{"list":"other","total":142,"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"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":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"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":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"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":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"1506.03340","title":"Teaching Machines to Read and Comprehend","created":"2015-06-10","cited_by_count":1049},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"1911.00536","title":"DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation","created":"2019-11-01","cited_by_count":842},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"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":"2002.08910","title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","created":"2020-02-10","cited_by_count":719},{"id":"2211.06687","title":"Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","created":"2022-11-12","cited_by_count":719},{"id":"2104.07567","title":"Retrieval Augmentation Reduces Hallucination in Conversation","created":"2021-04-15","cited_by_count":692},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609},{"id":"2306.05499","title":"Prompt Injection attack against LLM-integrated Applications","created":"2023-06-08","cited_by_count":605},{"id":"1712.07040","title":"The NarrativeQA Reading Comprehension Challenge","created":"2017-12-19","cited_by_count":597},{"id":"2104.08164","title":"Editing Factual Knowledge in Language Models","created":"2021-04-16","cited_by_count":553},{"id":"2110.11309","title":"Fast Model Editing at Scale","created":"2021-10-21","cited_by_count":498},{"id":"2108.11896","title":"A Survey on Automated Fact-Checking","created":"2021-08-26","cited_by_count":378},{"id":"2305.13172","title":"Editing Large Language Models: Problems, Methods, and Opportunities","created":"2023-05-22","cited_by_count":372},{"id":"2102.01017","title":"Measuring and Improving Consistency in Pretrained Language Models","created":"2021-02-01","cited_by_count":364},{"id":"2109.05052","title":"Entity-Based Knowledge Conflicts in Question Answering","created":"2021-09-10","cited_by_count":356},{"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":"2305.13300","title":"Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts","created":"2023-05-22","cited_by_count":341},{"id":"1708.01967","title":"Fake News Detection on Social Media: A Data Mining Perspective","created":"2017-08-07","cited_by_count":336},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"id":"2305.14739","title":"Trusting Your Evidence: Hallucinate Less with Context-aware Decoding","created":"2023-05-24","cited_by_count":327},{"id":"2308.03296","title":"Studying Large Language Model Generalization with Influence Functions","created":"2023-08-07","cited_by_count":326},{"id":"2310.03214","title":"FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation","created":"2023-10-05","cited_by_count":318},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"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":"2106.15110","title":"Time-Aware Language Models as Temporal Knowledge Bases","created":"2021-06-29","cited_by_count":296},{"id":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290},{"id":"2210.08726","title":"RARR: Researching and Revising What Language Models Say, Using Language Models","created":"2022-10-17","cited_by_count":287},{"id":"2306.13304","title":"ToolQA: A Dataset for LLM Question Answering with External Tools","created":"2023-06-23","cited_by_count":274},{"id":"2307.13528","title":"FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios","created":"2023-07-25","cited_by_count":251},{"id":"2207.13332","title":"RealTime QA: What's the Answer Right Now?","created":"2022-07-27","cited_by_count":244},{"id":"2102.01951","title":"Mind the Gap: Assessing Temporal Generalization in Neural Language Models","created":"2021-02-03","cited_by_count":230},{"id":"2311.10723","title":"Large Language Models in Finance: A Survey","created":"2023-09-28","cited_by_count":226},{"id":"2206.04624","title":"Factuality Enhanced Language Models for Open-Ended Text Generation","created":"2022-06-09","cited_by_count":202},{"id":"2309.13788","title":"Can LLM-Generated Misinformation Be Detected?","created":"2023-09-25","cited_by_count":177},{"id":"2110.03215","title":"Towards Continual Knowledge Learning of Language Models","created":"2021-10-07","cited_by_count":174},{"id":"2211.05110","title":"Large Language Models with Controllable Working Memory","created":"2022-11-09","cited_by_count":169},{"id":"2011.01314","title":"Automatic Detection of Machine Generated Text: A Critical Survey","created":"2020-11-02","cited_by_count":166},{"id":"2301.04246","title":"Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigations","created":"2023-01-10","cited_by_count":158},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157},{"id":"2004.00345","title":"Editable Neural Networks","created":"2020-04-01","cited_by_count":155},{"id":"2108.06314","title":"A Dataset for Answering Time-Sensitive Questions","created":"2021-08-13","cited_by_count":154},{"id":"2109.06157","title":"SituatedQA: Incorporating Extra-Linguistic Contexts into QA","created":"2021-09-13","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":"2305.13117","title":"AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web","created":"2023-05-22","cited_by_count":144},{"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":"2311.05112","title":"A Survey of Large Language Models in Medicine: Progress, Application, and Challenge","created":"2023-11-09","cited_by_count":124},{"id":"2204.14211","title":"TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models","created":"2022-04-29","cited_by_count":119},{"id":"2310.10378","title":"Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models","created":"2023-10-16","cited_by_count":118},{"id":"2305.18248","title":"Do Language Models Know When They're Hallucinating References?","created":"2023-05-29","cited_by_count":116},{"id":"2312.09085","title":"The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation","created":"2023-12-14","cited_by_count":109},{"id":"2104.08455","title":"Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding","created":"2021-04-17","cited_by_count":106},{"id":"1704.00656","title":"Detection and Resolution of Rumours in Social Media: A Survey","created":"2017-04-03","cited_by_count":104},{"id":"2004.08900","title":"The Cost of Training NLP Models: A Concise Overview","created":"2020-04-19","cited_by_count":98},{"id":"2211.05655","title":"DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering","created":"2022-11-10","cited_by_count":96},{"id":"2402.14409","title":"Tug-of-War Between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models","created":"2024-02-22","cited_by_count":93},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92},{"id":"2306.05949","title":"Evaluating the Social Impact of Generative AI Systems in Systems and Society","created":"2023-06-09","cited_by_count":92},{"id":"2111.07408","title":"Time Waits for No One! Analysis and Challenges of Temporal Misalignment","created":"2021-11-14","cited_by_count":91},{"id":"2308.14840","title":"Identifying and Mitigating the Security Risks of Generative AI","created":"2023-08-28","cited_by_count":91},{"id":"2402.18154","title":"Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models","created":"2024-02-28","cited_by_count":91},{"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":"2305.11171","title":"TrueTeacher: Learning Factual Consistency Evaluation with Large Language Models","created":"2023-05-18","cited_by_count":83},{"id":"2301.11924","title":"AI model GPT-3 (dis)informs us better than humans","created":"2023-01-23","cited_by_count":78},{"id":"2402.11782","title":"What Evidence Do Language Models Find Convincing?","created":"2024-02-19","cited_by_count":75},{"id":"2305.01651","title":"Can LMs Learn New Entities from Descriptions? Challenges in Propagating Injected Knowledge","created":"2023-05-02","cited_by_count":67},{"id":"2305.13507","title":"Multimodal Automated Fact-Checking: A Survey","created":"2023-05-22","cited_by_count":53}],"next_cursor":"100"}