{"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":"/task/language-modeling/papers/32","list_of":"/task/language-modeling","task":"Language Modeling","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":32,"pages_in_order":142,"rows_per_page":100,"rows":[3101,3200],"of":14182,"counts":{"archive_papers_tagged":14182,"with_a_code_link":5620,"where_syntology_ran_a_sample":1894,"not_listed_spam_title":0,"listed":14182,"listed_where_code_ran":1894,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1580,"every_run_a_failure_of_syntologys_instrument":314,"listed_with_a_run_with_no_instrument_failure":1580,"listed_every_run_a_failure_of_syntologys_instrument":314,"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":"/task/language-modeling","prev":"/task/language-modeling/papers/31","next":"/task/language-modeling/papers/33","papers":[{"url":"/paper/sketch-guided-constrained-decoding-for","slug":"sketch-guided-constrained-decoding-for","title":"Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit Access","date":"2024-01-18","arxiv_id":"2401.09967","repositories_listed":1,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"2 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; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/sketch-guided-constrained-decoding-for#ran","syntology_url":"https://syntology.ai/paper/2401.09967","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09967"}},"official":{"repos":["epfl-dlab/sketchgcd"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/skyeyegpt-unifying-remote-sensing-vision","slug":"skyeyegpt-unifying-remote-sensing-vision","title":"SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model","date":"2024-01-18","arxiv_id":"2401.09712","repositories_listed":1,"syntology":null},{"url":"/paper/adcnet-a-unified-framework-for-predicting-the","slug":"adcnet-a-unified-framework-for-predicting-the","title":"ADCNet: a unified framework for predicting the activity of antibody-drug conjugates","date":"2024-01-17","arxiv_id":"2401.09176","repositories_listed":1,"syntology":null},{"url":"/paper/asynchronous-local-sgd-training-for-language","slug":"asynchronous-local-sgd-training-for-language","title":"Asynchronous Local-SGD Training for Language Modeling","date":"2024-01-17","arxiv_id":"2401.09135","repositories_listed":1,"syntology":null},{"url":"/paper/into-the-crossfire-evaluating-the-use-of-a","slug":"into-the-crossfire-evaluating-the-use-of-a","title":"Into the crossfire: evaluating the use of a language model to crowdsource gun violence reports","date":"2024-01-16","arxiv_id":"2401.12989","repositories_listed":1,"syntology":null},{"url":"/paper/telme-teacher-leading-multimodal-fusion","slug":"telme-teacher-leading-multimodal-fusion","title":"TelME: Teacher-leading Multimodal Fusion Network for Emotion Recognition in Conversation","date":"2024-01-16","arxiv_id":"2401.12987","repositories_listed":1,"syntology":null},{"url":"/paper/a-character-based-steganography-using-masked","slug":"a-character-based-steganography-using-masked","title":"A character-based steganography using masked language modeling","date":"2024-01-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/activations-and-gradients-compression-for","slug":"activations-and-gradients-compression-for","title":"Activations and Gradients Compression for Model-Parallel Training","date":"2024-01-15","arxiv_id":"2401.07788","repositories_listed":1,"syntology":null},{"url":"/paper/flexibly-scaling-large-language-models","slug":"flexibly-scaling-large-language-models","title":"Flexibly Scaling Large Language Models Contexts Through Extensible Tokenization","date":"2024-01-15","arxiv_id":"2401.07793","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-importance-of-data-scale-in","slug":"on-the-importance-of-data-scale-in","title":"On the importance of Data Scale in Pretraining Arabic Language Models","date":"2024-01-15","arxiv_id":"2401.07760","repositories_listed":1,"syntology":null},{"url":"/paper/semeval-2017-task-4-sentiment-analysis-in","slug":"semeval-2017-task-4-sentiment-analysis-in","title":"SemEval-2017 Task 4: Sentiment Analysis in Twitter using BERT","date":"2024-01-15","arxiv_id":"2401.07944","repositories_listed":1,"syntology":null},{"url":"/paper/walert-putting-conversational-search","slug":"walert-putting-conversational-search","title":"Walert: Putting Conversational Search Knowledge into Action by Building and Evaluating a Large Language Model-Powered Chatbot","date":"2024-01-14","arxiv_id":"2401.07216","repositories_listed":1,"syntology":null},{"url":"/paper/graph-language-models","slug":"graph-language-models","title":"Graph Language Models","date":"2024-01-13","arxiv_id":"2401.07105","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"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","sample_list":"/paper/graph-language-models#ran","syntology_url":"https://syntology.ai/paper/2401.07105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.07105"}},"official":{"repos":["heidelberg-nlp/graphlanguagemodels"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/generalizing-visual-question-answering-from","slug":"generalizing-visual-question-answering-from","title":"Generalizing Visual Question Answering from Synthetic to Human-Written Questions via a Chain of QA with a Large Language Model","date":"2024-01-12","arxiv_id":"2401.06400","repositories_listed":1,"syntology":null},{"url":"/paper/modaverse-efficiently-transforming-modalities","slug":"modaverse-efficiently-transforming-modalities","title":"ModaVerse: Efficiently Transforming Modalities with LLMs","date":"2024-01-12","arxiv_id":"2401.06395","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_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","sample_list":"/paper/modaverse-efficiently-transforming-modalities#ran","syntology_url":"https://syntology.ai/paper/2401.06395","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.06395"}},"official":{"repos":["xinke-wang/modaverse"],"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"]}}},{"url":"/paper/multi-task-learning-for-front-end-text","slug":"multi-task-learning-for-front-end-text","title":"Multi-Task Learning for Front-End Text Processing in TTS","date":"2024-01-12","arxiv_id":"2401.06321","repositories_listed":1,"syntology":null},{"url":"/paper/prometheus-vision-vision-language-model-as-a","slug":"prometheus-vision-vision-language-model-as-a","title":"Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation","date":"2024-01-12","arxiv_id":"2401.06591","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/prometheus-vision-vision-language-model-as-a#ran","syntology_url":"https://syntology.ai/paper/2401.06591","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.06591"}},"official":{"repos":["kaistai/prometheus-vision"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/combating-adversarial-attacks-with-multi","slug":"combating-adversarial-attacks-with-multi","title":"Combating Adversarial Attacks with Multi-Agent Debate","date":"2024-01-11","arxiv_id":"2401.05998","repositories_listed":1,"syntology":null},{"url":"/paper/legobench-leaderboard-generation-benchmark","slug":"legobench-leaderboard-generation-benchmark","title":"LEGOBench: Scientific Leaderboard Generation Benchmark","date":"2024-01-11","arxiv_id":"2401.06233","repositories_listed":1,"syntology":null},{"url":"/paper/augsumm-towards-generalizable-speech","slug":"augsumm-towards-generalizable-speech","title":"AugSumm: towards generalizable speech summarization using synthetic labels from large language model","date":"2024-01-10","arxiv_id":"2401.06806","repositories_listed":1,"syntology":null},{"url":"/paper/generating-diverse-and-high-quality-texts-by","slug":"generating-diverse-and-high-quality-texts-by","title":"Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding","date":"2024-01-10","arxiv_id":"2401.05054","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/generating-diverse-and-high-quality-texts-by#ran","syntology_url":"https://syntology.ai/paper/2401.05054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05054"}},"official":{"repos":["CyberAgentAILab/diverse-mbr"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/rewriting-the-code-a-simple-method-for-large","slug":"rewriting-the-code-a-simple-method-for-large","title":"Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search","date":"2024-01-09","arxiv_id":"2401.04514","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"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) · 4 unverified","sample_list":"/paper/rewriting-the-code-a-simple-method-for-large#ran","syntology_url":"https://syntology.ai/paper/2401.04514","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.04514"}},"official":{"repos":["alex-haochenli/reco"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/techgpt-2-0-a-large-language-model-project-to","slug":"techgpt-2-0-a-large-language-model-project-to","title":"TechGPT-2.0: A large language model project to solve the task of knowledge graph construction","date":"2024-01-09","arxiv_id":"2401.04507","repositories_listed":1,"syntology":null},{"url":"/paper/twinbooster-synergising-large-language-models","slug":"twinbooster-synergising-large-language-models","title":"TwinBooster: Synergising Large Language Models with Barlow Twins and Gradient Boosting for Enhanced Molecular Property Prediction","date":"2024-01-09","arxiv_id":"2401.04478","repositories_listed":1,"syntology":null},{"url":"/paper/a-content-based-novelty-measure-for-scholarly","slug":"a-content-based-novelty-measure-for-scholarly","title":"A Content-Based Novelty Measure for Scholarly Publications: A Proof of Concept","date":"2024-01-08","arxiv_id":"2401.03642","repositories_listed":1,"syntology":null},{"url":"/paper/anatomy-of-neural-language-models","slug":"anatomy-of-neural-language-models","title":"Anatomy of Neural Language Models","date":"2024-01-08","arxiv_id":"2401.03797","repositories_listed":1,"syntology":null},{"url":"/paper/language-models-understand-numbers-at-least","slug":"language-models-understand-numbers-at-least","title":"Language Models Encode the Value of Numbers Linearly","date":"2024-01-08","arxiv_id":"2401.03735","repositories_listed":1,"syntology":null},{"url":"/paper/the-butterfly-effect-of-altering-prompts-how","slug":"the-butterfly-effect-of-altering-prompts-how","title":"The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performance","date":"2024-01-08","arxiv_id":"2401.03729","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/the-butterfly-effect-of-altering-prompts-how#ran","syntology_url":"https://syntology.ai/paper/2401.03729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03729"}},"official":{"repos":["abel2code/the_butterfly_effect_of_prompts"],"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"]}}},{"url":"/paper/exploring-large-language-model-based","slug":"exploring-large-language-model-based","title":"Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects","date":"2024-01-07","arxiv_id":"2401.03428","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_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) · 1 unverified","sample_list":"/paper/exploring-large-language-model-based#ran","syntology_url":"https://syntology.ai/paper/2401.03428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03428"}},"official":{"repos":["melih-unsal/demogpt"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-models-as-visual-cross-domain","slug":"large-language-models-as-visual-cross-domain","title":"VLLaVO: Mitigating Visual Gap through LLMs","date":"2024-01-06","arxiv_id":"2401.03253","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":13,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/large-language-models-as-visual-cross-domain#ran","syntology_url":"https://syntology.ai/paper/2401.03253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03253"}},"official":{"repos":["LL-a-VO/VLLaVO"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/malla-demystifying-real-world-large-language","slug":"malla-demystifying-real-world-large-language","title":"Malla: Demystifying Real-world Large Language Model Integrated Malicious Services","date":"2024-01-06","arxiv_id":"2401.03315","repositories_listed":1,"syntology":null},{"url":"/paper/aracovtexfinder-leveraging-the-transformer","slug":"aracovtexfinder-leveraging-the-transformer","title":"AraCovTexFinder: Leveraging the transformer-based language model for Arabic COVID-19 text identification","date":"2024-01-04","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/chartassisstant-a-universal-chart-multimodal","slug":"chartassisstant-a-universal-chart-multimodal","title":"ChartAssisstant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning","date":"2024-01-04","arxiv_id":"2401.02384","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/chartassisstant-a-universal-chart-multimodal#ran","syntology_url":"https://syntology.ai/paper/2401.02384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02384"}},"official":{"repos":["opengvlab/chartast"],"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"]}}},{"url":"/paper/generalizable-vision-language-pre-training","slug":"generalizable-vision-language-pre-training","title":"Multi-modal vision-language model for generalizable annotation-free pathology localization and clinical diagnosis","date":"2024-01-04","arxiv_id":"2401.02044","repositories_listed":1,"syntology":null},{"url":"/paper/llava-ph-efficient-multi-modal-assistant-with","slug":"llava-ph-efficient-multi-modal-assistant-with","title":"LLaVA-Phi: Efficient Multi-Modal Assistant with Small Language Model","date":"2024-01-04","arxiv_id":"2401.02330","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/llava-ph-efficient-multi-modal-assistant-with#ran","syntology_url":"https://syntology.ai/paper/2401.02330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02330"}},"official":{"repos":["zhuyiche/llava-phi"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/vulnerabilities-unveiled-adversarially","slug":"vulnerabilities-unveiled-adversarially","title":"Demonstration of an Adversarial Attack Against a Multimodal Vision Language Model for Pathology Imaging","date":"2024-01-04","arxiv_id":"2401.02565","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-model-capabilities-in","slug":"large-language-model-capabilities-in","title":"Large Language Model Capabilities in Perioperative Risk Prediction and Prognostication","date":"2024-01-03","arxiv_id":"2401.01620","repositories_listed":1,"syntology":null},{"url":"/paper/pllama-an-open-source-large-language-model","slug":"pllama-an-open-source-large-language-model","title":"PLLaMa: An Open-source Large Language Model for Plant Science","date":"2024-01-03","arxiv_id":"2401.01600","repositories_listed":1,"syntology":null},{"url":"/paper/cheetah-natural-language-generation-for-517","slug":"cheetah-natural-language-generation-for-517","title":"Cheetah: Natural Language Generation for 517 African Languages","date":"2024-01-02","arxiv_id":"2401.01053","repositories_listed":1,"syntology":null},{"url":"/paper/quokka-an-open-source-large-language-model","slug":"quokka-an-open-source-large-language-model","title":"Quokka: An Open-source Large Language Model ChatBot for Material Science","date":"2024-01-02","arxiv_id":"2401.01089","repositories_listed":1,"syntology":null},{"url":"/paper/general-point-model-pretraining-with","slug":"general-point-model-pretraining-with","title":"General Point Model Pretraining with Autoencoding and Autoregressive","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/large-language-model-for-bible-sentiment","slug":"large-language-model-for-bible-sentiment","title":"Large language model for Bible sentiment analysis: Sermon on the Mount","date":"2024-01-01","arxiv_id":"2401.00689","repositories_listed":1,"syntology":null},{"url":"/paper/lion-empowering-multimodal-large-language-1","slug":"lion-empowering-multimodal-large-language-1","title":"LION: Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/geogalactica-a-scientific-large-language","slug":"geogalactica-a-scientific-large-language","title":"GeoGalactica: A Scientific Large Language Model in Geoscience","date":"2023-12-31","arxiv_id":"2401.00434","repositories_listed":1,"syntology":null},{"url":"/paper/neural-networks-against-and-for-self-training","slug":"neural-networks-against-and-for-self-training","title":"Neural Networks Against (and For) Self-Training: Classification with Small Labeled and Large Unlabeled Sets","date":"2023-12-31","arxiv_id":"2401.00575","repositories_listed":1,"syntology":null},{"url":"/paper/sdif-da-a-shallow-to-deep-interaction","slug":"sdif-da-a-shallow-to-deep-interaction","title":"SDIF-DA: A Shallow-to-Deep Interaction Framework with Data Augmentation for Multi-modal Intent Detection","date":"2023-12-31","arxiv_id":"2401.00424","repositories_listed":1,"syntology":null},{"url":"/paper/open-ti-open-traffic-intelligence-with","slug":"open-ti-open-traffic-intelligence-with","title":"Open-TI: Open Traffic Intelligence with Augmented Language Model","date":"2023-12-30","arxiv_id":"2401.00211","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"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) · 3 unverified","sample_list":"/paper/open-ti-open-traffic-intelligence-with#ran","syntology_url":"https://syntology.ai/paper/2401.00211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.00211"}},"official":{"repos":["darl-libsignal/openti"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/mosaicbert-a-bidirectional-encoder-optimized-1","slug":"mosaicbert-a-bidirectional-encoder-optimized-1","title":"MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining","date":"2023-12-29","arxiv_id":"2312.17482","repositories_listed":1,"syntology":null},{"url":"/paper/an-improved-baseline-for-reasoning","slug":"an-improved-baseline-for-reasoning","title":"LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model","date":"2023-12-28","arxiv_id":"2312.17240","repositories_listed":1,"syntology":{"n":14,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"6 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; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/an-improved-baseline-for-reasoning#ran","syntology_url":"https://syntology.ai/paper/2312.17240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17240"}},"official":null}},{"url":"/paper/drugassist-a-large-language-model-for","slug":"drugassist-a-large-language-model-for","title":"DrugAssist: A Large Language Model for Molecule Optimization","date":"2023-12-28","arxiv_id":"2401.10334","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"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) · 2 unverified","sample_list":"/paper/drugassist-a-large-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2401.10334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10334"}},"official":{"repos":["blazerye/drugassist"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/mobilevlm-a-fast-reproducible-and-strong","slug":"mobilevlm-a-fast-reproducible-and-strong","title":"MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices","date":"2023-12-28","arxiv_id":"2312.16886","repositories_listed":1,"syntology":null},{"url":"/paper/recranker-instruction-tuning-large-language","slug":"recranker-instruction-tuning-large-language","title":"RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k Recommendation","date":"2023-12-26","arxiv_id":"2312.16018","repositories_listed":1,"syntology":null},{"url":"/paper/preliminary-study-on-incremental-learning-for","slug":"preliminary-study-on-incremental-learning-for","title":"Preliminary Study on Incremental Learning for Large Language Model-based Recommender Systems","date":"2023-12-25","arxiv_id":"2312.15599","repositories_listed":1,"syntology":null},{"url":"/paper/fairness-aware-structured-pruning-in","slug":"fairness-aware-structured-pruning-in","title":"Fairness-Aware Structured Pruning in Transformers","date":"2023-12-24","arxiv_id":"2312.15398","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/fairness-aware-structured-pruning-in#ran","syntology_url":"https://syntology.ai/paper/2312.15398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15398"}},"official":{"repos":["chandar-lab/fasp"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/large-language-models-as-zero-shot-keyphrase","slug":"large-language-models-as-zero-shot-keyphrase","title":"Large Language Models as Zero-Shot Keyphrase Extractors: A Preliminary Empirical Study","date":"2023-12-23","arxiv_id":"2312.15156","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-the-potential-of-fpga-based","slug":"understanding-the-potential-of-fpga-based","title":"Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inference","date":"2023-12-23","arxiv_id":"2312.15159","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-novel-gpt-4-apis","slug":"exploiting-novel-gpt-4-apis","title":"Exploiting Novel GPT-4 APIs","date":"2023-12-21","arxiv_id":"2312.14302","repositories_listed":1,"syntology":null},{"url":"/paper/almanacs-a-simulatability-benchmark-for","slug":"almanacs-a-simulatability-benchmark-for","title":"ALMANACS: A Simulatability Benchmark for Language Model Explainability","date":"2023-12-20","arxiv_id":"2312.12747","repositories_listed":1,"syntology":null},{"url":"/paper/cached-transformers-improving-transformers","slug":"cached-transformers-improving-transformers","title":"Cached Transformers: Improving Transformers with Differentiable Memory Cache","date":"2023-12-20","arxiv_id":"2312.12742","repositories_listed":1,"syntology":null},{"url":"/paper/dspy-assertions-computational-constraints-for","slug":"dspy-assertions-computational-constraints-for","title":"DSPy Assertions: Computational Constraints for Self-Refining Language Model Pipelines","date":"2023-12-20","arxiv_id":"2312.13382","repositories_listed":1,"syntology":null},{"url":"/paper/ecamp-entity-centered-context-aware-medical","slug":"ecamp-entity-centered-context-aware-medical","title":"ECAMP: Entity-centered Context-aware Medical Vision Language Pre-training","date":"2023-12-20","arxiv_id":"2312.13316","repositories_listed":1,"syntology":null},{"url":"/paper/lookahead-an-inference-acceleration-framework","slug":"lookahead-an-inference-acceleration-framework","title":"Lookahead: An Inference Acceleration Framework for Large Language Model with Lossless Generation Accuracy","date":"2023-12-20","arxiv_id":"2312.12728","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_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) · 1 unverified","sample_list":"/paper/lookahead-an-inference-acceleration-framework#ran","syntology_url":"https://syntology.ai/paper/2312.12728","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12728"}},"official":{"repos":["alipay/PainlessInferenceAcceleration"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/time-is-encoded-in-the-weights-of-finetuned","slug":"time-is-encoded-in-the-weights-of-finetuned","title":"Time is Encoded in the Weights of Finetuned Language Models","date":"2023-12-20","arxiv_id":"2312.13401","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_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) · 3 unverified","sample_list":"/paper/time-is-encoded-in-the-weights-of-finetuned#ran","syntology_url":"https://syntology.ai/paper/2312.13401","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.13401"}},"official":{"repos":["KaiNylund/lm-weights-encode-time"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/avoiding-data-contamination-in-language-model","slug":"avoiding-data-contamination-in-language-model","title":"LatestEval: Addressing Data Contamination in Language Model Evaluation through Dynamic and Time-Sensitive Test Construction","date":"2023-12-19","arxiv_id":"2312.12343","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"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) · 4 unverified","sample_list":"/paper/avoiding-data-contamination-in-language-model#ran","syntology_url":"https://syntology.ai/paper/2312.12343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12343"}},"official":{"repos":["liyucheng09/latesteval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/ipad-iterative-parallel-and-diffusion-based","slug":"ipad-iterative-parallel-and-diffusion-based","title":"IPAD: Iterative, Parallel, and Diffusion-based Network for Scene Text Recognition","date":"2023-12-19","arxiv_id":"2312.11923","repositories_listed":1,"syntology":null},{"url":"/paper/cascade-speculative-drafting-for-even-faster","slug":"cascade-speculative-drafting-for-even-faster","title":"Cascade Speculative Drafting for Even Faster LLM Inference","date":"2023-12-18","arxiv_id":"2312.11462","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/cascade-speculative-drafting-for-even-faster#ran","syntology_url":"https://syntology.ai/paper/2312.11462","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11462"}},"official":{"repos":["lfsszd/cs-drafting"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/entity-or-relation-embeddings-an-analysis-of","slug":"entity-or-relation-embeddings-an-analysis-of","title":"Entity or Relation Embeddings? An Analysis of Encoding Strategies for Relation Extraction","date":"2023-12-18","arxiv_id":"2312.11062","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-graphs-and-pre-trained-language","slug":"knowledge-graphs-and-pre-trained-language","title":"Knowledge Graphs and Pre-trained Language Models enhanced Representation Learning for Conversational Recommender Systems","date":"2023-12-18","arxiv_id":"2312.10967","repositories_listed":1,"syntology":null},{"url":"/paper/decoding-concerns-multi-label-classification","slug":"decoding-concerns-multi-label-classification","title":"Decoding Concerns: Multi-label Classification of Vaccine Sentiments in Social Media","date":"2023-12-17","arxiv_id":"2312.10626","repositories_listed":1,"syntology":null},{"url":"/paper/rolecraft-glm-advancing-personalized-role","slug":"rolecraft-glm-advancing-personalized-role","title":"RoleCraft-GLM: Advancing Personalized Role-Playing in Large Language Models","date":"2023-12-17","arxiv_id":"2401.09432","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"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","sample_list":"/paper/rolecraft-glm-advancing-personalized-role#ran","syntology_url":"https://syntology.ai/paper/2401.09432","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09432"}},"official":{"repos":["tml2002/rolecraft"],"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"]}}},{"url":"/paper/starvector-generating-scalable-vector","slug":"starvector-generating-scalable-vector","title":"StarVector: Generating Scalable Vector Graphics Code from Images and Text","date":"2023-12-17","arxiv_id":"2312.11556","repositories_listed":1,"syntology":null},{"url":"/paper/catwalk-a-unified-language-model-evaluation","slug":"catwalk-a-unified-language-model-evaluation","title":"Catwalk: A Unified Language Model Evaluation Framework for Many Datasets","date":"2023-12-15","arxiv_id":"2312.10253","repositories_listed":1,"syntology":null},{"url":"/paper/context-driven-interactive-query-simulations","slug":"context-driven-interactive-query-simulations","title":"Context-Driven Interactive Query Simulations Based on Generative Large Language Models","date":"2023-12-15","arxiv_id":"2312.09631","repositories_listed":1,"syntology":null},{"url":"/paper/topic-vq-vae-leveraging-latent-codebooks-for","slug":"topic-vq-vae-leveraging-latent-codebooks-for","title":"Topic-VQ-VAE: Leveraging Latent Codebooks for Flexible Topic-Guided Document Generation","date":"2023-12-15","arxiv_id":"2312.11532","repositories_listed":1,"syntology":null},{"url":"/paper/dissecting-vocabulary-biases-datasets-through","slug":"dissecting-vocabulary-biases-datasets-through","title":"Dissecting vocabulary biases datasets through statistical testing and automated data augmentation for artifact mitigation in Natural Language Inference","date":"2023-12-14","arxiv_id":"2312.08747","repositories_listed":1,"syntology":null},{"url":"/paper/helping-or-herding-reward-model-ensembles","slug":"helping-or-herding-reward-model-ensembles","title":"Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking","date":"2023-12-14","arxiv_id":"2312.09244","repositories_listed":1,"syntology":null},{"url":"/paper/modeling-complex-mathematical-reasoning-via","slug":"modeling-complex-mathematical-reasoning-via","title":"Modeling Complex Mathematical Reasoning via Large Language Model based MathAgent","date":"2023-12-14","arxiv_id":"2312.08926","repositories_listed":1,"syntology":null},{"url":"/paper/tap4llm-table-provider-on-sampling-augmenting","slug":"tap4llm-table-provider-on-sampling-augmenting","title":"TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning","date":"2023-12-14","arxiv_id":"2312.09039","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":12,"n_pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tap4llm-table-provider-on-sampling-augmenting#ran","syntology_url":"https://syntology.ai/paper/2312.09039","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09039"}},"official":null}},{"url":"/paper/unbiased-organism-agnostic-and-highly","slug":"unbiased-organism-agnostic-and-highly","title":"Unbiased organism-agnostic and highly sensitive signal peptide predictor with deep protein language model","date":"2023-12-14","arxiv_id":"2312.08987","repositories_listed":1,"syntology":null},{"url":"/paper/breaking-the-silence-the-threats-of-using","slug":"breaking-the-silence-the-threats-of-using","title":"Breaking the Silence: the Threats of Using LLMs in Software Engineering","date":"2023-12-13","arxiv_id":"2312.08055","repositories_listed":1,"syntology":null},{"url":"/paper/foundationpose-unified-6d-pose-estimation-and","slug":"foundationpose-unified-6d-pose-estimation-and","title":"FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects","date":"2023-12-13","arxiv_id":"2312.08344","repositories_listed":1,"syntology":null},{"url":"/paper/vlap-efficient-video-language-alignment-via","slug":"vlap-efficient-video-language-alignment-via","title":"ViLA: Efficient Video-Language Alignment for Video Question Answering","date":"2023-12-13","arxiv_id":"2312.08367","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_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","sample_list":"/paper/vlap-efficient-video-language-alignment-via#ran","syntology_url":"https://syntology.ai/paper/2312.08367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08367"}},"official":{"repos":["xijun-cs/vila"],"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"]}}},{"url":"/paper/hallucination-augmented-contrastive-learning","slug":"hallucination-augmented-contrastive-learning","title":"Hallucination Augmented Contrastive Learning for Multimodal Large Language Model","date":"2023-12-12","arxiv_id":"2312.06968","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hallucination-augmented-contrastive-learning#ran","syntology_url":"https://syntology.ai/paper/2312.06968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06968"}},"official":{"repos":["x-plug/mplug-halowl"],"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","unlocated"]}}},{"url":"/paper/on-diverse-preferences-for-large-language","slug":"on-diverse-preferences-for-large-language","title":"On Diversified Preferences of Large Language Model Alignment","date":"2023-12-12","arxiv_id":"2312.07401","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_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","sample_list":"/paper/on-diverse-preferences-for-large-language#ran","syntology_url":"https://syntology.ai/paper/2312.07401","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.07401"}},"official":{"repos":["dunzeng/more"],"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"]}}},{"url":"/paper/read-pvla-recurrent-adapter-with-partial","slug":"read-pvla-recurrent-adapter-with-partial","title":"READ: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling","date":"2023-12-12","arxiv_id":"2312.06950","repositories_listed":1,"syntology":null},{"url":"/paper/gta-gated-toxicity-avoidance-for-lm","slug":"gta-gated-toxicity-avoidance-for-lm","title":"GTA: Gated Toxicity Avoidance for LM Performance Preservation","date":"2023-12-11","arxiv_id":"2312.06122","repositories_listed":1,"syntology":null},{"url":"/paper/mmdesign-multi-modality-transfer-learning-for","slug":"mmdesign-multi-modality-transfer-learning-for","title":"Progressive Multi-Modality Learning for Inverse Protein Folding","date":"2023-12-11","arxiv_id":"2312.06297","repositories_listed":1,"syntology":null},{"url":"/paper/promptmtopic-unsupervised-multimodal-topic","slug":"promptmtopic-unsupervised-multimodal-topic","title":"PromptMTopic: Unsupervised Multimodal Topic Modeling of Memes using Large Language Models","date":"2023-12-11","arxiv_id":"2312.06093","repositories_listed":1,"syntology":null},{"url":"/paper/agile-quant-activation-guided-quantization","slug":"agile-quant-activation-guided-quantization","title":"Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge","date":"2023-12-09","arxiv_id":"2312.05693","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/agile-quant-activation-guided-quantization#ran","syntology_url":"https://syntology.ai/paper/2312.05693","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.05693"}},"official":{"repos":["shawnricecake/agile-quant"],"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"]}}},{"url":"/paper/history-matters-temporal-knowledge-editing-in","slug":"history-matters-temporal-knowledge-editing-in","title":"History Matters: Temporal Knowledge Editing in Large Language Model","date":"2023-12-09","arxiv_id":"2312.05497","repositories_listed":1,"syntology":null},{"url":"/paper/labrador-exploring-the-limits-of-masked","slug":"labrador-exploring-the-limits-of-masked","title":"Labrador: Exploring the Limits of Masked Language Modeling for Laboratory Data","date":"2023-12-09","arxiv_id":"2312.11502","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_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","sample_list":"/paper/labrador-exploring-the-limits-of-masked#ran","syntology_url":"https://syntology.ai/paper/2312.11502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11502"}},"official":{"repos":["davidbellamy/labrador"],"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"]}}},{"url":"/paper/preserving-privacy-through-dememorization-an","slug":"preserving-privacy-through-dememorization-an","title":"Preserving Privacy Through Dememorization: An Unlearning Technique For Mitigating Memorization Risks In Language Models","date":"2023-12-09","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/boosting-prompt-based-self-training-with","slug":"boosting-prompt-based-self-training-with","title":"Boosting Prompt-Based Self-Training With Mapping-Free Automatic Verbalizer for Multi-Class Classification","date":"2023-12-08","arxiv_id":"2312.04982","repositories_listed":1,"syntology":null},{"url":"/paper/fine-tuning-instructpix2pix-for-advanced","slug":"fine-tuning-instructpix2pix-for-advanced","title":"Fine-Tuning InstructPix2Pix for Advanced Image Colorization","date":"2023-12-08","arxiv_id":"2312.04780","repositories_listed":1,"syntology":null},{"url":"/paper/how-to-determine-the-most-powerful-pre","slug":"how-to-determine-the-most-powerful-pre","title":"How to Determine the Most Powerful Pre-trained Language Model without Brute Force Fine-tuning? An Empirical Survey","date":"2023-12-08","arxiv_id":"2312.04775","repositories_listed":1,"syntology":null},{"url":"/paper/sparq-attention-bandwidth-efficient-llm","slug":"sparq-attention-bandwidth-efficient-llm","title":"SparQ Attention: Bandwidth-Efficient LLM Inference","date":"2023-12-08","arxiv_id":"2312.04985","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sparq-attention-bandwidth-efficient-llm#ran","syntology_url":"https://syntology.ai/paper/2312.04985","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04985"}},"official":{"repos":["graphcore-research/llm-inference-research"],"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"]}}},{"url":"/paper/typefly-flying-drones-with-large-language","slug":"typefly-flying-drones-with-large-language","title":"TypeFly: Flying Drones with Large Language Model","date":"2023-12-08","arxiv_id":"2312.14950","repositories_listed":1,"syntology":null},{"url":"/paper/chain-of-code-reasoning-with-a-language-model","slug":"chain-of-code-reasoning-with-a-language-model","title":"Chain of Code: Reasoning with a Language Model-Augmented Code Emulator","date":"2023-12-07","arxiv_id":"2312.04474","repositories_listed":1,"syntology":null},{"url":"/paper/lampilot-an-open-benchmark-dataset-for","slug":"lampilot-an-open-benchmark-dataset-for","title":"LaMPilot: An Open Benchmark Dataset for Autonomous Driving with Language Model Programs","date":"2023-12-07","arxiv_id":"2312.04372","repositories_listed":1,"syntology":null},{"url":"/paper/language-model-knowledge-distillation-for","slug":"language-model-knowledge-distillation-for","title":"Language Model Knowledge Distillation for Efficient Question Answering in Spanish","date":"2023-12-07","arxiv_id":"2312.04193","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_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","sample_list":"/paper/language-model-knowledge-distillation-for#ran","syntology_url":"https://syntology.ai/paper/2312.04193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04193"}},"official":{"repos":["adrianbzg/tinyroberta-distillation-qa-es"],"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"]}}}],"record_sha256":"4e34945b9bafd16a483c9c1cbf25f7289ff511bb7931b146864f404d813d7692","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}