{"list":"other","total":77,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"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":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"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":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"2212.10511","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","created":"2022-12-20","cited_by_count":1128},{"id":"2212.03827","title":"Discovering Latent Knowledge in Language Models Without Supervision","created":"2022-12-07","cited_by_count":767},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609},{"id":"2403.14403","title":"Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity","created":"2024-03-21","cited_by_count":451},{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437},{"id":"2402.07927","title":"A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications","created":"2024-02-05","cited_by_count":431},{"id":"2303.04048","title":"Is ChatGPT a Good NLG Evaluator? A Preliminary Study","created":"2023-03-07","cited_by_count":422},{"id":"2309.03883","title":"DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models","created":"2023-09-07","cited_by_count":376},{"id":"2209.10063","title":"Generate rather than Retrieve: Large Language Models are Strong Context Generators","created":"2022-09-21","cited_by_count":298},{"id":"2401.01313","title":"A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models","created":"2024-01-02","cited_by_count":269},{"id":"1306.0940","title":"(More) Efficient Reinforcement Learning via Posterior Sampling","created":"2013-06-04","cited_by_count":233},{"id":"2305.14283","title":"Query Rewriting for Retrieval-Augmented Large Language Models","created":"2023-05-23","cited_by_count":213},{"id":"2206.04624","title":"Factuality Enhanced Language Models for Open-Ended Text Generation","created":"2022-06-09","cited_by_count":202},{"id":"2310.10505","title":"ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models","created":"2023-10-16","cited_by_count":187},{"id":"2310.01469","title":"LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples","created":"2023-10-02","cited_by_count":177},{"id":"2304.10428","title":"GPT-NER: Named Entity Recognition via Large Language Models","created":"2023-04-20","cited_by_count":160},{"id":"2307.16877","title":"Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering","created":"2023-07-31","cited_by_count":151},{"id":"2304.14399","title":"We're Afraid Language Models Aren't Modeling Ambiguity","created":"2023-04-27","cited_by_count":126},{"id":"2311.04205","title":"Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves","created":"2023-11-07","cited_by_count":123},{"id":"2310.20410","title":"FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models","created":"2023-10-31","cited_by_count":117},{"id":"2305.13626","title":"Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration","created":"2023-05-23","cited_by_count":116},{"id":"2402.17811","title":"TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space","created":"2024-02-27","cited_by_count":91},{"id":"2310.06271","title":"Towards Mitigating Hallucination in Large Language Models via Self-Reflection","created":"2023-10-10","cited_by_count":81},{"id":"2312.15710","title":"Alleviating Hallucinations of Large Language Models through Induced Hallucinations","created":"2023-12-25","cited_by_count":79},{"id":"2306.08189","title":"Language models are not naysayers: An analysis of language models on negation benchmarks","created":"2023-06-14","cited_by_count":74},{"id":"2401.07078","title":"PUB: A Pragmatics Understanding Benchmark for Assessing LLMs' Pragmatics Capabilities","created":"2024-01-13","cited_by_count":59},{"id":"2405.14431","title":"RaFe: Ranking Feedback Improves Query Rewriting for RAG","created":"2024-05-23","cited_by_count":49},{"id":"2312.17484","title":"Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning","created":"2023-12-29","cited_by_count":45},{"id":"2002.00287","title":"Efficient and Robust Algorithms for Adversarial Linear Contextual Bandits","created":"2020-02-01","cited_by_count":43},{"id":"1904.06707","title":"Rare Words: A Major Problem for Contextualized Embeddings And How to Fix it by Attentive Mimicking","created":"2019-04-14","cited_by_count":41},{"id":"1704.04572","title":"Task-Oriented Query Reformulation with Reinforcement Learning","created":"2017-04-15","cited_by_count":39},{"id":"2211.07830","title":"Prompting Language Models for Linguistic Structure","created":"2022-11-15","cited_by_count":39},{"id":"1911.09661","title":"Paraphrasing with Large Language Models","created":"2019-11-21","cited_by_count":36},{"id":"2402.08702","title":"PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Heuristic-based Sampling","created":"2024-02-13","cited_by_count":32},{"id":"1810.09807","title":"PreCo: A Large-scale Dataset in Preschool Vocabulary for Coreference Resolution","created":"2018-10-23","cited_by_count":30},{"id":"2401.05930","title":"SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully","created":"2024-01-11","cited_by_count":15},{"id":"2112.07066","title":"Continual Learning In Environments With Polynomial Mixing Times","created":"2021-12-13","cited_by_count":14},{"id":"2404.04332","title":"Scope Ambiguities in Large Language Models","created":"2024-04-05","cited_by_count":11},{"id":"1908.05762","title":"Entity-aware ELMo: Learning Contextual Entity Representation for Entity Disambiguation","created":"2019-08-14","cited_by_count":10},{"id":"2006.07541","title":"Follow the Perturbed Leader: Optimism and Fast Parallel Algorithms for Smooth Minimax Games","created":"2020-06-13","cited_by_count":10},{"id":"2109.04604","title":"How May I Help You? Using Neural Text Simplification to Improve Downstream NLP Tasks","created":"2021-09-10","cited_by_count":9},{"id":"2310.17413","title":"Harnessing GPT-3.5-turbo for Rhetorical Role Prediction in Legal Cases","created":"2023-10-26","cited_by_count":8},{"id":"1904.03799","title":"Enriching Rare Word Representations in Neural Language Models by Embedding Matrix Augmentation","created":"2019-04-08","cited_by_count":7},{"id":"2210.14486","title":"Leveraging Affirmative Interpretations from Negation Improves Natural Language Understanding","created":"2022-10-26","cited_by_count":7},{"id":"2404.12535","title":"Is There No Such Thing as a Bad Question? H4R: HalluciBot For Ratiocination, Rewriting, Ranking, and Routing","created":"2024-04-18","cited_by_count":6},{"id":"2406.10803","title":"HiddenTables & PyQTax: A Cooperative Game and Dataset For TableQA to Ensure Scale and Data Privacy Across a Myriad of Taxonomies","created":"2024-06-16","cited_by_count":6},{"id":"2412.11063","title":"LAW: Legal Agentic Workflows for Custody and Fund Services Contracts","created":"2024-12-15","cited_by_count":6},{"id":"2101.10448","title":"PolyLM: Learning about Polysemy through Language Modeling","created":"2021-01-25","cited_by_count":5},{"id":"2405.20967","title":"Superlatives in Context: Modeling the Implicit Semantics of Superlatives","created":"2024-05-31","cited_by_count":5},{"id":"2410.19727","title":"FISHNET: Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert Swarms, and Task Planning","created":"2024-10-25","cited_by_count":5},{"id":"2311.15507","title":"Improving Word Sense Disambiguation in Neural Machine Translation with Salient Document Context","created":"2023-11-27","cited_by_count":2},{"id":"2502.03711","title":"MultiQ&A: An Analysis in Measuring Robustness via Automated Crowdsourcing of Question Perturbations and Answers","created":"2025-02-06","cited_by_count":2}],"next_cursor":null}