{"list":"other","total":90,"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":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"id":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"2011.01060","title":"Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps","created":"2020-11-02","cited_by_count":1282},{"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":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"2212.10509","title":"Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions","created":"2022-12-20","cited_by_count":923},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916},{"id":"2301.12652","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","created":"2023-01-30","cited_by_count":792},{"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":"2009.02252","title":"KILT: a Benchmark for Knowledge Intensive Language Tasks","created":"2020-09-04","cited_by_count":573},{"id":"2104.08164","title":"Editing Factual Knowledge in Language Models","created":"2021-04-16","cited_by_count":553},{"id":"2211.08411","title":"Large Language Models Struggle to Learn Long-Tail Knowledge","created":"2022-11-15","cited_by_count":458},{"id":"2206.06520","title":"Memory-Based Model Editing at Scale","created":"2022-06-13","cited_by_count":447},{"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":"1706.04115","title":"Zero-Shot Relation Extraction via Reading Comprehension","created":"2017-06-13","cited_by_count":426},{"id":"2310.01558","title":"Making Retrieval-Augmented Language Models Robust to Irrelevant Context","created":"2023-10-02","cited_by_count":369},{"id":"2309.05922","title":"A Survey of Hallucination in Large Foundation Models","created":"2023-09-12","cited_by_count":368},{"id":"2109.05052","title":"Entity-Based Knowledge Conflicts in Question Answering","created":"2021-09-10","cited_by_count":356},{"id":"2305.15294","title":"Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy","created":"2023-05-24","cited_by_count":346},{"id":"2010.00904","title":"Autoregressive Entity Retrieval","created":"2020-10-02","cited_by_count":334},{"id":"2303.14070","title":"ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge","created":"2023-03-24","cited_by_count":325},{"id":"2212.14024","title":"Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP","created":"2022-12-28","cited_by_count":318},{"id":"2310.03214","title":"FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation","created":"2023-10-05","cited_by_count":318},{"id":"2306.15447","title":"Are aligned neural networks adversarially aligned?","created":"2023-06-26","cited_by_count":315},{"id":"2305.14795","title":"MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions","created":"2023-05-24","cited_by_count":300},{"id":"2209.10063","title":"Generate rather than Retrieve: Large Language Models are Strong Context Generators","created":"2022-09-21","cited_by_count":298},{"id":"2210.08726","title":"RARR: Researching and Revising What Language Models Say, Using Language Models","created":"2022-10-17","cited_by_count":287},{"id":"2305.12740","title":"Can We Edit Factual Knowledge by In-Context Learning?","created":"2023-05-22","cited_by_count":285},{"id":"2211.11031","title":"Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors","created":"2022-11-20","cited_by_count":271},{"id":"2210.09150","title":"Prompting GPT-3 To Be Reliable","created":"2022-10-17","cited_by_count":260},{"id":"2202.06991","title":"Transformer Memory as a Differentiable Search Index","created":"2022-02-14","cited_by_count":247},{"id":"2301.04213","title":"Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models","created":"2023-01-10","cited_by_count":243},{"id":"2305.18153","title":"Do Large Language Models Know What They Don't Know?","created":"2023-05-29","cited_by_count":243},{"id":"2307.12976","title":"Evaluating the Ripple Effects of Knowledge Editing in Language Models","created":"2023-07-24","cited_by_count":242},{"id":"2012.04584","title":"Distilling Knowledge from Reader to Retriever for Question Answering","created":"2020-12-08","cited_by_count":226},{"id":"2301.09785","title":"Transformer-Patcher: One Mistake worth One Neuron","created":"2023-01-24","cited_by_count":197},{"id":"2308.08742","title":"PMET: Precise Model Editing in a Transformer","created":"2023-08-17","cited_by_count":173},{"id":"2211.05110","title":"Large Language Models with Controllable Working Memory","created":"2022-11-09","cited_by_count":169},{"id":"2106.05707","title":"FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured information","created":"2021-06-10","cited_by_count":167},{"id":"2309.17410","title":"Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks","created":"2023-09-29","cited_by_count":158},{"id":"2004.00345","title":"Editable Neural Networks","created":"2020-04-01","cited_by_count":155},{"id":"2307.11019","title":"Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation","created":"2023-07-20","cited_by_count":147},{"id":"2109.06157","title":"SituatedQA: Incorporating Extra-Linguistic Contexts into QA","created":"2021-09-13","cited_by_count":145},{"id":"2301.00303","title":"Rethinking with Retrieval: Faithful Large Language Model Inference","created":"2022-12-31","cited_by_count":145},{"id":"2210.13701","title":"Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence","created":"2022-10-25","cited_by_count":144},{"id":"2305.03268","title":"Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework","created":"2023-05-05","cited_by_count":139},{"id":"2205.11388","title":"StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models","created":"2022-05-23","cited_by_count":126},{"id":"2010.04389","title":"A Survey of Knowledge-Enhanced Text Generation","created":"2020-10-09","cited_by_count":120},{"id":"2306.04136","title":"Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering","created":"2023-06-07","cited_by_count":119},{"id":"2204.10628","title":"Autoregressive Search Engines: Generating Substrings as Document Identifiers","created":"2022-04-22","cited_by_count":113},{"id":"2206.02743","title":"A Neural Corpus Indexer for Document Retrieval","created":"2022-06-06","cited_by_count":111},{"id":"2201.05320","title":"CommonsenseQA 2.0: Exposing the Limits of AI through Gamification","created":"2022-01-14","cited_by_count":109},{"id":"2211.05655","title":"DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering","created":"2022-11-10","cited_by_count":96},{"id":"2210.03329","title":"Calibrating Factual Knowledge in Pretrained Language Models","created":"2022-10-07","cited_by_count":92},{"id":"2305.14002","title":"Improving Language Models via Plug-and-Play Retrieval Feedback","created":"2023-05-23","cited_by_count":87},{"id":"2005.06117","title":"INFOTABS: Inference on Tables as Semi-structured Data","created":"2020-05-13","cited_by_count":86},{"id":"2202.13257","title":"Controllable Natural Language Generation with Contrastive Prefixes","created":"2022-02-27","cited_by_count":75},{"id":"1906.03538","title":"Seeing Things from a Different Angle: Discovering Diverse Perspectives about Claims","created":"2019-06-08","cited_by_count":74},{"id":"2305.17331","title":"Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-In","created":"2023-05-27","cited_by_count":71},{"id":"1801.10314","title":"Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph","created":"2018-01-31","cited_by_count":67},{"id":"2305.17553","title":"Detecting Edit Failures In Large Language Models: An Improved Specificity Benchmark","created":"2023-05-27","cited_by_count":62},{"id":"2307.08487","title":"Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models","created":"2023-07-17","cited_by_count":60},{"id":"2104.04725","title":"Fool Me Twice: Entailment from Wikipedia Gamification","created":"2021-04-10","cited_by_count":50},{"id":"2305.09955","title":"Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models","created":"2023-05-17","cited_by_count":46},{"id":"2202.09381","title":"Synthetic Disinformation Attacks on Automated Fact Verification Systems","created":"2022-02-18","cited_by_count":44},{"id":"2310.08475","title":"Can We Edit Multimodal Large Language Models?","created":"2023-10-12","cited_by_count":44},{"id":"2305.04757","title":"Augmented Large Language Models with Parametric Knowledge Guiding","created":"2023-05-08","cited_by_count":37},{"id":"2210.02889","title":"A Distributional Lens for Multi-Aspect Controllable Text Generation","created":"2022-10-06","cited_by_count":33},{"id":"2310.11958","title":"Emptying the Ocean with a Spoon: Should We Edit Models?","created":"2023-10-18","cited_by_count":27},{"id":"2308.09954","title":"DocTER: Evaluating Document-based Knowledge Editing","created":"2023-08-19","cited_by_count":26},{"id":"2208.00399","title":"Neural Knowledge Bank for Pretrained Transformers","created":"2022-07-31","cited_by_count":16},{"id":"2303.00046","title":"Edit at your own risk: evaluating the robustness of edited models to distribution shifts","created":"2023-02-28","cited_by_count":8},{"id":"2309.16535","title":"KLoB: a Benchmark for Assessing Knowledge Locating Methods in Language Models","created":"2023-09-28","cited_by_count":8},{"id":"2108.02365","title":"Hybrid Reasoning Network for Video-based Commonsense Captioning","created":"2021-08-05","cited_by_count":4}],"next_cursor":null}