{"list":"other","total":66,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"2303.08896","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","created":"2023-03-15","cited_by_count":810},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"2304.14767","title":"Dissecting Recall of Factual Associations in Auto-Regressive Language Models","created":"2023-04-28","cited_by_count":528},{"id":"2110.11309","title":"Fast Model Editing at Scale","created":"2021-10-21","cited_by_count":498},{"id":"2206.06520","title":"Memory-Based Model Editing at Scale","created":"2022-06-13","cited_by_count":447},{"id":"2305.14795","title":"MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions","created":"2023-05-24","cited_by_count":300},{"id":"2106.15110","title":"Time-Aware Language Models as Temporal Knowledge Bases","created":"2021-06-29","cited_by_count":296},{"id":"2305.12740","title":"Can We Edit Factual Knowledge by In-Context Learning?","created":"2023-05-22","cited_by_count":285},{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283},{"id":"2211.11031","title":"Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors","created":"2022-11-20","cited_by_count":271},{"id":"2207.13332","title":"RealTime QA: What's the Answer Right Now?","created":"2022-07-27","cited_by_count":244},{"id":"2405.05904","title":"Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?","created":"2024-05-09","cited_by_count":232},{"id":"2110.03215","title":"Towards Continual Knowledge Learning of Language Models","created":"2021-10-07","cited_by_count":174},{"id":"2312.15166","title":"SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling","created":"2023-12-23","cited_by_count":172},{"id":"2401.01286","title":"A Comprehensive Study of Knowledge Editing for Large Language Models","created":"2024-01-02","cited_by_count":163},{"id":"2108.06314","title":"A Dataset for Answering Time-Sensitive Questions","created":"2021-08-13","cited_by_count":154},{"id":"2401.06855","title":"Fine-grained Hallucination Detection and Editing for Language Models","created":"2024-01-12","cited_by_count":149},{"id":"2109.06157","title":"SituatedQA: Incorporating Extra-Linguistic Contexts into QA","created":"2021-09-13","cited_by_count":145},{"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":"2204.14211","title":"TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models","created":"2022-04-29","cited_by_count":119},{"id":"2104.10353","title":"Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning","created":"2021-04-21","cited_by_count":106},{"id":"2308.07269","title":"EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models","created":"2023-08-14","cited_by_count":98},{"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":"2405.14768","title":"WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models","created":"2024-05-23","cited_by_count":92},{"id":"2406.11813","title":"How Do Large Language Models Acquire Factual Knowledge During Pretraining?","created":"2024-06-17","cited_by_count":90},{"id":"2406.09170","title":"Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning","created":"2024-06-13","cited_by_count":88},{"id":"2109.07154","title":"Can Language Models be Biomedical Knowledge Bases?","created":"2021-09-15","cited_by_count":83},{"id":"2312.11795","title":"MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA","created":"2023-12-19","cited_by_count":80},{"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":"2404.00213","title":"Injecting New Knowledge into Large Language Models via Supervised Fine-Tuning","created":"2024-03-30","cited_by_count":58},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51},{"id":"2310.00935","title":"Resolving Knowledge Conflicts in Large Language Models","created":"2023-10-02","cited_by_count":50},{"id":"2310.15910","title":"Characterizing Mechanisms for Factual Recall in Language Models","created":"2023-10-24","cited_by_count":48},{"id":"2012.11490","title":"CSKG: The CommonSense Knowledge Graph","created":"2020-12-21","cited_by_count":45},{"id":"2406.12673","title":"Estimating Knowledge in Large Language Models Without Generating a Single Token","created":"2024-06-18","cited_by_count":40},{"id":"2310.07343","title":"How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances","created":"2023-10-11","cited_by_count":33},{"id":"2312.13401","title":"Time is Encoded in the Weights of Finetuned Language Models","created":"2023-12-20","cited_by_count":33},{"id":"2406.14785","title":"Understanding Finetuning for Factual Knowledge Extraction","created":"2024-06-20","cited_by_count":32},{"id":"2402.16797","title":"Set the Clock: Temporal Alignment of Pretrained Language Models","created":"2024-02-26","cited_by_count":25},{"id":"2407.08039","title":"Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models","created":"2024-07-10","cited_by_count":25},{"id":"2406.02472","title":"Analyzing Temporal Complex Events with Large Language Models? A Benchmark towards Temporal, Long Context Understanding","created":"2024-06-04","cited_by_count":23},{"id":"2403.06259","title":"Editing Conceptual Knowledge for Large Language Models","created":"2024-03-10","cited_by_count":21},{"id":"2311.08106","title":"Carpe Diem: On the Evaluation of World Knowledge in Lifelong Language Models","created":"2023-11-14","cited_by_count":18},{"id":"2305.14221","title":"Question Answering as Programming for Solving Time-Sensitive Questions","created":"2023-05-23","cited_by_count":14},{"id":"2406.04496","title":"Time Sensitive Knowledge Editing through Efficient Finetuning","created":"2024-06-06","cited_by_count":14},{"id":"2403.14364","title":"WikiFactDiff: A Large, Realistic, and Temporally Adaptable Dataset for Atomic Factual Knowledge Update in Causal Language Models","created":"2024-03-21","cited_by_count":9},{"id":"2012.10595","title":"T-GAP: Learning to Walk across Time for Temporal Knowledge Graph Completion","created":"2020-12-19","cited_by_count":5},{"id":"2406.02919","title":"MultifacetEval: Multifaceted Evaluation to Probe LLMs in Mastering Medical Knowledge","created":"2024-06-05","cited_by_count":5},{"id":"2205.03772","title":"Math-KG: Construction and Applications of Mathematical Knowledge Graph","created":"2022-05-08","cited_by_count":4},{"id":"2402.13731","title":"Cracking Factual Knowledge: A Comprehensive Analysis of Degenerate Knowledge Neurons in Large Language Models","created":"2024-02-21","cited_by_count":3},{"id":"2405.10288","title":"Timeline-based Sentence Decomposition with In-Context Learning for Temporal Fact Extraction","created":"2024-05-16","cited_by_count":3},{"id":"2405.10621","title":"Historically Relevant Event Structuring for Temporal Knowledge Graph Reasoning","created":"2024-05-17","cited_by_count":2}],"next_cursor":null}