05-23","cited_by_count":1282},{"id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254},{"id":"2406.12793","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","created":"2024-06-18","cited_by_count":1121},{"id":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075},{"id":"2007.15779","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","created":"2020-07-31","cited_by_count":1009},{"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":"1802.01933","title":"A Survey Of Methods For Explaining Black Box Models","created":"2018-02-06","cited_by_count":973},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"1602.06023","title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","created":"2016-02-19","cited_by_count":812},{"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":"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":"1910.12840","title":"Evaluating the Factual Consistency of Abstractive Text Summarization","created":"2019-10-28","cited_by_count":584},{"id":"1907.09190","title":"ELI5: Long Form Question Answering","created":"2019-07-22","cited_by_count":575},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401},{"id":"2302.12813","title":"Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback","created":"2023-02-24","cited_by_count":353},{"id":"2210.09150","title":"Prompting GPT-3 To Be Reliable","created":"2022-10-17","cited_by_count":260},{"id":"2311.08298","title":"A Survey of Confidence Estimation and Calibration in Large Language Models","created":"2023-11-14","cited_by_count":256},{"id":"2303.10420","title":"A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models","created":"2023-03-18","cited_by_count":246},{"id":"1805.11783","title":"To Trust Or Not To Trust A Classifier","created":"2018-05-30","cited_by_count":207},{"id":"2402.00367","title":"Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration","created":"2024-02-01","cited_by_count":180},{"id":"2205.03401","title":"The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning","created":"2022-05-06","cited_by_count":169},{"id":"2405.20003","title":"Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities","created":"2024-05-30","cited_by_count":159},{"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":"2404.00971","title":"Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code","created":"2024-04-01","cited_by_count":107},{"id":"2210.04714","title":"Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis","created":"2022-10-10","cited_by_count":104},{"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":"2403.20279","title":"LUQ: Long-text Uncertainty Quantification for LLMs","created":"2024-03-29","cited_by_count":81},{"id":"2311.13240","title":"On the Calibration of Large Language Models and Alignment","created":"2023-11-22","cited_by_count":73},{"id":"2401.02009","title":"Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives","created":"2024-01-04","cited_by_count":71},{"id":"2403.05973","title":"Calibrating Large Language Models Using Their Generations Only","created":"2024-03-09","cited_by_count":65},{"id":"2309.12236","title":"Smooth ECE: Principled Reliability Diagrams via Kernel Smoothing","created":"2023-09-21","cited_by_count":63},{"id":"2404.00474","title":"Linguistic Calibration of Long-Form Generations","created":"2024-03-30","cited_by_count":60},{"id":"2402.11457","title":"When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation","created":"2024-02-18","cited_by_count":59},{"id":"1406.3676","title":"Question Answering with Subgraph Embeddings","created":"2014-06-14","cited_by_count":58},{"id":"2402.02047","title":"Calibration and Correctness of Language Models for Code","created":"2024-02-03","cited_by_count":49},{"id":"2107.08353","title":"Top-label calibration and multiclass-to-binary reductions","created":"2021-07-18","cited_by_count":46},{"id":"2404.04689","title":"Multicalibration for Confidence Scoring in LLMs","created":"2024-04-06","cited_by_count":46},{"id":"2310.19208","title":"LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses","created":"2023-10-30","cited_by_count":44},{"id":"2312.02896","title":"BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models","created":"2023-12-05","cited_by_count":41},{"id":"2404.03163","title":"Uncertainty in Language Models: Assessment through Rank-Calibration","created":"2024-04-04","cited_by_count":41},{"id":"2311.08877","title":"Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation","created":"2023-11-15","cited_by_count":39},{"id":"2405.11613","title":"Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts","created":"2024-05-19","cited_by_count":36},{"id":"2104.08736","title":"Stochastic Optimization of Areas Under Precision-Recall Curves with Provable Convergence","created":"2021-04-18","cited_by_count":35},{"id":"2205.09680","title":"Metrics of calibration for probabilistic predictions","created":"2022-05-19","cited_by_count":32},{"id":"2301.12307","title":"MQAG: Multiple-choice Question Answering and Generation for Assessing Information Consistency in Summarization","created":"2023-01-28","cited_by_count":30},{"id":"2406.03441","title":"Cycles of Thought: Measuring LLM Confidence through Stable Explanations","created":"2024-06-05","cited_by_count":29},{"id":"2406.08434","title":"TasTe: Teaching Large Language Models to Translate through Self-Reflection","created":"2024-06-12","cited_by_count":27},{"id":"2110.07586","title":"Can Explanations Be Useful for Calibrating Black Box Models?","created":"2021-10-14","cited_by_count":20},{"id":"2405.16856","title":"Can We Trust LLMs? Mitigate Overconfidence Bias in LLMs through Knowledge Transfer","created":"2024-05-27","cited_by_count":19},{"id":"2410.11594","title":"Black-box Uncertainty Quantification Method for LLM-as-a-Judge","created":"2024-10-15","cited_by_count":18},{"id":"2406.11514","title":"Counterfactual Debating with Preset Stances for Hallucination Elimination of LLMs","created":"2024-06-17","cited_by_count":17},{"id":"2402.00251","title":"Efficient Non-Parametric Uncertainty Quantification for Black-Box Large Language Models and Decision Planning","created":"2024-02-01","cited_by_count":16},{"id":"2406.04370","title":"Large Language Model Confidence Estimation via Black-Box Access","created":"2024-06-01","cited_by_count":14},{"id":"2402.14963","title":"Mirror: A Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning","created":"2024-02-22","cited_by_count":10},{"id":"2405.20434","title":"Facilitating Human-LLM Collaboration through Factuality Scores and Source Attributions","created":"2024-05-30","cited_by_count":9},{"id":"2409.03225","title":"Enhancing Healthcare LLM Trust with Atypical Presentations Recalibration","created":"2024-09-05","cited_by_count":6},{"id":"2109.10092","title":"Bayesian Confidence Calibration for Epistemic Uncertainty Modelling","created":"2021-09-21","cited_by_count":5},{"id":"2306.16564","title":"Pareto Optimal Learning for Estimating Large Language Model Errors","created":"2023-06-28","cited_by_count":5},{"id":"1905.07898","title":"Learning to Count Objects with Few Exemplar Annotations","created":"2019-05-20","cited_by_count":4},{"id":"2310.03283","title":"A Formalism and Approach for Improving Robustness of Large Language Models Using Risk-Adjusted Confidence Scores","created":"2023-10-05","cited_by_count":2}],"next_cursor":null}