{"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/bloom","slug":"bloom","name":"BLOOM","full_name":"BLOOM","full_name_withheld":false,"description_markdown":"**BLOOM** is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of\r\nsources in 46 natural and 13 programming languages (59 in total).","description_state":"present","introduced_year":null,"introduced_by":{"title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","paper":"/paper/bloom-a-176b-parameter-open-access","first_author":"BigScience Workshop","n_authors":394,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/bloom-a-176b-parameter-open-access"},"source":{"url":"https://arxiv.org/abs/2211.05100v4","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Language Models","url":"/methods/category/language-models","pwc_aliases":[]}],"n_papers_tagged":116,"archive_num_papers":116,"papers_newest_first":[{"paper":"/paper/ai-driven-multi-source-data-fusion-for-algal","slug":"ai-driven-multi-source-data-fusion-for-algal","title":"AI-driven multi-source data fusion for algal bloom severity classification in small inland water bodies: Leveraging Sentinel-2, DEM, and NOAA climate data","date":"2025-05-02","arxiv_id":"2505.03808","n_code_links":1,"syntology":null},{"paper":null,"slug":"decentralizing-ai-memory-shimi-a-semantic","title":"Decentralizing AI Memory: SHIMI, a Semantic Hierarchical Memory Index for Scalable Agent Reasoning","date":"2025-04-08","arxiv_id":"2504.06135","n_code_links":0,"syntology":null},{"paper":null,"slug":"cascaded-learned-bloom-filter-for-optimal","title":"Cascaded Learned Bloom Filter for Optimal Model-Filter Size Balance and Fast Rejection","date":"2025-02-06","arxiv_id":"2502.03696","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-does-a-multilingual-lm-handle-multiple","title":"How does a Multilingual LM Handle Multiple Languages?","date":"2025-02-06","arxiv_id":"2502.04269","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-privacy-model-for-classical-learned-bloom","title":"Adversarially Robust Bloom Filters: Privacy, Reductions, and Open Problems","date":"2025-01-27","arxiv_id":"2501.15751","n_code_links":0,"syntology":null},{"paper":null,"slug":"implicit-causality-biases-in-humans-and-llms","title":"Implicit Causality-biases in humans and LLMs as a tool for benchmarking LLM discourse capabilities","date":"2025-01-22","arxiv_id":"2501.12980","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-robustness-of-multilingual-llms-on","slug":"exploring-robustness-of-multilingual-llms-on","title":"Exploring Robustness of Multilingual LLMs on Real-World Noisy Data","date":"2025-01-14","arxiv_id":"2501.08322","n_code_links":1,"syntology":null},{"paper":"/paper/bloomcoreset-fast-coreset-sampling-using","slug":"bloomcoreset-fast-coreset-sampling-using","title":"BloomCoreset: Fast Coreset Sampling using Bloom Filters for Fine-Grained Self-Supervised Learning","date":"2024-12-22","arxiv_id":"2412.16942","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-open-source-advantage-in-large-language","title":"The Open Source Advantage in Large Language Models (LLMs)","date":"2024-12-16","arxiv_id":"2412.12004","n_code_links":0,"syntology":null},{"paper":null,"slug":"combining-knowledge-graphs-and-llms-for","title":"Combining knowledge graphs and LLMs for hazardous chemical information management and reuse","date":"2024-12-10","arxiv_id":"2412.09644","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-language-models-as-mirrors-of-societal","title":"Large Language Models as Mirrors of Societal Moral Standards","date":"2024-12-01","arxiv_id":"2412.00956","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-extensive-evaluation-of-factual","title":"An Extensive Evaluation of Factual Consistency in Large Language Models for Data-to-Text Generation","date":"2024-11-28","arxiv_id":"2411.19203","n_code_links":0,"syntology":null},{"paper":null,"slug":"la4sr-illuminating-the-dark-proteome-with","title":"LA4SR: illuminating the dark proteome with generative AI","date":"2024-11-11","arxiv_id":"2411.06798","n_code_links":0,"syntology":null},{"paper":null,"slug":"lshbloom-memory-efficient-extreme-scale","title":"LSHBloom: Memory-efficient, Extreme-scale Document Deduplication","date":"2024-11-06","arxiv_id":"2411.04257","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-benefits-of-domain-pretraining","title":"Exploring the Benefits of Domain-Pretraining of Generative Large Language Models for Chemistry","date":"2024-11-05","arxiv_id":"2411.03542","n_code_links":0,"syntology":null},{"paper":null,"slug":"converging-to-a-lingua-franca-evolution-of","title":"Converging to a Lingua Franca: Evolution of Linguistic Regions and Semantics Alignment in Multilingual Large Language Models","date":"2024-10-15","arxiv_id":"2410.11718","n_code_links":0,"syntology":null},{"paper":null,"slug":"lstm-networks-provide-efficient","title":"LSTM networks provide efficient cyanobacterial blooms forecasting even with incomplete spatio-temporal data","date":"2024-10-09","arxiv_id":"2410.08237","n_code_links":0,"syntology":null},{"paper":"/paper/commonit-commonality-aware-instruction-tuning","slug":"commonit-commonality-aware-instruction-tuning","title":"CommonIT: Commonality-Aware Instruction Tuning for Large Language Models via Data Partitions","date":"2024-10-04","arxiv_id":"2410.03077","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"1 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; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["raojay7/commonit"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"k-mer-based-approaches-to-bridging","title":"k-mer-based approaches to bridging pangenomics and population genetics","date":"2024-09-18","arxiv_id":"2409.11683","n_code_links":0,"syntology":null},{"paper":"/paper/goldfish-monolingual-language-models-for-350","slug":"goldfish-monolingual-language-models-for-350","title":"Goldfish: Monolingual Language Models for 350 Languages","date":"2024-08-19","arxiv_id":"2408.10441","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":3,"n_instrument":1,"unverified":1,"pointer_only":5,"phrase":"4 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["tylerachang/goldfish"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"interventional-causal-structure-discovery","title":"Interventional Causal Structure Discovery over Graphical Models with Convergence and Optimality Guarantees","date":"2024-08-09","arxiv_id":"2408.04819","n_code_links":0,"syntology":null},{"paper":null,"slug":"impact-of-model-size-on-fine-tuned-llm","title":"Impact of Model Size on Fine-tuned LLM Performance in Data-to-Text Generation: A State-of-the-Art Investigation","date":"2024-07-19","arxiv_id":"2407.14088","n_code_links":0,"syntology":null},{"paper":null,"slug":"mini-llm-memory-efficient-structured-pruning","title":"MINI-LLM: Memory-Efficient Structured Pruning for Large Language Models","date":"2024-07-16","arxiv_id":"2407.11681","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-portability-strategies-for-open","title":"Language Portability Strategies for Open-domain Dialogue with Pre-trained Language Models from High to Low Resource Languages","date":"2024-07-01","arxiv_id":"2407.01315","n_code_links":0,"syntology":null},{"paper":"/paper/preference-tuning-for-toxicity-mitigation","slug":"preference-tuning-for-toxicity-mitigation","title":"Preference Tuning For Toxicity Mitigation Generalizes Across Languages","date":"2024-06-23","arxiv_id":"2406.16235","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":5,"n_instrument":2,"unverified":2,"pointer_only":0,"phrase":"7 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; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["batsresearch/cross-lingual-detox"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"identity-with-locality-an-ideal-hash-for-gene","title":"IDentity with Locality: An ideal hash for gene sequence search","date":"2024-06-21","arxiv_id":"2406.14901","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-the-emergence-of-cross-lingual","title":"Probing the Emergence of Cross-lingual Alignment during LLM Training","date":"2024-06-19","arxiv_id":"2406.13229","n_code_links":0,"syntology":null},{"paper":null,"slug":"estimating-the-increase-in-emissions-caused","title":"Estimating the Increase in Emissions caused by AI-augmented Search","date":"2024-06-17","arxiv_id":"2407.16894","n_code_links":0,"syntology":null},{"paper":null,"slug":"multilingual-large-language-models-and-curse","title":"Multilingual Large Language Models and Curse of Multilinguality","date":"2024-06-15","arxiv_id":"2406.10602","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-beyond-english-scaling-the-multilingual","title":"LLMs Beyond English: Scaling the Multilingual Capability of LLMs with Cross-Lingual Feedback","date":"2024-06-03","arxiv_id":"2406.01771","n_code_links":0,"syntology":null},{"paper":"/paper/your-transformer-is-secretly-linear","slug":"your-transformer-is-secretly-linear","title":"Your Transformer is Secretly Linear","date":"2024-05-19","arxiv_id":"2405.12250","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: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["AIRI-Institute/LLM-Microscope"],"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":"llms-can-find-mathematical-reasoning-mistakes","title":"LLMs can Find Mathematical Reasoning Mistakes by Pedagogical Chain-of-Thought","date":"2024-05-09","arxiv_id":"2405.06705","n_code_links":0,"syntology":null},{"paper":null,"slug":"transferring-troubles-cross-lingual","title":"TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning","date":"2024-04-30","arxiv_id":"2404.19597","n_code_links":0,"syntology":null},{"paper":"/paper/indicgenbench-a-multilingual-benchmark-to","slug":"indicgenbench-a-multilingual-benchmark-to","title":"IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languages","date":"2024-04-25","arxiv_id":"2404.16816","n_code_links":1,"syntology":null},{"paper":null,"slug":"sambalingo-teaching-large-language-models-new","title":"SambaLingo: Teaching Large Language Models New Languages","date":"2024-04-08","arxiv_id":"2404.05829","n_code_links":0,"syntology":null},{"paper":null,"slug":"lucky-52-how-many-languages-are-needed-to","title":"How Many Languages Make Good Multilingual Instruction Tuning? A Case Study on BLOOM","date":"2024-04-07","arxiv_id":"2404.04850","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-brain-surgeon-large-language","slug":"multilingual-brain-surgeon-large-language","title":"Multilingual Brain Surgeon: Large Language Models Can be Compressed Leaving No Language Behind","date":"2024-04-06","arxiv_id":"2404.04748","n_code_links":1,"syntology":null},{"paper":null,"slug":"aurora-m-the-first-open-source-multilingual","title":"Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code","date":"2024-03-30","arxiv_id":"2404.00399","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-pruning-of-large-language-model","title":"Toward Adaptive Large Language Models Structured Pruning via Hybrid-grained Weight Importance Assessment","date":"2024-03-16","arxiv_id":"2403.10799","n_code_links":0,"syntology":null},{"paper":null,"slug":"pre-trained-language-models-represent-some","title":"Pre-Trained Language Models Represent Some Geographic Populations Better Than Others","date":"2024-03-16","arxiv_id":"2403.11025","n_code_links":0,"syntology":null},{"paper":"/paper/rcooper-a-real-world-large-scale-dataset-for","slug":"rcooper-a-real-world-large-scale-dataset-for","title":"RCooper: A Real-world Large-scale Dataset for Roadside Cooperative Perception","date":"2024-03-15","arxiv_id":"2403.10145","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":4,"n_instrument":5,"unverified":1,"pointer_only":10,"phrase":"9 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; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["air-thu/dair-rcooper"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/predict-the-next-word-humans-exhibit","slug":"predict-the-next-word-humans-exhibit","title":"Predict the Next Word: Humans exhibit uncertainty in this task and language models _____","date":"2024-02-27","arxiv_id":"2402.17527","n_code_links":2,"syntology":null},{"paper":"/paper/language-specific-neurons-the-key-to","slug":"language-specific-neurons-the-key-to","title":"Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models","date":"2024-02-26","arxiv_id":"2402.16438","n_code_links":1,"syntology":null},{"paper":null,"slug":"xling-a-learned-filter-framework-for","title":"Xling: A Learned Filter Framework for Accelerating High-Dimensional Approximate Similarity Join","date":"2024-02-20","arxiv_id":"2402.13397","n_code_links":0,"syntology":null},{"paper":"/paper/browse-and-concentrate-comprehending","slug":"browse-and-concentrate-comprehending","title":"Browse and Concentrate: Comprehending Multimodal Content via prior-LLM Context Fusion","date":"2024-02-19","arxiv_id":"2402.12195","n_code_links":1,"syntology":null},{"paper":"/paper/hybrid-machine-learning-techniques-in-the","slug":"hybrid-machine-learning-techniques-in-the","title":"Hybrid Machine Learning techniques in the management of harmful algal blooms impact","date":"2024-02-14","arxiv_id":"2402.09271","n_code_links":1,"syntology":null},{"paper":"/paper/identification-of-algal-blooms-in-lakes-in","slug":"identification-of-algal-blooms-in-lakes-in","title":"Identification of algal blooms in lakes in the Baltic states using Sentinel-2 data and artificial neural networks","date":"2024-02-14","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-standardization-of-behavioral-use","title":"On the Standardization of Behavioral Use Clauses and Their Adoption for Responsible Licensing of AI","date":"2024-02-07","arxiv_id":"2402.05979","n_code_links":0,"syntology":null},{"paper":null,"slug":"paramanu-a-family-of-novel-efficient-indic","title":"Paramanu: A Family of Novel Efficient Generative Foundation Language Models for Indian Languages","date":"2024-01-31","arxiv_id":"2401.18034","n_code_links":0,"syntology":null},{"paper":null,"slug":"baichuan2-sum-instruction-finetune-baichuan2","title":"Baichuan2-Sum: Instruction Finetune Baichuan2-7B Model for Dialogue Summarization","date":"2024-01-27","arxiv_id":"2401.15496","n_code_links":0,"syntology":null},{"paper":null,"slug":"long-term-effects-of-india-s-childhood","title":"Long-term Effects of India's Childhood Immunization Program on Earnings and Consumption Expenditure: Comment","date":"2024-01-20","arxiv_id":"2401.11100","n_code_links":0,"syntology":null},{"paper":"/paper/cross-lingual-editing-in-multilingual","slug":"cross-lingual-editing-in-multilingual","title":"Cross-lingual Editing in Multilingual Language Models","date":"2024-01-19","arxiv_id":"2401.10521","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-scalable-structural-representations","title":"Learning Scalable Structural Representations for Link Prediction with Bloom Signatures","date":"2023-12-28","arxiv_id":"2312.16784","n_code_links":0,"syntology":null},{"paper":"/paper/tigerbot-an-open-multilingual-multitask-llm","slug":"tigerbot-an-open-multilingual-multitask-llm","title":"TigerBot: An Open Multilingual Multitask LLM","date":"2023-12-14","arxiv_id":"2312.08688","n_code_links":1,"syntology":null},{"paper":"/paper/distributed-inference-and-fine-tuning-of-1","slug":"distributed-inference-and-fine-tuning-of-1","title":"Distributed Inference and Fine-tuning of Large Language Models Over The Internet","date":"2023-12-13","arxiv_id":"2312.08361","n_code_links":2,"syntology":{"ran":6,"of":6,"n_ran_checked":5,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/perseus-removing-energy-bloat-from-large","slug":"perseus-removing-energy-bloat-from-large","title":"Reducing Energy Bloat in Large Model Training","date":"2023-12-12","arxiv_id":"2312.06902","n_code_links":2,"syntology":null},{"paper":"/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","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":["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"]}}},{"paper":null,"slug":"general-framework-to-evaluate-unlinkability","title":"General Framework to Evaluate Unlinkability in Biometric Template Protection Systems","date":"2023-11-08","arxiv_id":"2311.04633","n_code_links":0,"syntology":null},{"paper":"/paper/fingpt-large-generative-models-for-a-small","slug":"fingpt-large-generative-models-for-a-small","title":"FinGPT: Large Generative Models for a Small Language","date":"2023-11-03","arxiv_id":"2311.05640","n_code_links":0,"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":null}},{"paper":null,"slug":"teacherlm-teaching-to-fish-rather-than-giving","title":"TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling Likewise","date":"2023-10-29","arxiv_id":"2310.19019","n_code_links":0,"syntology":null},{"paper":null,"slug":"condefects-a-new-dataset-to-address-the-data","title":"ConDefects: A New Dataset to Address the Data Leakage Concern for LLM-based Fault Localization and Program Repair","date":"2023-10-25","arxiv_id":"2310.16253","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-the-cognitive-knowledge-structure","title":"Exploring the Cognitive Knowledge Structure of Large Language Models: An Educational Diagnostic Assessment Approach","date":"2023-10-12","arxiv_id":"2310.08172","n_code_links":0,"syntology":null},{"paper":"/paper/fast-partitioned-learned-bloom-filter","slug":"fast-partitioned-learned-bloom-filter","title":"Fast Partitioned Learned Bloom Filter","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/tart-a-plug-and-play-transformer-module-for","slug":"tart-a-plug-and-play-transformer-module-for","title":"TART: A plug-and-play Transformer module for task-agnostic reasoning","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"fptq-fine-grained-post-training-quantization","title":"FPTQ: Fine-grained Post-Training Quantization for Large Language Models","date":"2023-08-30","arxiv_id":"2308.15987","n_code_links":0,"syntology":null},{"paper":"/paper/improving-translation-faithfulness-of-large","slug":"improving-translation-faithfulness-of-large","title":"Improving Translation Faithfulness of Large Language Models via Augmenting Instructions","date":"2023-08-24","arxiv_id":"2308.12674","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":5,"n_instrument":3,"unverified":1,"pointer_only":9,"phrase":"8 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["pppa2019/swie_overmiss_llm4mt"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/halo-estimation-and-reduction-of","slug":"halo-estimation-and-reduction-of","title":"Halo: Estimation and Reduction of Hallucinations in Open-Source Weak Large Language Models","date":"2023-08-22","arxiv_id":"2308.11764","n_code_links":1,"syntology":null},{"paper":"/paper/differential-privacy-linguistic-fairness-and","slug":"differential-privacy-linguistic-fairness-and","title":"Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models","date":"2023-08-17","arxiv_id":"2308.08774","n_code_links":0,"syntology":{"ran":14,"of":23,"n_ran_checked":14,"n_instrument":0,"unverified":9,"pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","official":null}},{"paper":"/paper/llmebench-a-flexible-framework-for","slug":"llmebench-a-flexible-framework-for","title":"LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarking","date":"2023-08-09","arxiv_id":"2308.04945","n_code_links":1,"syntology":null},{"paper":"/paper/do-multilingual-language-models-think-better","slug":"do-multilingual-language-models-think-better","title":"Do Multilingual Language Models Think Better in English?","date":"2023-08-02","arxiv_id":"2308.01223","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":1,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["juletx/self-translate"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"emotionprompt-leveraging-psychology-for-large","title":"Large Language Models Understand and Can be Enhanced by Emotional Stimuli","date":"2023-07-14","arxiv_id":"2307.11760","n_code_links":0,"syntology":null},{"paper":null,"slug":"forward-hysteresis-and-hopf-bifurcation-in-an","title":"Forward hysteresis and Hopf bifurcation in an NPZD model with application to harmful algal blooms","date":"2023-07-12","arxiv_id":"2307.06234","n_code_links":0,"syntology":null},{"paper":"/paper/polylm-an-open-source-polyglot-large-language","slug":"polylm-an-open-source-polyglot-large-language","title":"PolyLM: An Open Source Polyglot Large Language Model","date":"2023-07-12","arxiv_id":"2307.06018","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-technical-report-for-polyglot-ko-open","title":"A Technical Report for Polyglot-Ko: Open-Source Large-Scale Korean Language Models","date":"2023-06-04","arxiv_id":"2306.02254","n_code_links":0,"syntology":null},{"paper":"/paper/bigtrans-augmenting-large-language-models","slug":"bigtrans-augmenting-large-language-models","title":"BigTranslate: Augmenting Large Language Models with Multilingual Translation Capability over 100 Languages","date":"2023-05-29","arxiv_id":"2305.18098","n_code_links":2,"syntology":null},{"paper":"/paper/pivoine-instruction-tuning-for-open-world","slug":"pivoine-instruction-tuning-for-open-world","title":"PIVOINE: Instruction Tuning for Open-world Information Extraction","date":"2023-05-24","arxiv_id":"2305.14898","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":["lukeming-tsinghua/instruction-tuning-for-open-world-ie"],"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":"/paper/tricking-llms-into-disobedience-understanding","slug":"tricking-llms-into-disobedience-understanding","title":"Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks","date":"2023-05-24","arxiv_id":"2305.14965","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["AetherPrior/TrickLLM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/decomposed-prompting-for-machine-translation","slug":"decomposed-prompting-for-machine-translation","title":"Decomposed Prompting for Machine Translation Between Related Languages using Large Language Models","date":"2023-05-22","arxiv_id":"2305.13085","n_code_links":1,"syntology":null},{"paper":"/paper/prompting-with-pseudo-code-instructions","slug":"prompting-with-pseudo-code-instructions","title":"Prompting with Pseudo-Code Instructions","date":"2023-05-19","arxiv_id":"2305.11790","n_code_links":2,"syntology":{"ran":6,"of":13,"n_ran_checked":6,"n_instrument":0,"unverified":7,"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) · 7 unverified","official":{"repos":["mayank31398/pseudo-code-instructions"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"mem-rec-memory-efficient-recommendation","title":"Mem-Rec: Memory Efficient Recommendation System using Alternative Representation","date":"2023-05-12","arxiv_id":"2305.07205","n_code_links":0,"syntology":null},{"paper":null,"slug":"lacos-bloom-low-rank-adaptation-with","title":"LACoS-BLOOM: Low-rank Adaptation with Contrastive objective on 8 bits Siamese-BLOOM","date":"2023-05-10","arxiv_id":"2305.06404","n_code_links":0,"syntology":null},{"paper":null,"slug":"high-throughput-cotton-phenotyping-big-data","title":"High-throughput Cotton Phenotyping Big Data Pipeline Lambda Architecture Computer Vision Deep Neural Networks","date":"2023-05-09","arxiv_id":"2305.05423","n_code_links":0,"syntology":null},{"paper":null,"slug":"governance-of-the-ai-by-the-ai-and-for-the-ai","title":"Governance of the AI, by the AI, and for the AI","date":"2023-05-04","arxiv_id":"2305.03719","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-sampling-of-algal-blooms-using","slug":"adaptive-sampling-of-algal-blooms-using","title":"Adaptive Sampling of Algal Blooms Using Autonomous Underwater Vehicle and Satellite Imagery: Experimental Validation in the Baltic Sea","date":"2023-05-01","arxiv_id":"2305.00774","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-efficient-hash-based-data-structure-for","title":"An Efficient Hash-based Data Structure for Dynamic Vision Sensors and its Application to Low-energy Low-memory Noise Filtering","date":"2023-04-28","arxiv_id":"2304.14688","n_code_links":0,"syntology":null},{"paper":"/paper/impact-of-position-bias-on-language-models-in","slug":"impact-of-position-bias-on-language-models-in","title":"Technical Report: Impact of Position Bias on Language Models in Token Classification","date":"2023-04-26","arxiv_id":"2304.13567","n_code_links":2,"syntology":null},{"paper":null,"slug":"who-s-the-best-detective-llms-vs-mls-in","title":"Who's the Best Detective? LLMs vs. MLs in Detecting Incoherent Fourth Grade Math Answers","date":"2023-04-21","arxiv_id":"2304.11257","n_code_links":0,"syntology":null},{"paper":"/paper/outlier-suppression-accurate-quantization-of","slug":"outlier-suppression-accurate-quantization-of","title":"Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling","date":"2023-04-18","arxiv_id":"2304.09145","n_code_links":1,"syntology":{"ran":5,"of":7,"n_ran_checked":2,"n_instrument":3,"unverified":2,"pointer_only":0,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["modeltc/outlier_suppression_plus"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/llm-adapters-an-adapter-family-for-parameter","slug":"llm-adapters-an-adapter-family-for-parameter","title":"LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models","date":"2023-04-04","arxiv_id":"2304.01933","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["agi-edgerunners/llm-adapters"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/llmmaps-a-visual-metaphor-for-stratified","slug":"llmmaps-a-visual-metaphor-for-stratified","title":"LLMMaps -- A Visual Metaphor for Stratified Evaluation of Large Language Models","date":"2023-04-02","arxiv_id":"2304.00457","n_code_links":1,"syntology":null},{"paper":"/paper/towards-phytoplankton-parasite-detection","slug":"towards-phytoplankton-parasite-detection","title":"Towards Phytoplankton Parasite Detection Using Autoencoders","date":"2023-03-15","arxiv_id":"2303.08744","n_code_links":1,"syntology":null},{"paper":null,"slug":"extending-the-pre-training-of-bloom-for","title":"Extending the Pre-Training of BLOOM for Improved Support of Traditional Chinese: Models, Methods and Results","date":"2023-03-08","arxiv_id":"2303.04715","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-carbon-emissions-of-writing-and","title":"The Carbon Emissions of Writing and Illustrating Are Lower for AI than for Humans","date":"2023-03-08","arxiv_id":"2303.06219","n_code_links":0,"syntology":null},{"paper":"/paper/investigating-the-translation-performance-of","slug":"investigating-the-translation-performance-of","title":"Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOM","date":"2023-03-03","arxiv_id":"2303.01911","n_code_links":1,"syntology":null},{"paper":"/paper/intermittent-upwelling-events-trigger-delayed","slug":"intermittent-upwelling-events-trigger-delayed","title":"Intermittent Upwelling Events Trigger Delayed, Major, and Reproducible Pico-Nanophytoplankton Responses in Coastal Oligotrophic Waters","date":"2023-03-02","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/the-roots-search-tool-data-transparency-for","slug":"the-roots-search-tool-data-transparency-for","title":"The ROOTS Search Tool: Data Transparency for LLMs","date":"2023-02-27","arxiv_id":"2302.14035","n_code_links":1,"syntology":null},{"paper":null,"slug":"benchmarking-of-cancelable-biometrics-for","title":"Benchmarking of Cancelable Biometrics for Deep Templates","date":"2023-02-26","arxiv_id":"2302.13286","n_code_links":0,"syntology":null},{"paper":"/paper/in-what-languages-are-generative-language","slug":"in-what-languages-are-generative-language","title":"In What Languages are Generative Language Models the Most Formal? Analyzing Formality Distribution across Languages","date":"2023-02-23","arxiv_id":"2302.12299","n_code_links":1,"syntology":null},{"paper":"/paper/bounding-the-capabilities-of-large-language","slug":"bounding-the-capabilities-of-large-language","title":"Bounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraints","date":"2023-02-17","arxiv_id":"2302.09185","n_code_links":1,"syntology":null},{"paper":null,"slug":"complex-qa-and-language-models-hybrid","title":"Complex QA and language models hybrid architectures, Survey","date":"2023-02-17","arxiv_id":"2302.09051","n_code_links":0,"syntology":null}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":116,"with_a_code_link":51,"where_syntology_ran_a_sample":18,"not_listed_spam_title":0,"listed":116,"listed_where_code_ran":18,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":15,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":15,"listed_every_run_a_failure_of_syntologys_instrument":3,"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"},"papers_where_code_ran":18,"papers_where_code_ran_first_page":"/method/bloom/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"archive","page":2,"of":2,"url":"/method/bloom/papers/2","json":"/method/bloom/papers/2.json","rows":16},{"order":"ran","page":1,"of":1,"url":"/method/bloom/papers/ran/1","json":"/method/bloom/papers/ran/1.json","rows":18}],"tasks":[{"task":"/task/language-modelling","name":"Language Modelling","papers":17},{"task":"/task/language-modeling","name":"Language Modeling","papers":12},{"task":"/task/machine-translation","name":"Machine Translation","papers":8},{"task":"/task/question-answering","name":"Question Answering","papers":8},{"task":"/task/text-generation","name":"Text Generation","papers":8},{"task":"/task/large-language-model","name":"Large Language Model","papers":6},{"task":"/task/translation","name":"Translation","papers":6},{"task":"/task/quantization","name":"Quantization","papers":5},{"task":"/task/model","name":"model","papers":5},{"task":"/task/benchmarking","name":"Benchmarking","papers":4},{"task":"/task/decoder","name":"Decoder","papers":4},{"task":"/task/retrieval","name":"Retrieval","papers":4},{"task":"/task/cross-lingual-transfer","name":"Cross-Lingual Transfer","papers":3},{"task":"/task/diversity","name":"Diversity","papers":3},{"task":null,"name":"GPU","papers":3},{"task":"/task/instruction-following","name":"Instruction Following","papers":3},{"task":"/task/mmlu","name":"MMLU","papers":3},{"task":"/task/math","name":"Math","papers":3},{"task":"/task/named-entity-recognition-1","name":"Named Entity Recognition","papers":3},{"task":"/task/sentence","name":"Sentence","papers":3}],"tasks_shown":20,"n_tasks":140,"usage_by_year":[{"year":"2022","papers":11},{"year":"2023","papers":53},{"year":"2024","papers":45},{"year":"2025","papers":7}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/bloom"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=BLOOM","read_at":"2026-10-05T00:53:12+00:00","query":"BLOOM","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"BLOOM","origin_arxiv_id":"2211.05100"},"resolution":"exact","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"same_paper","archive_paper_arxiv_id":"2211.05100","repositories":{"listed":5,"in_graph":11,"list_truncated":true,"strongest_link":"mentioned_in_paper"},"retrieve_with":null,"name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2211.05100","citations":3017},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'BLOOM'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2211.05100","page":"/paper/bloom-a-176b-parameter-open-access","syntology_url":"https://syntology.ai/paper/2211.05100","in_graph_layer":true,"samples":11,"ran":2,"n_ran_checked":1,"n_instrument":1,"unverified":9,"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) · 9 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"repository known, no verified implementation (declared_code; repositories: 5 listed of 11 in the graph, strongest link: mentioned in the paper). This answer is about arXiv:2211.05100, the paper the archive credits with this method.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"0597254d185122d1a8e008d7676b457c28fa562cbfddbee1dca63eee603113d5","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}