{"list":"other","total":68,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"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":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"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":"2005.00661","title":"On Faithfulness and Factuality in Abstractive Summarization","created":"2020-05-02","cited_by_count":900},{"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":"2403.07691","title":"ORPO: Monolithic Preference Optimization without Reference Model","created":"2024-03-12","cited_by_count":562},{"id":"2411.04368","title":"Measuring short-form factuality in large language models","created":"2024-11-07","cited_by_count":373},{"id":"2307.01928","title":"Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners","created":"2023-07-04","cited_by_count":308},{"id":"2208.02814","title":"Conformal Risk Control","created":"2022-08-04","cited_by_count":299},{"id":"2305.19187","title":"Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models","created":"2023-05-30","cited_by_count":293},{"id":"2101.02703","title":"Distribution-Free, Risk-Controlling Prediction Sets","created":"2021-01-07","cited_by_count":288},{"id":"2210.08726","title":"RARR: Researching and Revising What Language Models Say, Using Language Models","created":"2022-10-17","cited_by_count":287},{"id":"2110.01052","title":"Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control","created":"2021-10-03","cited_by_count":271},{"id":"2404.10774","title":"MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents","created":"2024-04-16","cited_by_count":257},{"id":"2112.12870","title":"Measuring Attribution in Natural Language Generation Models","created":"2021-12-23","cited_by_count":256},{"id":"2404.12358","title":"From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function","created":"2024-04-18","cited_by_count":242},{"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":"2311.08401","title":"Fine-tuning Language Models for Factuality","created":"2023-11-14","cited_by_count":221},{"id":"2012.14983","title":"Reducing conversational agents' overconfidence through linguistic calibration","created":"2020-12-30","cited_by_count":210},{"id":"2206.04624","title":"Factuality Enhanced Language Models for Open-Ended Text Generation","created":"2022-06-09","cited_by_count":202},{"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":"2306.10193","title":"Conformal Language Modeling","created":"2023-06-16","cited_by_count":170},{"id":"2403.18802","title":"Long-form factuality in large language models","created":"2024-03-27","cited_by_count":155},{"id":"2305.18404","title":"Conformal Prediction with Large Language Models for Multi-Choice Question Answering","created":"2023-05-28","cited_by_count":139},{"id":"2402.10978","title":"Language Models with Conformal Factuality Guarantees","created":"2024-02-15","cited_by_count":131},{"id":"2406.19276","title":"VERISCORE: Evaluating the factuality of verifiable claims in long-form text generation","created":"2024-06-27","cited_by_count":117},{"id":"2406.09714","title":"Large language model validity via enhanced conformal prediction methods","created":"2024-06-14","cited_by_count":92},{"id":"1910.10562","title":"Nested conformal prediction and quantile out-of-bag ensemble methods","created":"2019-10-23","cited_by_count":89},{"id":"2311.09000","title":"Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers","created":"2023-11-15","cited_by_count":87},{"id":"2107.05719","title":"Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration","created":"2021-07-12","cited_by_count":79},{"id":"2410.08847","title":"Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization","created":"2024-10-11","cited_by_count":67},{"id":"2205.06938","title":"Generating Literal and Implied Subquestions to Fact-check Complex Claims","created":"2022-05-14","cited_by_count":66},{"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":"2405.10301","title":"Conformal Alignment: Knowing When to Trust Foundation Models with Guarantees","created":"2024-05-16","cited_by_count":54},{"id":"2401.13275","title":"Can AI Assistants Know What They Don't Know?","created":"2024-01-24","cited_by_count":50},{"id":"2104.08731","title":"Can NLI Models Verify QA Systems' Predictions?","created":"2021-04-18","cited_by_count":46},{"id":"2406.20079","title":"Molecular Facts: Desiderata for Decontextualization in LLM Fact Verification","created":"2024-06-28","cited_by_count":44},{"id":"2305.13252","title":"\"According to ...\": Prompting Language Models Improves Quoting from Pre-Training Data","created":"2023-05-22","cited_by_count":42},{"id":"2403.11903","title":"A Closer Look at Claim Decomposition","created":"2024-03-18","cited_by_count":41},{"id":"1904.04792","title":"Quizbowl: The Case for Incremental Question Answering","created":"2019-04-09","cited_by_count":36},{"id":"2301.09044","title":"Learning to Reject with a Fixed Predictor: Application to Decontextualization","created":"2023-01-22","cited_by_count":32},{"id":"2311.03533","title":"Quantifying Uncertainty in Natural Language Explanations of Large Language Models","created":"2023-11-06","cited_by_count":32},{"id":"2104.05837","title":"Relational World Knowledge Representation in Contextual Language Models: A Review","created":"2021-04-12","cited_by_count":31},{"id":"2410.20774","title":"Are LLM-Judges Robust to Expressions of Uncertainty? Investigating the effect of Epistemic Markers on LLM-based Evaluation","created":"2024-10-28","cited_by_count":29},{"id":"2407.14614","title":"Evaluating language models as risk scores","created":"2024-07-19","cited_by_count":27},{"id":"2407.17468","title":"WildHallucinations: Evaluating Long-form Factuality in LLMs with Real-World Entity Queries","created":"2024-07-24","cited_by_count":26},{"id":"2409.12180","title":"Finetuning Language Models to Emit Linguistic Expressions of Uncertainty","created":"2024-09-18","cited_by_count":26},{"id":"2412.13175","title":"DnDScore: Decontextualization and Decomposition for Factuality Verification in Long-Form Text Generation","created":"2024-12-17","cited_by_count":22},{"id":"2310.14520","title":"QUDEVAL: The Evaluation of Questions Under Discussion Discourse Parsing","created":"2023-10-23","cited_by_count":19},{"id":"2501.12868","title":"As Confidence Aligns: Exploring the Effect of AI Confidence on Human Self-confidence in Human-AI Decision Making","created":"2025-01-22","cited_by_count":19},{"id":"2501.01303","title":"Citations and Trust in LLM Generated Responses","created":"2025-01-02","cited_by_count":18},{"id":"2404.05904","title":"The Hallucinations Leaderboard -- An Open Effort to Measure Hallucinations in Large Language Models","created":"2024-04-08","cited_by_count":17},{"id":"2407.03572","title":"Core: Robust Factual Precision with Informative Sub-Claim Identification","created":"2024-07-04","cited_by_count":16},{"id":"2410.18359","title":"Improving Model Factuality with Fine-grained Critique-based Evaluator","created":"2024-10-24","cited_by_count":15},{"id":"2410.01888","title":"Conformal Prediction Sets Can Cause Disparate Impact","created":"2024-10-02","cited_by_count":14},{"id":"2404.03862","title":"Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data","created":"2024-04-05","cited_by_count":13},{"id":"2404.16164","title":"Towards a Holistic Evaluation of LLMs on Factual Knowledge Recall","created":"2024-04-24","cited_by_count":8},{"id":"2410.04315","title":"Calibrating Expressions of Certainty","created":"2024-10-06","cited_by_count":7},{"id":"2405.13022","title":"LLMs can learn self-restraint through iterative self-reflection","created":"2024-05-15","cited_by_count":6}],"next_cursor":null}