{"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/gpt-4/papers/29","list_of":"/method/gpt-4","method":"GPT-4","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":29,"pages_in_order":29,"rows_per_page":100,"rows":[2801,2870],"of":2870,"counts":{"archive_papers_tagged":2870,"with_a_code_link":1244,"where_syntology_ran_a_sample":526,"not_listed_spam_title":0,"listed":2870,"listed_where_code_ran":526,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":417,"every_run_a_failure_of_syntologys_instrument":109,"listed_with_a_run_with_no_instrument_failure":417,"listed_every_run_a_failure_of_syntologys_instrument":109,"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/gpt-4","prev":"/method/gpt-4/papers/28","next":null,"papers":[{"paper":"/paper/autonomous-gis-the-next-generation-ai-powered","slug":"autonomous-gis-the-next-generation-ai-powered","title":"Autonomous GIS: the next-generation AI-powered GIS","date":"2023-05-10","arxiv_id":"2305.06453","n_code_links":1,"syntology":null},{"paper":null,"slug":"bits-of-grass-does-gpt-already-know-how-to","title":"Bits of Grass: Does GPT already know how to write like Whitman?","date":"2023-05-10","arxiv_id":"2305.11064","n_code_links":0,"syntology":null},{"paper":"/paper/bot-or-human-detecting-chatgpt-imposters-with","slug":"bot-or-human-detecting-chatgpt-imposters-with","title":"Bot or Human? Detecting ChatGPT Imposters with A Single Question","date":"2023-05-10","arxiv_id":"2305.06424","n_code_links":1,"syntology":null},{"paper":"/paper/large-language-models-in-biomedical-natural","slug":"large-language-models-in-biomedical-natural","title":"Benchmarking large language models for biomedical natural language processing applications and recommendations","date":"2023-05-10","arxiv_id":"2305.16326","n_code_links":1,"syntology":null},{"paper":"/paper/frugalgpt-how-to-use-large-language-models","slug":"frugalgpt-how-to-use-large-language-models","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","date":"2023-05-09","arxiv_id":"2305.05176","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":null}},{"paper":"/paper/internchat-solving-vision-centric-tasks-by","slug":"internchat-solving-vision-centric-tasks-by","title":"InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language","date":"2023-05-09","arxiv_id":"2305.05662","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["opengvlab/internchat","opengvlab/interngpt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-building-the-federated-gpt-federated","slug":"towards-building-the-federated-gpt-federated","title":"Towards Building the Federated GPT: Federated Instruction Tuning","date":"2023-05-09","arxiv_id":"2305.05644","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":1,"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) · 1 unverified","official":{"repos":["jayzhang42/federatedgpt-shepherd"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/vision-language-models-in-remote-sensing","slug":"vision-language-models-in-remote-sensing","title":"Vision-Language Models in Remote Sensing: Current Progress and Future Trends","date":"2023-05-09","arxiv_id":"2305.05726","n_code_links":3,"syntology":null},{"paper":null,"slug":"gersteinlab-at-mediqa-chat-2023-clinical-note","title":"GersteinLab at MEDIQA-Chat 2023: Clinical Note Summarization from Doctor-Patient Conversations through Fine-tuning and In-context Learning","date":"2023-05-08","arxiv_id":"2305.05001","n_code_links":0,"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/x-llm-bootstrapping-advanced-large-language","slug":"x-llm-bootstrapping-advanced-large-language","title":"X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages","date":"2023-05-07","arxiv_id":"2305.04160","n_code_links":2,"syntology":{"ran":8,"of":11,"n_ran_checked":4,"n_instrument":4,"unverified":3,"pointer_only":2,"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) · 3 unverified","official":null}},{"paper":"/paper/refining-the-responses-of-llms-by-themselves","slug":"refining-the-responses-of-llms-by-themselves","title":"Refining the Responses of LLMs by Themselves","date":"2023-05-06","arxiv_id":"2305.04039","n_code_links":1,"syntology":null},{"paper":"/paper/lmeye-an-interactive-perception-network-for","slug":"lmeye-an-interactive-perception-network-for","title":"LMEye: An Interactive Perception Network for Large Language Models","date":"2023-05-05","arxiv_id":"2305.03701","n_code_links":1,"syntology":null},{"paper":"/paper/mindgames-targeting-theory-of-mind-in-large","slug":"mindgames-targeting-theory-of-mind-in-large","title":"MindGames: Targeting Theory of Mind in Large Language Models with Dynamic Epistemic Modal Logic","date":"2023-05-05","arxiv_id":"2305.03353","n_code_links":2,"syntology":null},{"paper":null,"slug":"retrieval-augmented-chest-x-ray-report","title":"Retrieval Augmented Chest X-Ray Report Generation using OpenAI GPT models","date":"2023-05-05","arxiv_id":"2305.03660","n_code_links":0,"syntology":null},{"paper":null,"slug":"simulating-h-p-lovecraft-horror-literature","title":"Simulating H.P. Lovecraft horror literature with the ChatGPT large language model","date":"2023-05-05","arxiv_id":"2305.03429","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-automatically-discovered-chain-of-thought","title":"An automatically discovered chain-of-thought prompt generalizes to novel models and datasets","date":"2023-05-04","arxiv_id":"2305.02897","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-4-a-review-on-advancements-and","title":"Gpt-4: A Review on Advancements and Opportunities in Natural Language Processing","date":"2023-05-04","arxiv_id":"2305.03195","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-time-preferences-and-consumer","title":"Can LLMs Capture Human Preferences?","date":"2023-05-04","arxiv_id":"2305.02531","n_code_links":0,"syntology":null},{"paper":"/paper/personallm-investigating-the-ability-of-gpt-3","slug":"personallm-investigating-the-ability-of-gpt-3","title":"PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits","date":"2023-05-04","arxiv_id":"2305.02547","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"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":["hjian42/personallm"],"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":"/paper/a-systematic-study-of-knowledge-distillation","slug":"a-systematic-study-of-knowledge-distillation","title":"A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training","date":"2023-05-03","arxiv_id":"2305.02031","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":2,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["nitaytech/kd4gen"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"clinical-note-generation-from-doctor-patient","title":"WangLab at MEDIQA-Chat 2023: Clinical Note Generation from Doctor-Patient Conversations using Large Language Models","date":"2023-05-03","arxiv_id":"2305.02220","n_code_links":0,"syntology":null},{"paper":"/paper/is-your-code-generated-by-chatgpt-really-1","slug":"is-your-code-generated-by-chatgpt-really-1","title":"Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation","date":"2023-05-02","arxiv_id":"2305.01210","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["evalplus/evalplus"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"new-trends-in-machine-translation-using-large","title":"A Paradigm Shift: The Future of Machine Translation Lies with Large Language Models","date":"2023-05-02","arxiv_id":"2305.01181","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-linguistic-models-analyzing-theoretical","title":"Large Linguistic Models: Investigating LLMs' metalinguistic abilities","date":"2023-05-01","arxiv_id":"2305.00948","n_code_links":0,"syntology":null},{"paper":"/paper/llama-adapter-v2-parameter-efficient-visual","slug":"llama-adapter-v2-parameter-efficient-visual","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","date":"2023-04-28","arxiv_id":"2304.15010","n_code_links":3,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["zrrskywalker/llama-adapter"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":"/paper/speak-memory-an-archaeology-of-books-known-to","slug":"speak-memory-an-archaeology-of-books-known-to","title":"Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4","date":"2023-04-28","arxiv_id":"2305.00118","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"1 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["bamman-group/gpt4-books"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/boosting-big-brother-attacking-search-engines","slug":"boosting-big-brother-attacking-search-engines","title":"Boosting Big Brother: Attacking Search Engines with Encodings","date":"2023-04-27","arxiv_id":"2304.14031","n_code_links":1,"syntology":null},{"paper":null,"slug":"chatgpt-as-an-attack-tool-stealthy-textual","title":"ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model Trigger","date":"2023-04-27","arxiv_id":"2304.14475","n_code_links":0,"syntology":null},{"paper":null,"slug":"conscendi-a-contrastive-and-scenario-guided","title":"CONSCENDI: A Contrastive and Scenario-Guided Distillation Approach to Guardrail Models for Virtual Assistants","date":"2023-04-27","arxiv_id":"2304.14364","n_code_links":0,"syntology":null},{"paper":"/paper/datacomp-in-search-of-the-next-generation-of","slug":"datacomp-in-search-of-the-next-generation-of","title":"DataComp: In search of the next generation of multimodal datasets","date":"2023-04-27","arxiv_id":"2304.14108","n_code_links":3,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mlfoundations/datacomp"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/we-re-afraid-language-models-aren-t-modeling","slug":"we-re-afraid-language-models-aren-t-modeling","title":"We're Afraid Language Models Aren't Modeling Ambiguity","date":"2023-04-27","arxiv_id":"2304.14399","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-case-based-reasoning-framework-for-adaptive","title":"Prompting GPT-3.5 for Text-to-SQL with De-semanticization and Skeleton Retrieval","date":"2023-04-26","arxiv_id":"2304.13301","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-of-gpt-3-5-and-gpt-4-for","title":"Evaluation of GPT-3.5 and GPT-4 for supporting real-world information needs in healthcare delivery","date":"2023-04-26","arxiv_id":"2304.13714","n_code_links":0,"syntology":null},{"paper":"/paper/is-a-prompt-and-a-few-samples-all-you-need","slug":"is-a-prompt-and-a-few-samples-all-you-need","title":"The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification Tasks","date":"2023-04-26","arxiv_id":"2304.13861","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":{"repos":["andersgiovanni/worker_vs_gpt","AGMoller/worker_vs_gpt"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/ai-assisted-coding-experiments-with-gpt-4","slug":"ai-assisted-coding-experiments-with-gpt-4","title":"AI-assisted coding: Experiments with GPT-4","date":"2023-04-25","arxiv_id":"2304.13187","n_code_links":1,"syntology":null},{"paper":null,"slug":"semantic-compression-with-large-language","title":"Semantic Compression With Large Language Models","date":"2023-04-25","arxiv_id":"2304.12512","n_code_links":0,"syntology":null},{"paper":null,"slug":"artificial-general-intelligence-agi-for","title":"AGI: Artificial General Intelligence for Education","date":"2023-04-24","arxiv_id":"2304.12479","n_code_links":0,"syntology":null},{"paper":"/paper/better-question-answering-models-on-a-budget","slug":"better-question-answering-models-on-a-budget","title":"Better Question-Answering Models on a Budget","date":"2023-04-24","arxiv_id":"2304.12370","n_code_links":1,"syntology":null},{"paper":"/paper/wizardlm-empowering-large-language-models-to","slug":"wizardlm-empowering-large-language-models-to","title":"WizardLM: Empowering Large Language Models to Follow Complex Instructions","date":"2023-04-24","arxiv_id":"2304.12244","n_code_links":4,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["nlpxucan/wizardlm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/boosting-theory-of-mind-performance-in-large","slug":"boosting-theory-of-mind-performance-in-large","title":"Boosting Theory-of-Mind Performance in Large Language Models via Prompting","date":"2023-04-22","arxiv_id":"2304.11490","n_code_links":1,"syntology":null},{"paper":"/paper/can-gpt-4-perform-neural-architecture-search","slug":"can-gpt-4-perform-neural-architecture-search","title":"Can GPT-4 Perform Neural Architecture Search?","date":"2023-04-21","arxiv_id":"2304.10970","n_code_links":1,"syntology":null},{"paper":null,"slug":"analyzing-fomc-minutes-accuracy-and","title":"Analyzing FOMC Minutes: Accuracy and Constraints of Language Models","date":"2023-04-20","arxiv_id":"2304.10164","n_code_links":0,"syntology":null},{"paper":"/paper/minigpt-4-enhancing-vision-language","slug":"minigpt-4-enhancing-vision-language","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","date":"2023-04-20","arxiv_id":"2304.10592","n_code_links":6,"syntology":null},{"paper":null,"slug":"performance-of-chatgpt-on-the-us-fundamentals","title":"Performance of ChatGPT on the US Fundamentals of Engineering Exam: Comprehensive Assessment of Proficiency and Potential Implications for Professional Environmental Engineering Practice","date":"2023-04-20","arxiv_id":"2304.12198","n_code_links":0,"syntology":null},{"paper":"/paper/safety-assessment-of-chinese-large-language","slug":"safety-assessment-of-chinese-large-language","title":"Safety Assessment of Chinese Large Language Models","date":"2023-04-20","arxiv_id":"2304.10436","n_code_links":2,"syntology":null},{"paper":"/paper/text2seg-remote-sensing-image-semantic","slug":"text2seg-remote-sensing-image-semantic","title":"Text2Seg: Remote Sensing Image Semantic Segmentation via Text-Guided Visual Foundation Models","date":"2023-04-20","arxiv_id":"2304.10597","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":{"repos":["douglas2code/text2seg"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/chameleon-plug-and-play-compositional","slug":"chameleon-plug-and-play-compositional","title":"Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models","date":"2023-04-19","arxiv_id":"2304.09842","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":null}},{"paper":"/paper/is-chatgpt-good-at-search-investigating-large","slug":"is-chatgpt-good-at-search-investigating-large","title":"Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents","date":"2023-04-19","arxiv_id":"2304.09542","n_code_links":1,"syntology":null},{"paper":"/paper/progressive-hint-prompting-improves-reasoning","slug":"progressive-hint-prompting-improves-reasoning","title":"Progressive-Hint Prompting Improves Reasoning in Large Language Models","date":"2023-04-19","arxiv_id":"2304.09797","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":["chuanyang-Zheng/Progressive-Hint"],"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":null,"slug":"exploring-the-trade-offs-unified-large","title":"Exploring the Trade-Offs: Unified Large Language Models vs Local Fine-Tuned Models for Highly-Specific Radiology NLI Task","date":"2023-04-18","arxiv_id":"2304.09138","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-can-generate-robotic-scripts-from-goal","title":"LLMs can generate robotic scripts from goal-oriented instructions in biological laboratory automation","date":"2023-04-18","arxiv_id":"2304.10267","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-in-depth-investigation-of-user-response","title":"An In-depth Investigation of User Response Simulation for Conversational Search","date":"2023-04-17","arxiv_id":"2304.07944","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-and-effective-text-encoding-for","slug":"efficient-and-effective-text-encoding-for","title":"Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca","date":"2023-04-17","arxiv_id":"2304.08177","n_code_links":6,"syntology":{"ran":18,"of":24,"n_ran_checked":9,"n_instrument":9,"unverified":6,"pointer_only":2,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 9 where Syntology's instrument failed) · 6 unverified","official":{"repos":["ymcui/chinese-llama-alpaca","ymcui/chinese-llama-alpaca-2"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":"/paper/visual-instruction-tuning-1","slug":"visual-instruction-tuning-1","title":"Visual Instruction Tuning","date":"2023-04-17","arxiv_id":"2304.08485","n_code_links":13,"syntology":{"ran":16,"of":51,"n_ran_checked":8,"n_instrument":8,"unverified":35,"pointer_only":0,"phrase":"16 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 35 unverified","official":{"repos":["haotian-liu/LLaVA"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["community","listed","named_in_paper","official"]}}},{"paper":"/paper/api-bank-a-benchmark-for-tool-augmented-llms","slug":"api-bank-a-benchmark-for-tool-augmented-llms","title":"API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs","date":"2023-04-14","arxiv_id":"2304.08244","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"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) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":null}},{"paper":null,"slug":"chatgpt-applications-opportunities-and","title":"ChatGPT: Applications, Opportunities, and Threats","date":"2023-04-14","arxiv_id":"2304.09103","n_code_links":0,"syntology":null},{"paper":"/paper/agieval-a-human-centric-benchmark-for","slug":"agieval-a-human-centric-benchmark-for","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","date":"2023-04-13","arxiv_id":"2304.06364","n_code_links":3,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ruixiangcui/agieval"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/multilingual-machine-translation-with-large","slug":"multilingual-machine-translation-with-large","title":"Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis","date":"2023-04-10","arxiv_id":"2304.04675","n_code_links":2,"syntology":null},{"paper":"/paper/llm-adapters-an-adapter-family-for-parameter","slug":"llm-adapters-an-adapter-family-for-parameter","title":"LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models","date":"2023-04-04","arxiv_id":"2304.01933","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":1,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["agi-edgerunners/llm-adapters"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"one-small-step-for-generative-ai-one-giant","title":"One Small Step for Generative AI, One Giant Leap for AGI: A Complete Survey on ChatGPT in AIGC Era","date":"2023-04-04","arxiv_id":"2304.06488","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-prime-number-divisibility-by-deep","slug":"on-the-prime-number-divisibility-by-deep","title":"Classification of integers based on residue classes via modern deep learning algorithms","date":"2023-04-03","arxiv_id":"2304.01333","n_code_links":1,"syntology":null},{"paper":"/paper/understanding-individual-and-team-based-human","slug":"understanding-individual-and-team-based-human","title":"Does Human Collaboration Enhance the Accuracy of Identifying LLM-Generated Deepfake Texts?","date":"2023-04-03","arxiv_id":"2304.01002","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["huashen218/llm-deepfake-human-study"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/self-refine-iterative-refinement-with-self-1","slug":"self-refine-iterative-refinement-with-self-1","title":"Self-Refine: Iterative Refinement with Self-Feedback","date":"2023-03-30","arxiv_id":"2303.17651","n_code_links":3,"syntology":null},{"paper":"/paper/zero-shot-clinical-entity-recognition-using","slug":"zero-shot-clinical-entity-recognition-using","title":"Improving Large Language Models for Clinical Named Entity Recognition via Prompt Engineering","date":"2023-03-29","arxiv_id":"2303.16416","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-analysis-of-gpt-3-s-performance-in","title":"Analyzing the Performance of GPT-3.5 and GPT-4 in Grammatical Error Correction","date":"2023-03-25","arxiv_id":"2303.14342","n_code_links":0,"syntology":null},{"paper":"/paper/mega-multilingual-evaluation-of-generative-ai","slug":"mega-multilingual-evaluation-of-generative-ai","title":"MEGA: Multilingual Evaluation of Generative AI","date":"2023-03-22","arxiv_id":"2303.12528","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":7,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"8 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; 1 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/reflexion-language-agents-with-verbal","slug":"reflexion-language-agents-with-verbal","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","date":"2023-03-20","arxiv_id":"2303.11366","n_code_links":5,"syntology":{"ran":8,"of":9,"n_ran_checked":6,"n_instrument":2,"unverified":1,"pointer_only":1,"phrase":"8 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["noahshinn024/reflexion"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/how-well-do-large-language-models-perform-in","slug":"how-well-do-large-language-models-perform-in","title":"How well do Large Language Models perform in Arithmetic tasks?","date":"2023-03-16","arxiv_id":"2304.02015","n_code_links":1,"syntology":null},{"paper":"/paper/gpt-4-technical-report-1","slug":"gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","n_code_links":11,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["openai/evals"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"record_sha256":"3850f1d4dd90d24a65a42b1e312cf0b6c847f6b183b0492a98b33614a3d00013","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}