{"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/cosine-annealing/papers/21","list_of":"/method/cosine-annealing","method":"Cosine Annealing","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":21,"pages_in_order":40,"rows_per_page":100,"rows":[2001,2100],"of":3965,"counts":{"archive_papers_tagged":3965,"with_a_code_link":1734,"where_syntology_ran_a_sample":627,"not_listed_spam_title":0,"listed":3965,"listed_where_code_ran":627,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":513,"every_run_a_failure_of_syntologys_instrument":114,"listed_with_a_run_with_no_instrument_failure":513,"listed_every_run_a_failure_of_syntologys_instrument":114,"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/cosine-annealing","prev":"/method/cosine-annealing/papers/20","next":"/method/cosine-annealing/papers/22","papers":[{"paper":null,"slug":"rcagent-cloud-root-cause-analysis-by","title":"RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models","date":"2023-10-25","arxiv_id":"2310.16340","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-communication-theory-perspective-on","title":"A Communication Theory Perspective on Prompting Engineering Methods for Large Language Models","date":"2023-10-24","arxiv_id":"2310.18358","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-language-model-with-limited-memory-capacity","title":"A Language Model with Limited Memory Capacity Captures Interference in Human Sentence Processing","date":"2023-10-24","arxiv_id":"2310.16142","n_code_links":0,"syntology":null},{"paper":null,"slug":"ai-enhanced-auto-correction-of-programming","title":"AI-enhanced Auto-correction of Programming Exercises: How Effective is GPT-3.5?","date":"2023-10-24","arxiv_id":"2311.10737","n_code_links":0,"syntology":null},{"paper":"/paper/background-summarization-of-event-timelines","slug":"background-summarization-of-event-timelines","title":"Background Summarization of Event Timelines","date":"2023-10-24","arxiv_id":"2310.16197","n_code_links":1,"syntology":null},{"paper":null,"slug":"dissecting-in-context-learning-of","title":"Dissecting In-Context Learning of Translations in GPTs","date":"2023-10-24","arxiv_id":"2310.15987","n_code_links":0,"syntology":null},{"paper":"/paper/fighting-fire-with-fire-the-dual-role-of-llms","slug":"fighting-fire-with-fire-the-dual-role-of-llms","title":"Fighting Fire with Fire: The Dual Role of LLMs in Crafting and Detecting Elusive Disinformation","date":"2023-10-24","arxiv_id":"2310.15515","n_code_links":1,"syntology":null},{"paper":"/paper/learning-from-free-text-human-feedback","slug":"learning-from-free-text-human-feedback","title":"Learning From Free-Text Human Feedback -- Collect New Datasets Or Extend Existing Ones?","date":"2023-10-24","arxiv_id":"2310.15758","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["ukplab/emnlp2023-learning-from-free-text-human-feedback"],"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/the-janus-interface-how-fine-tuning-in-large","slug":"the-janus-interface-how-fine-tuning-in-large","title":"The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks","date":"2023-10-24","arxiv_id":"2310.15469","n_code_links":1,"syntology":null},{"paper":"/paper/trams-training-free-memory-selection-for-long","slug":"trams-training-free-memory-selection-for-long","title":"TRAMS: Training-free Memory Selection for Long-range Language Modeling","date":"2023-10-24","arxiv_id":"2310.15494","n_code_links":1,"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":["lwaekfjlk/trams"],"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":null,"slug":"what-makes-it-ok-to-set-a-fire-iterative-self","title":"What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations","date":"2023-10-24","arxiv_id":"2310.15431","n_code_links":0,"syntology":null},{"paper":null,"slug":"causal-inference-using-llm-guided-discovery","title":"Causal Inference Using LLM-Guided Discovery","date":"2023-10-23","arxiv_id":"2310.15117","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-spatial-understanding-of-large","slug":"evaluating-spatial-understanding-of-large","title":"Evaluating Spatial Understanding of Large Language Models","date":"2023-10-23","arxiv_id":"2310.14540","n_code_links":1,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["runopti/spatialevalllm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"evaluating-the-knowledge-base-completion","title":"Evaluating the Knowledge Base Completion Potential of GPT","date":"2023-10-23","arxiv_id":"2310.14771","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-pre-trained-transformer-for-1","title":"Generative Pre-trained Transformer for Vietnamese Community-based COVID-19 Question Answering","date":"2023-10-23","arxiv_id":"2310.14602","n_code_links":0,"syntology":null},{"paper":null,"slug":"gpt-4-as-an-effective-zero-shot-evaluator-for","title":"GPT-4 as an Effective Zero-Shot Evaluator for Scientific Figure Captions","date":"2023-10-23","arxiv_id":"2310.15405","n_code_links":0,"syntology":null},{"paper":null,"slug":"instructexcel-a-benchmark-for-natural","title":"InstructExcel: A Benchmark for Natural Language Instruction in Excel","date":"2023-10-23","arxiv_id":"2310.14495","n_code_links":0,"syntology":null},{"paper":"/paper/language-models-hallucinate-but-may-excel-at","slug":"language-models-hallucinate-but-may-excel-at","title":"Language Models Hallucinate, but May Excel at Fact Verification","date":"2023-10-23","arxiv_id":"2310.14564","n_code_links":1,"syntology":{"ran":6,"of":9,"n_ran_checked":6,"n_instrument":0,"unverified":3,"pointer_only":9,"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) · 3 unverified","official":{"repos":["jianguanthu/llmforfv"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/linc-a-neurosymbolic-approach-for-logical","slug":"linc-a-neurosymbolic-approach-for-logical","title":"LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers","date":"2023-10-23","arxiv_id":"2310.15164","n_code_links":1,"syntology":{"ran":1,"of":7,"n_ran_checked":0,"n_instrument":1,"unverified":6,"pointer_only":7,"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) · 6 unverified","official":{"repos":["benlipkin/linc"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/llm-in-the-loop-leveraging-large-language","slug":"llm-in-the-loop-leveraging-large-language","title":"LLM-in-the-loop: Leveraging Large Language Model for Thematic Analysis","date":"2023-10-23","arxiv_id":"2310.15100","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"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":["sjdai/llm-thematic-analysis"],"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":"prefix-tuning-based-unsupervised-text-style","title":"Prefix-Tuning Based Unsupervised Text Style Transfer","date":"2023-10-23","arxiv_id":"2310.14599","n_code_links":0,"syntology":null},{"paper":"/paper/teleqna-a-benchmark-dataset-to-assess-large","slug":"teleqna-a-benchmark-dataset-to-assess-large","title":"TeleQnA: A Benchmark Dataset to Assess Large Language Models Telecommunications Knowledge","date":"2023-10-23","arxiv_id":"2310.15051","n_code_links":1,"syntology":null},{"paper":"/paper/the-continued-usefulness-of-vocabulary-tests","slug":"the-continued-usefulness-of-vocabulary-tests","title":"Establishing Vocabulary Tests as a Benchmark for Evaluating Large Language Models","date":"2023-10-23","arxiv_id":"2310.14703","n_code_links":1,"syntology":null},{"paper":"/paper/towards-a-mechanistic-interpretation-of-multi","slug":"towards-a-mechanistic-interpretation-of-multi","title":"Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models","date":"2023-10-23","arxiv_id":"2310.14491","n_code_links":2,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":{"repos":["yifan-h/mechanisticprobe"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/can-language-models-laugh-at-youtube-short","slug":"can-language-models-laugh-at-youtube-short","title":"Can Language Models Laugh at YouTube Short-form Videos?","date":"2023-10-22","arxiv_id":"2310.14159","n_code_links":1,"syntology":null},{"paper":"/paper/is-chatgpt-a-game-changer-for-geocoding-a","slug":"is-chatgpt-a-game-changer-for-geocoding-a","title":"Is ChatGPT a game changer for geocoding -- a benchmark for geocoding address parsing techniques","date":"2023-10-22","arxiv_id":"2310.14360","n_code_links":1,"syntology":null},{"paper":"/paper/text-generation-for-dataset-augmentation-in","slug":"text-generation-for-dataset-augmentation-in","title":"Text generation for dataset augmentation in security classification tasks","date":"2023-10-22","arxiv_id":"2310.14429","n_code_links":1,"syntology":null},{"paper":"/paper/gemba-mqm-detecting-translation-quality-error","slug":"gemba-mqm-detecting-translation-quality-error","title":"GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4","date":"2023-10-21","arxiv_id":"2310.13988","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":8,"n_instrument":0,"unverified":0,"pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"haterephrase-zero-and-few-shot-reduction-of","title":"HateRephrase: Zero- and Few-Shot Reduction of Hate Intensity in Online Posts using Large Language Models","date":"2023-10-21","arxiv_id":"2310.13985","n_code_links":0,"syntology":null},{"paper":"/paper/a-simple-baseline-for-knowledge-based-visual","slug":"a-simple-baseline-for-knowledge-based-visual","title":"A Simple Baseline for Knowledge-Based Visual Question Answering","date":"2023-10-20","arxiv_id":"2310.13570","n_code_links":0,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":3,"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) · 1 unverified","official":null}},{"paper":null,"slug":"alltogether-investigating-the-efficacy-of","title":"AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models","date":"2023-10-20","arxiv_id":"2310.18331","n_code_links":0,"syntology":null},{"paper":null,"slug":"application-of-deep-learning-for-livestock","title":"Application of deep learning for livestock behaviour recognition: A systematic literature review","date":"2023-10-20","arxiv_id":"2310.13483","n_code_links":0,"syntology":null},{"paper":"/paper/cache-me-if-you-can-an-online-cost-aware","slug":"cache-me-if-you-can-an-online-cost-aware","title":"Cache me if you Can: an Online Cost-aware Teacher-Student framework to Reduce the Calls to Large Language Models","date":"2023-10-20","arxiv_id":"2310.13395","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: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["stoyian/OCaTS"],"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":"challenges-and-contributing-factors-in-the","title":"Challenges and Contributing Factors in the Utilization of Large Language Models (LLMs)","date":"2023-10-20","arxiv_id":"2310.13343","n_code_links":0,"syntology":null},{"paper":null,"slug":"design-inclusive-language-models-for","title":"She had Cobalt Blue Eyes: Prompt Testing to Create Aligned and Sustainable Language Models","date":"2023-10-20","arxiv_id":"2310.18333","n_code_links":0,"syntology":null},{"paper":null,"slug":"equivariant-transformer-is-all-you-need","title":"Equivariant Transformer is all you need","date":"2023-10-20","arxiv_id":"2310.13222","n_code_links":0,"syntology":null},{"paper":null,"slug":"foundation-model-s-embedded-representations","title":"Foundation Model's Embedded Representations May Detect Distribution Shift","date":"2023-10-20","arxiv_id":"2310.13836","n_code_links":0,"syntology":null},{"paper":null,"slug":"robust-training-for-conversational-question","title":"Robust Training for Conversational Question Answering Models with Reinforced Reformulation Generation","date":"2023-10-20","arxiv_id":"2310.13505","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-perils-promises-of-fact-checking-with","title":"The Perils & Promises of Fact-checking with Large Language Models","date":"2023-10-20","arxiv_id":"2310.13549","n_code_links":0,"syntology":null},{"paper":null,"slug":"wordart-designer-user-driven-artistic","title":"WordArt Designer: User-Driven Artistic Typography Synthesis using Large Language Models","date":"2023-10-20","arxiv_id":"2310.18332","n_code_links":0,"syntology":null},{"paper":"/paper/agenttuning-enabling-generalized-agent","slug":"agenttuning-enabling-generalized-agent","title":"AgentTuning: Enabling Generalized Agent Abilities for LLMs","date":"2023-10-19","arxiv_id":"2310.12823","n_code_links":1,"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":["thudm/agenttuning"],"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":null,"slug":"an-exploration-of-in-context-learning-for","title":"Exploring In-Context Learning of Textless Speech Language Model for Speech Classification Tasks","date":"2023-10-19","arxiv_id":"2310.12477","n_code_links":0,"syntology":null},{"paper":null,"slug":"experimental-narratives-a-comparison-of-human","title":"Experimental Narratives: A Comparison of Human Crowdsourced Storytelling and AI Storytelling","date":"2023-10-19","arxiv_id":"2310.12902","n_code_links":0,"syntology":null},{"paper":"/paper/identifying-and-adapting-transformer","slug":"identifying-and-adapting-transformer","title":"Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model","date":"2023-10-19","arxiv_id":"2310.12611","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":5,"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) · 1 unverified","official":{"repos":["iabhijith/bias-causal-analysis"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"laser-linear-compression-in-wireless","title":"LASER: Linear Compression in Wireless Distributed Optimization","date":"2023-10-19","arxiv_id":"2310.13033","n_code_links":0,"syntology":null},{"paper":null,"slug":"not-all-countries-celebrate-thanksgiving-on","title":"Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models","date":"2023-10-19","arxiv_id":"2310.12481","n_code_links":0,"syntology":null},{"paper":"/paper/product-attribute-value-extraction-using","slug":"product-attribute-value-extraction-using","title":"ExtractGPT: Exploring the Potential of Large Language Models for Product Attribute Value Extraction","date":"2023-10-19","arxiv_id":"2310.12537","n_code_links":1,"syntology":null},{"paper":"/paper/the-shifted-and-the-overlooked-a-task","slug":"the-shifted-and-the-overlooked-a-task","title":"The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions","date":"2023-10-19","arxiv_id":"2310.12418","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":["ozyyshr/sharegpt_investigation"],"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":"evaluating-the-symbol-binding-ability-of","title":"Evaluating the Symbol Binding Ability of Large Language Models for Multiple-Choice Questions in Vietnamese General Education","date":"2023-10-18","arxiv_id":"2310.12059","n_code_links":0,"syntology":null},{"paper":null,"slug":"solving-the-multiplication-problem-of-a-large","title":"Solving the multiplication problem of a large language model system using a graph-based method","date":"2023-10-18","arxiv_id":"2310.13016","n_code_links":0,"syntology":null},{"paper":null,"slug":"emergent-ai-assisted-discourse-case-study-of","title":"Emergent AI-Assisted Discourse: Case Study of a Second Language Writer Authoring with ChatGPT","date":"2023-10-17","arxiv_id":"2310.10903","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-llms-for-privilege-escalation","slug":"evaluating-llms-for-privilege-escalation","title":"LLMs as Hackers: Autonomous Linux Privilege Escalation Attacks","date":"2023-10-17","arxiv_id":"2310.11409","n_code_links":1,"syntology":null},{"paper":"/paper/intent-detection-and-slot-filling-for-home","slug":"intent-detection-and-slot-filling-for-home","title":"Intent Detection and Slot Filling for Home Assistants: Dataset and Analysis for Bangla and Sylheti","date":"2023-10-17","arxiv_id":"2310.10935","n_code_links":1,"syntology":null},{"paper":"/paper/probing-the-creativity-of-large-language","slug":"probing-the-creativity-of-large-language","title":"Probing the Creativity of Large Language Models: Can models produce divergent semantic association?","date":"2023-10-17","arxiv_id":"2310.11158","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":{"repos":["dingnlab/probing_creativity"],"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":null,"slug":"utilising-a-large-language-model-to-annotate","title":"Utilising a Large Language Model to Annotate Subject Metadata: A Case Study in an Australian National Research Data Catalogue","date":"2023-10-17","arxiv_id":"2310.11318","n_code_links":0,"syntology":null},{"paper":"/paper/approximating-two-layer-feedforward-networks","slug":"approximating-two-layer-feedforward-networks","title":"Approximating Two-Layer Feedforward Networks for Efficient Transformers","date":"2023-10-16","arxiv_id":"2310.10837","n_code_links":2,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["robertcsordas/moe","robertcsordas/moe_layer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"battle-of-the-large-language-models-dolly-vs","title":"Battle of the Large Language Models: Dolly vs LLaMA vs Vicuna vs Guanaco vs Bard vs ChatGPT -- A Text-to-SQL Parsing Comparison","date":"2023-10-16","arxiv_id":"2310.10190","n_code_links":0,"syntology":null},{"paper":"/paper/bioplanner-automatic-evaluation-of-llms-on","slug":"bioplanner-automatic-evaluation-of-llms-on","title":"BioPlanner: Automatic Evaluation of LLMs on Protocol Planning in Biology","date":"2023-10-16","arxiv_id":"2310.10632","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"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":["bioplanner/bioplanner"],"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":"/paper/data-contamination-through-the-lens-of-time","slug":"data-contamination-through-the-lens-of-time","title":"Data Contamination Through the Lens of Time","date":"2023-10-16","arxiv_id":"2310.10628","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":["abacusai/to-the-cutoff"],"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":"fine-tuning-chatgpt-for-automatic-scoring","title":"Fine-tuning ChatGPT for Automatic Scoring","date":"2023-10-16","arxiv_id":"2310.10072","n_code_links":0,"syntology":null},{"paper":null,"slug":"moconvq-unified-physics-based-motion-control","title":"MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations","date":"2023-10-16","arxiv_id":"2310.10198","n_code_links":0,"syntology":null},{"paper":null,"slug":"prediction-of-arabic-legal-rulings-using","title":"Prediction of Arabic Legal Rulings using Large Language Models","date":"2023-10-16","arxiv_id":"2310.10260","n_code_links":0,"syntology":null},{"paper":"/paper/transom-an-efficient-fault-tolerant-system","slug":"transom-an-efficient-fault-tolerant-system","title":"TRANSOM: An Efficient Fault-Tolerant System for Training LLMs","date":"2023-10-16","arxiv_id":"2310.10046","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"0 ran · 3 unverified","official":{"repos":["SenseCore/transom-checkpoint-engine"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"paper":null,"slug":"configuration-validation-with-large-language","title":"Configuration Validation with Large Language Models","date":"2023-10-15","arxiv_id":"2310.09690","n_code_links":0,"syntology":null},{"paper":null,"slug":"image-augmentation-with-controlled-diffusion","title":"Image Augmentation with Controlled Diffusion for Weakly-Supervised Semantic Segmentation","date":"2023-10-15","arxiv_id":"2310.09760","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-model-aware-in-context","title":"Large Language Model-Aware In-Context Learning for Code Generation","date":"2023-10-15","arxiv_id":"2310.09748","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-for-in-context-student","slug":"large-language-models-for-in-context-student","title":"Large Language Models for In-Context Student Modeling: Synthesizing Student's Behavior in Visual Programming","date":"2023-10-15","arxiv_id":"2310.10690","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-model-agnostic-multi-group","title":"Efficient Model-Agnostic Multi-Group Equivariant Networks","date":"2023-10-14","arxiv_id":"2310.09675","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":null,"slug":"from-words-and-exercises-to-wellness-farsi","title":"From Words and Exercises to Wellness: Farsi Chatbot for Self-Attachment Technique","date":"2023-10-13","arxiv_id":"2310.09362","n_code_links":0,"syntology":null},{"paper":"/paper/human-in-the-loop-machine-translation-with","slug":"human-in-the-loop-machine-translation-with","title":"Human-in-the-loop Machine Translation with Large Language Model","date":"2023-10-13","arxiv_id":"2310.08908","n_code_links":1,"syntology":null},{"paper":null,"slug":"table-gpt-table-tuned-gpt-for-diverse-table","title":"Table-GPT: Table-tuned GPT for Diverse Table Tasks","date":"2023-10-13","arxiv_id":"2310.09263","n_code_links":0,"syntology":null},{"paper":"/paper/towards-end-to-end-4-bit-inference-on","slug":"towards-end-to-end-4-bit-inference-on","title":"QUIK: Towards End-to-End 4-Bit Inference on Generative Large Language Models","date":"2023-10-13","arxiv_id":"2310.09259","n_code_links":1,"syntology":{"ran":9,"of":13,"n_ran_checked":9,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["ist-daslab/quik"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/jailbreaking-black-box-large-language-models","slug":"jailbreaking-black-box-large-language-models","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","date":"2023-10-12","arxiv_id":"2310.08419","n_code_links":1,"syntology":{"ran":2,"of":7,"n_ran_checked":1,"n_instrument":1,"unverified":5,"pointer_only":0,"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) · 5 unverified","official":{"repos":["patrickrchao/jailbreakingllms"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"large-language-models-can-replicate-cross","title":"Large language models can replicate cross-cultural differences in personality","date":"2023-10-12","arxiv_id":"2310.10679","n_code_links":0,"syntology":null},{"paper":null,"slug":"multiclass-classification-of-policy-documents","title":"Multiclass Classification of Policy Documents with Large Language Models","date":"2023-10-12","arxiv_id":"2310.08167","n_code_links":0,"syntology":null},{"paper":null,"slug":"promptor-a-conversational-and-autonomous","title":"Promptor: A Conversational and Autonomous Prompt Generation Agent for Intelligent Text Entry Techniques","date":"2023-10-12","arxiv_id":"2310.08101","n_code_links":0,"syntology":null},{"paper":"/paper/qasina-religious-domain-question-answering","slug":"qasina-religious-domain-question-answering","title":"QASiNa: Religious Domain Question Answering using Sirah Nabawiyah","date":"2023-10-12","arxiv_id":"2310.08102","n_code_links":1,"syntology":null},{"paper":null,"slug":"training-generative-question-answering-on","title":"Training Generative Question-Answering on Synthetic Data Obtained from an Instruct-tuned Model","date":"2023-10-12","arxiv_id":"2310.08072","n_code_links":0,"syntology":null},{"paper":null,"slug":"diversity-of-thought-improves-reasoning","title":"Diversity of Thought Improves Reasoning Abilities of LLMs","date":"2023-10-11","arxiv_id":"2310.07088","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-landscape-of-large-language","title":"Do Large Language Models have Shared Weaknesses in Medical Question Answering?","date":"2023-10-11","arxiv_id":"2310.07225","n_code_links":0,"syntology":null},{"paper":"/paper/found-in-the-middle-permutation-self","slug":"found-in-the-middle-permutation-self","title":"Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language Models","date":"2023-10-11","arxiv_id":"2310.07712","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["castorini/perm-sc"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/instructretro-instruction-tuning-post","slug":"instructretro-instruction-tuning-post","title":"InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining","date":"2023-10-11","arxiv_id":"2310.07713","n_code_links":1,"syntology":null},{"paper":"/paper/large-language-models-are-zero-shot-time-1","slug":"large-language-models-are-zero-shot-time-1","title":"Large Language Models Are Zero-Shot Time Series Forecasters","date":"2023-10-11","arxiv_id":"2310.07820","n_code_links":2,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ngruver/llmtime"],"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":["listed","official"]}}},{"paper":"/paper/uncovering-hidden-connections-iterative","slug":"uncovering-hidden-connections-iterative","title":"Uncovering Hidden Connections: Iterative Search and Reasoning for Video-grounded Dialog","date":"2023-10-11","arxiv_id":"2310.07259","n_code_links":2,"syntology":{"ran":3,"of":6,"n_ran_checked":1,"n_instrument":2,"unverified":3,"pointer_only":6,"phrase":"3 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; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["hyu-zhang/itr","Hyu-Zhang/ISR"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"wigenai-the-symphony-of-wireless-and","title":"Diffusion Models for Wireless Communications","date":"2023-10-11","arxiv_id":"2310.07312","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-clinical-coding-using-off-the-shelf","title":"Automated clinical coding using off-the-shelf large language models","date":"2023-10-10","arxiv_id":"2310.06552","n_code_links":0,"syntology":null},{"paper":"/paper/geollm-extracting-geospatial-knowledge-from","slug":"geollm-extracting-geospatial-knowledge-from","title":"GeoLLM: Extracting Geospatial Knowledge from Large Language Models","date":"2023-10-10","arxiv_id":"2310.06213","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["rohinmanvi/GeoLLM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"gpt-4-as-an-agronomist-assistant-answering","title":"GPT-4 as an Agronomist Assistant? Answering Agriculture Exams Using Large Language Models","date":"2023-10-10","arxiv_id":"2310.06225","n_code_links":0,"syntology":null},{"paper":"/paper/humans-and-language-models-diverge-when","slug":"humans-and-language-models-diverge-when","title":"Humans and language models diverge when predicting repeating text","date":"2023-10-10","arxiv_id":"2310.06408","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":["huthlab/lm-repeating-text"],"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/large-language-models-for-propaganda","slug":"large-language-models-for-propaganda","title":"Large Language Models for Propaganda Detection","date":"2023-10-10","arxiv_id":"2310.06422","n_code_links":2,"syntology":null},{"paper":"/paper/longllmlingua-accelerating-and-enhancing-llms","slug":"longllmlingua-accelerating-and-enhancing-llms","title":"LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression","date":"2023-10-10","arxiv_id":"2310.06839","n_code_links":3,"syntology":null},{"paper":"/paper/seer-a-knapsack-approach-to-exemplar","slug":"seer-a-knapsack-approach-to-exemplar","title":"SEER : A Knapsack approach to Exemplar Selection for In-Context HybridQA","date":"2023-10-10","arxiv_id":"2310.06675","n_code_links":1,"syntology":{"ran":6,"of":16,"n_ran_checked":5,"n_instrument":1,"unverified":10,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified","official":{"repos":["jtonglet/seer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":10,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"cabbage-sweeter-than-cake-analysing-the","title":"Cabbage Sweeter than Cake? Analysing the Potential of Large Language Models for Learning Conceptual Spaces","date":"2023-10-09","arxiv_id":"2310.05481","n_code_links":0,"syntology":null},{"paper":null,"slug":"foundation-models-meet-visualizations","title":"Foundation Models Meet Visualizations: Challenges and Opportunities","date":"2023-10-09","arxiv_id":"2310.05771","n_code_links":0,"syntology":null},{"paper":"/paper/mbbc-exploring-the-multilingual-maze","slug":"mbbc-exploring-the-multilingual-maze","title":"Exploring the Maze of Multilingual Modeling","date":"2023-10-09","arxiv_id":"2310.05404","n_code_links":0,"syntology":null},{"paper":null,"slug":"sc-safety-a-multi-round-open-ended-question","title":"SC-Safety: A Multi-round Open-ended Question Adversarial Safety Benchmark for Large Language Models in Chinese","date":"2023-10-09","arxiv_id":"2310.05818","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-program-testing-ability-of-large-language","title":"The Program Testing Ability of Large Language Models for Code","date":"2023-10-09","arxiv_id":"2310.05727","n_code_links":0,"syntology":null},{"paper":null,"slug":"are-emily-and-greg-still-more-employable-than","title":"Are Emily and Greg Still More Employable than Lakisha and Jamal? Investigating Algorithmic Hiring Bias in the Era of ChatGPT","date":"2023-10-08","arxiv_id":"2310.05135","n_code_links":0,"syntology":null},{"paper":"/paper/distantly-supervised-joint-entity-and","slug":"distantly-supervised-joint-entity-and","title":"Distantly-Supervised Joint Extraction with Noise-Robust Learning","date":"2023-10-08","arxiv_id":"2310.04994","n_code_links":1,"syntology":null}],"record_sha256":"945548f6cba2b606354e02530264750a1e61c39da9b69a6b669ad8f2fdb5236d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}