{"list":"other","total":58,"rows":[{"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":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"2207.04672","title":"No Language Left Behind: Scaling Human-Centered Machine Translation","created":"2022-07-11","cited_by_count":1312},{"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":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"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":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"1906.00300","title":"Latent Retrieval for Weakly Supervised Open Domain Question Answering","created":"2019-06-01","cited_by_count":695},{"id":"2211.15661","title":"What learning algorithm is in-context learning? Investigations with linear models","created":"2022-11-28","cited_by_count":684},{"id":"1808.07042","title":"CoQA: A Conversational Question Answering Challenge","created":"2018-08-21","cited_by_count":683},{"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":"2303.04048","title":"Is ChatGPT a Good NLG Evaluator? A Preliminary Study","created":"2023-03-07","cited_by_count":422},{"id":"2305.19187","title":"Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models","created":"2023-05-30","cited_by_count":293},{"id":"2006.09462","title":"Selective Question Answering under Domain Shift","created":"2020-06-16","cited_by_count":238},{"id":"1711.06664","title":"Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer","created":"2017-11-17","cited_by_count":233},{"id":"2012.14983","title":"Reducing conversational agents' overconfidence through linguistic calibration","created":"2020-12-30","cited_by_count":210},{"id":"2404.11018","title":"Many-Shot In-Context Learning","created":"2024-04-17","cited_by_count":206},{"id":"2103.15025","title":"On Hallucination and Predictive Uncertainty in Conditional Language Generation","created":"2021-03-28","cited_by_count":176},{"id":"2306.10193","title":"Conformal Language Modeling","created":"2023-06-16","cited_by_count":170},{"id":"2002.10689","title":"A Theory of Usable Information Under Computational Constraints","created":"2020-02-25","cited_by_count":162},{"id":"2011.00416","title":"Deep Learning for Text Style Transfer: A Survey","created":"2020-11-01","cited_by_count":162},{"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":"2307.16877","title":"Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering","created":"2023-07-31","cited_by_count":151},{"id":"2406.04449","title":"MAIRA-2: Grounded Radiology Report Generation","created":"2024-06-06","cited_by_count":145},{"id":"2402.10978","title":"Language Models with Conformal Factuality Guarantees","created":"2024-02-15","cited_by_count":131},{"id":"2302.14545","title":"Modern Bayesian Experimental Design","created":"2023-02-28","cited_by_count":125},{"id":"2404.10136","title":"Language Model Cascades: Token-level uncertainty and beyond","created":"2024-04-15","cited_by_count":121},{"id":"2406.02543","title":"To Believe or Not to Believe Your LLM","created":"2024-06-04","cited_by_count":120},{"id":"2311.14648","title":"Calibrated Language Models Must Hallucinate","created":"2023-11-24","cited_by_count":115},{"id":"2207.10342","title":"Language Model Cascades","created":"2022-07-21","cited_by_count":107},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92},{"id":"2310.11589","title":"Eliciting Human Preferences with Language Models","created":"2023-10-17","cited_by_count":92},{"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":"2303.07971","title":"A Theory of Emergent In-Context Learning as Implicit Structure Induction","created":"2023-03-14","cited_by_count":86},{"id":"2312.09300","title":"Self-Evaluation Improves Selective Generation in Large Language Models","created":"2023-12-14","cited_by_count":76},{"id":"2308.04430","title":"SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore","created":"2023-08-08","cited_by_count":71},{"id":"2304.08151","title":"Prediction-Oriented Bayesian Active Learning","created":"2023-04-17","cited_by_count":62},{"id":"2404.00474","title":"Linguistic Calibration of Long-Form Generations","created":"2024-03-30","cited_by_count":60},{"id":"2405.01563","title":"Mitigating LLM Hallucinations via Conformal Abstention","created":"2024-04-04","cited_by_count":59},{"id":"2310.01387","title":"It's MBR All the Way Down: Modern Generation Techniques Through the Lens of Minimum Bayes Risk","created":"2023-10-02","cited_by_count":51},{"id":"2402.03563","title":"Distinguishing the Knowable from the Unknowable with Language Models","created":"2024-02-05","cited_by_count":47},{"id":"2103.15671","title":"Martingale posterior distributions","created":"2021-03-29","cited_by_count":45},{"id":"2404.03163","title":"Uncertainty in Language Models: Assessment through Rank-Calibration","created":"2024-04-04","cited_by_count":41},{"id":"2012.14868","title":"Minimum Excess Risk in Bayesian Learning","created":"2020-12-29","cited_by_count":35},{"id":"2402.06544","title":"Calibrating Long-form Generations from Large Language Models","created":"2024-02-09","cited_by_count":32},{"id":"2107.09224","title":"From Predictions to Decisions: The Importance of Joint Predictive Distributions","created":"2021-07-20","cited_by_count":29},{"id":"2309.07423","title":"ChatGPT MT: Competitive for High- (but not Low-) Resource Languages","created":"2023-09-14","cited_by_count":23},{"id":"2402.08733","title":"Experts Don't Cheat: Learning What You Don't Know By Predicting Pairs","created":"2024-02-13","cited_by_count":19},{"id":"2202.09244","title":"Transfer and Marginalize: Explaining Away Label Noise with Privileged Information","created":"2022-02-18","cited_by_count":15},{"id":"2206.11468","title":"Modular Conformal Calibration","created":"2022-06-23","cited_by_count":15}],"next_cursor":null}