{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/llama/papers/11","list_of":"/method/llama","method":"LLaMA","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":11,"pages_in_order":11,"rows_per_page":100,"rows":[1001,1062],"of":1062,"counts":{"archive_papers_tagged":1062,"with_a_code_link":423,"where_syntology_ran_a_sample":143,"not_listed_spam_title":0,"listed":1062,"listed_where_code_ran":143,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":127,"every_run_a_failure_of_syntologys_instrument":16,"listed_with_a_run_with_no_instrument_failure":127,"listed_every_run_a_failure_of_syntologys_instrument":16,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/llama","prev":"/method/llama/papers/10","next":null,"papers":[{"paper":"/paper/building-accurate-translation-tailored-llms","slug":"building-accurate-translation-tailored-llms","title":"Building Accurate Translation-Tailored LLMs with Language Aware Instruction Tuning","date":"2024-03-21","arxiv_id":"2403.14399","n_code_links":1,"syntology":null},{"paper":"/paper/chainlm-empowering-large-language-models-with","slug":"chainlm-empowering-large-language-models-with","title":"ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting","date":"2024-03-21","arxiv_id":"2403.14312","n_code_links":1,"syntology":{"ran":4,"of":10,"n_ran_checked":4,"n_instrument":0,"unverified":6,"pointer_only":10,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["rucaibox/chainlm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/from-representational-harms-to-quality-of","slug":"from-representational-harms-to-quality-of","title":"From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards","date":"2024-03-20","arxiv_id":"2403.13213","n_code_links":1,"syntology":null},{"paper":"/paper/llama-meets-eu-investigating-the-european","slug":"llama-meets-eu-investigating-the-european","title":"Llama meets EU: Investigating the European Political Spectrum through the Lens of LLMs","date":"2024-03-20","arxiv_id":"2403.13592","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":4,"n_instrument":1,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["coastalcph/eu-politics-llms"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/vl-mamba-exploring-state-space-models-for","slug":"vl-mamba-exploring-state-space-models-for","title":"VL-Mamba: Exploring State Space Models for Multimodal Learning","date":"2024-03-20","arxiv_id":"2403.13600","n_code_links":0,"syntology":null},{"paper":null,"slug":"dee-dual-stage-explainable-evaluation-method","title":"DEE: Dual-stage Explainable Evaluation Method for Text Generation","date":"2024-03-18","arxiv_id":"2403.11509","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-hokkien-dual-translation-by","slug":"enhancing-hokkien-dual-translation-by","title":"Enhancing Taiwanese Hokkien Dual Translation by Exploring and Standardizing of Four Writing Systems","date":"2024-03-18","arxiv_id":"2403.12024","n_code_links":1,"syntology":null},{"paper":null,"slug":"finllama-financial-sentiment-classification","title":"FinLlama: Financial Sentiment Classification for Algorithmic Trading Applications","date":"2024-03-18","arxiv_id":"2403.12285","n_code_links":0,"syntology":null},{"paper":null,"slug":"metaphor-understanding-challenge-dataset-for","title":"Metaphor Understanding Challenge Dataset for LLMs","date":"2024-03-18","arxiv_id":"2403.11810","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-large-language-models-understand-medical","title":"Can Large Language Models abstract Medical Coded Language?","date":"2024-03-16","arxiv_id":"2403.10822","n_code_links":0,"syntology":null},{"paper":"/paper/empirical-studies-of-parameter-efficient","slug":"empirical-studies-of-parameter-efficient","title":"Empirical Studies of Parameter Efficient Methods for Large Language Models of Code and Knowledge Transfer to R","date":"2024-03-16","arxiv_id":"2405.01553","n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-erosion-emulating-controlled","title":"Neural Erosion: Emulating Controlled Neurodegeneration and Aging in AI Systems","date":"2024-03-15","arxiv_id":"2403.10596","n_code_links":0,"syntology":null},{"paper":"/paper/can-large-language-models-identify-authorship","slug":"can-large-language-models-identify-authorship","title":"Can Large Language Models Identify Authorship?","date":"2024-03-13","arxiv_id":"2403.08213","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-novel-nuanced-conversation-evaluation","title":"A Novel Nuanced Conversation Evaluation Framework for Large Language Models in Mental Health","date":"2024-03-08","arxiv_id":"2403.09705","n_code_links":0,"syntology":null},{"paper":null,"slug":"privacy-aware-semantic-cache-for-large","title":"MeanCache: User-Centric Semantic Caching for LLM Web Services","date":"2024-03-05","arxiv_id":"2403.02694","n_code_links":0,"syntology":null},{"paper":"/paper/information-flow-routes-automatically","slug":"information-flow-routes-automatically","title":"Information Flow Routes: Automatically Interpreting Language Models at Scale","date":"2024-02-27","arxiv_id":"2403.00824","n_code_links":1,"syntology":null},{"paper":"/paper/truthx-alleviating-hallucinations-by-editing","slug":"truthx-alleviating-hallucinations-by-editing","title":"TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space","date":"2024-02-27","arxiv_id":"2402.17811","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":3,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["ictnlp/truthx"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/pandora-s-white-box-increased-training-data","slug":"pandora-s-white-box-increased-training-data","title":"Pandora's White-Box: Precise Training Data Detection and Extraction in Large Language Models","date":"2024-02-26","arxiv_id":"2402.17012","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"rainbow-teaming-open-ended-generation-of","title":"Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts","date":"2024-02-26","arxiv_id":"2402.16822","n_code_links":0,"syntology":null},{"paper":"/paper/how-do-humans-write-code-large-models-do-it","slug":"how-do-humans-write-code-large-models-do-it","title":"How Do Humans Write Code? Large Models Do It the Same Way Too","date":"2024-02-24","arxiv_id":"2402.15729","n_code_links":1,"syntology":null},{"paper":"/paper/prosparse-introducing-and-enhancing-intrinsic","slug":"prosparse-introducing-and-enhancing-intrinsic","title":"ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models","date":"2024-02-21","arxiv_id":"2402.13516","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["raincleared-song/sparse_gpu_operator"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"test-driven-development-for-code-generation","title":"Test-Driven Development for Code Generation","date":"2024-02-21","arxiv_id":"2402.13521","n_code_links":0,"syntology":null},{"paper":"/paper/onebit-towards-extremely-low-bit-large","slug":"onebit-towards-extremely-low-bit-large","title":"OneBit: Towards Extremely Low-bit Large Language Models","date":"2024-02-17","arxiv_id":"2402.11295","n_code_links":1,"syntology":{"ran":8,"of":12,"n_ran_checked":4,"n_instrument":4,"unverified":4,"pointer_only":7,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","official":{"repos":["xuyuzhuang11/onebit"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/network-formation-and-dynamics-among-multi","slug":"network-formation-and-dynamics-among-multi","title":"Network Formation and Dynamics Among Multi-LLMs","date":"2024-02-16","arxiv_id":"2402.10659","n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-imitation-generating-human-mobility","title":"Chain-of-Planned-Behaviour Workflow Elicits Few-Shot Mobility Generation in LLMs","date":"2024-02-15","arxiv_id":"2402.09836","n_code_links":0,"syntology":null},{"paper":"/paper/urbankgent-a-unified-large-language-model","slug":"urbankgent-a-unified-large-language-model","title":"UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Construction","date":"2024-02-10","arxiv_id":"2402.06861","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":1,"n_instrument":2,"unverified":2,"pointer_only":5,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["usail-hkust/urbankgent"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/pedagogical-alignment-of-large-language","slug":"pedagogical-alignment-of-large-language","title":"Pedagogical Alignment of Large Language Models","date":"2024-02-07","arxiv_id":"2402.05000","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-matrix-a-bayesian-learning-model-for-llms","title":"Beyond the Black Box: A Statistical Model for LLM Reasoning and Inference","date":"2024-02-05","arxiv_id":"2402.03175","n_code_links":0,"syntology":null},{"paper":"/paper/autotimes-autoregressive-time-series","slug":"autotimes-autoregressive-time-series","title":"AutoTimes: Autoregressive Time Series Forecasters via Large Language Models","date":"2024-02-04","arxiv_id":"2402.02370","n_code_links":1,"syntology":null},{"paper":null,"slug":"llm4vuln-a-unified-evaluation-framework-for","title":"LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning","date":"2024-01-29","arxiv_id":"2401.16185","n_code_links":0,"syntology":null},{"paper":"/paper/learning-from-emotions-demographic","slug":"learning-from-emotions-demographic","title":"Learning from Implicit User Feedback, Emotions and Demographic Information in Task-Oriented and Document-Grounded Dialogues","date":"2024-01-17","arxiv_id":"2401.09248","n_code_links":1,"syntology":null},{"paper":null,"slug":"low-rank-approximation-for-sparse-attention","title":"Low-Rank Approximation for Sparse Attention in Multi-Modal LLMs","date":"2024-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"do-llm-agents-exhibit-social-behavior","title":"Do LLM Agents Exhibit Social Behavior?","date":"2023-12-23","arxiv_id":"2312.15198","n_code_links":0,"syntology":null},{"paper":null,"slug":"paraphrasing-the-original-text-makes-high","title":"Training With \"Paraphrasing the Original Text\" Improves Long-Context Performance","date":"2023-12-18","arxiv_id":"2312.11193","n_code_links":0,"syntology":null},{"paper":null,"slug":"jellyfish-a-large-language-model-for-data","title":"Jellyfish: A Large Language Model for Data Preprocessing","date":"2023-12-04","arxiv_id":"2312.01678","n_code_links":0,"syntology":null},{"paper":"/paper/gift-generative-interpretable-fine-tuning","slug":"gift-generative-interpretable-fine-tuning","title":"Generative Parameter-Efficient Fine-Tuning","date":"2023-12-01","arxiv_id":"2312.00700","n_code_links":1,"syntology":{"ran":12,"of":16,"n_ran_checked":12,"n_instrument":0,"unverified":4,"pointer_only":10,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["savadikarc/gift"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/mark-my-words-analyzing-and-evaluating","slug":"mark-my-words-analyzing-and-evaluating","title":"Mark My Words: Analyzing and Evaluating Language Model Watermarks","date":"2023-12-01","arxiv_id":"2312.00273","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wagner-group/markmywords"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"scaling-political-texts-with-chatgpt","title":"Positioning Political Texts with Large Language Models by Asking and Averaging","date":"2023-11-28","arxiv_id":"2311.16639","n_code_links":0,"syntology":null},{"paper":"/paper/meditron-70b-scaling-medical-pretraining-for","slug":"meditron-70b-scaling-medical-pretraining-for","title":"MEDITRON-70B: Scaling Medical Pretraining for Large Language Models","date":"2023-11-27","arxiv_id":"2311.16079","n_code_links":1,"syntology":{"ran":9,"of":14,"n_ran_checked":9,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["epfllm/meditron"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/outcome-supervised-verifiers-for-planning-in","slug":"outcome-supervised-verifiers-for-planning-in","title":"OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning","date":"2023-11-16","arxiv_id":"2311.09724","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["freedomintelligence/ovm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/extrinsically-focused-evaluation-of-omissions","slug":"extrinsically-focused-evaluation-of-omissions","title":"Extrinsically-Focused Evaluation of Omissions in Medical Summarization","date":"2023-11-14","arxiv_id":"2311.08303","n_code_links":1,"syntology":null},{"paper":"/paper/fair-abstractive-summarization-of-diverse","slug":"fair-abstractive-summarization-of-diverse","title":"Fair Abstractive Summarization of Diverse Perspectives","date":"2023-11-14","arxiv_id":"2311.07884","n_code_links":1,"syntology":null},{"paper":null,"slug":"llms-and-finetuning-benchmarking-cross-domain","title":"LLMs and Finetuning: Benchmarking cross-domain performance for hate speech detection","date":"2023-10-29","arxiv_id":"2310.18964","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-can-share-images-too","slug":"large-language-models-can-share-images-too","title":"Large Language Models can Share Images, Too!","date":"2023-10-23","arxiv_id":"2310.14804","n_code_links":2,"syntology":null},{"paper":"/paper/entity-matching-using-large-language-models","slug":"entity-matching-using-large-language-models","title":"Entity Matching using Large Language Models","date":"2023-10-17","arxiv_id":"2310.11244","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-is-a-good-question-task-oriented-asking","title":"Alexpaca: Learning Factual Clarification Question Generation Without Examples","date":"2023-10-17","arxiv_id":"2310.11571","n_code_links":0,"syntology":null},{"paper":"/paper/a-systematic-evaluation-of-large-language-1","slug":"a-systematic-evaluation-of-large-language-1","title":"Assessing and Enhancing the Robustness of Large Language Models with Task Structure Variations for Logical Reasoning","date":"2023-10-13","arxiv_id":"2310.09430","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["strong-ai-lab/logical-and-abstract-reasoning"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/typing-to-listen-at-the-cocktail-party-text","slug":"typing-to-listen-at-the-cocktail-party-text","title":"Typing to Listen at the Cocktail Party: Text-Guided Target Speaker Extraction","date":"2023-10-11","arxiv_id":"2310.07284","n_code_links":1,"syntology":null},{"paper":"/paper/query-and-response-augmentation-cannot-help","slug":"query-and-response-augmentation-cannot-help","title":"MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning","date":"2023-10-09","arxiv_id":"2310.05506","n_code_links":1,"syntology":null},{"paper":"/paper/compresso-structured-pruning-with","slug":"compresso-structured-pruning-with","title":"Compresso: Structured Pruning with Collaborative Prompting Learns Compact Large Language Models","date":"2023-10-08","arxiv_id":"2310.05015","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["microsoft/moonlit"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"faceatt-enhancing-image-captioning-with","title":"FaceGemma: Enhancing Image Captioning with Facial Attributes for Portrait Images","date":"2023-09-24","arxiv_id":"2309.13601","n_code_links":0,"syntology":null},{"paper":"/paper/cpllm-clinical-prediction-with-large-language","slug":"cpllm-clinical-prediction-with-large-language","title":"CPLLM: Clinical Prediction with Large Language Models","date":"2023-09-20","arxiv_id":"2309.11295","n_code_links":1,"syntology":null},{"paper":"/paper/amurd-annotated-multilingual-receipts-dataset","slug":"amurd-annotated-multilingual-receipts-dataset","title":"AMuRD: Annotated Arabic-English Receipt Dataset for Key Information Extraction and Classification","date":"2023-09-18","arxiv_id":"2309.09800","n_code_links":1,"syntology":null},{"paper":null,"slug":"accelerating-in-browser-deep-learning","title":"Empowering In-Browser Deep Learning Inference on Edge Devices with Just-in-Time Kernel Optimizations","date":"2023-09-16","arxiv_id":"2309.08978","n_code_links":0,"syntology":null},{"paper":"/paper/cultural-alignment-in-large-language-models","slug":"cultural-alignment-in-large-language-models","title":"Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions","date":"2023-08-25","arxiv_id":"2309.12342","n_code_links":1,"syntology":null},{"paper":"/paper/do-multilingual-language-models-think-better","slug":"do-multilingual-language-models-think-better","title":"Do Multilingual Language Models Think Better in English?","date":"2023-08-02","arxiv_id":"2308.01223","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["juletx/self-translate"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/scaling-sentence-embeddings-with-large","slug":"scaling-sentence-embeddings-with-large","title":"Scaling Sentence Embeddings with Large Language Models","date":"2023-07-31","arxiv_id":"2307.16645","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["kongds/scaling_sentemb"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/can-llms-express-their-uncertainty-an","slug":"can-llms-express-their-uncertainty-an","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","date":"2023-06-22","arxiv_id":"2306.13063","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":0,"n_instrument":3,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["miaoxiong2320/llm-uncertainty"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/in-context-learning-user-simulators-for-task","slug":"in-context-learning-user-simulators-for-task","title":"In-Context Learning User Simulators for Task-Oriented Dialog Systems","date":"2023-06-01","arxiv_id":"2306.00774","n_code_links":2,"syntology":null},{"paper":"/paper/coedit-text-editing-by-task-specific","slug":"coedit-text-editing-by-task-specific","title":"CoEdIT: Text Editing by Task-Specific Instruction Tuning","date":"2023-05-17","arxiv_id":"2305.09857","n_code_links":1,"syntology":null},{"paper":"/paper/neurocomparatives-neuro-symbolic-distillation","slug":"neurocomparatives-neuro-symbolic-distillation","title":"NeuroComparatives: Neuro-Symbolic Distillation of Comparative Knowledge","date":"2023-05-08","arxiv_id":"2305.04978","n_code_links":1,"syntology":null},{"paper":"/paper/llama-open-and-efficient-foundation-language-1","slug":"llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","arxiv_id":"2302.13971","n_code_links":57,"syntology":{"ran":37,"of":58,"n_ran_checked":25,"n_instrument":12,"unverified":21,"pointer_only":4,"phrase":"37 ran (of which 9 constructed an object rather than computing a result; 25 with no instrument failure: 3 honoured, 0 violated, 22 with no contract checked; 12 where Syntology's instrument failed) · 21 unverified","official":{"repos":["facebookresearch/llama"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}}],"record_sha256":"b7209f44356668345882c2a5aed5d319990352517b5aff294db2232ac671aeab","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}