{"url":"/task/world-knowledge","name":"World Knowledge","slug":"world-knowledge","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":818,"papers_with_code":358,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/bear-big","name":"BEAR-probe","full_name":"Benchmark for Evaluating Associative Reasoning","num_papers_in_archive":1},{"url":"/dataset/mm-eval","name":"MM-Eval","full_name":"Modern Mongolian Evaluation","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":358,"tagged_in_all":818,"items":[{"url":"/paper/direct-preference-optimization-your-language","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","date":"2023-05-29","arxiv_id":"2305.18290","repositories_listed":29,"syntology":{"n":31,"n_ran":6,"n_unverified":25,"n_pointer_only":2}},{"url":"/paper/measuring-massive-multitask-language","title":"Measuring Massive Multitask Language Understanding","date":"2020-09-07","arxiv_id":"2009.03300","repositories_listed":18,"syntology":{"n":26,"n_ran":5,"n_unverified":21,"n_pointer_only":1}},{"url":"/paper/retrieval-augmented-generation-for-knowledge","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","date":"2020-05-22","arxiv_id":"2005.11401","repositories_listed":18,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/mistral-7b","title":"Mistral 7B","date":"2023-10-10","arxiv_id":"2310.06825","repositories_listed":6,"syntology":{"n":11,"n_ran":9,"n_unverified":2,"n_pointer_only":1}},{"url":"/paper/realm-retrieval-augmented-language-model-pre","title":"REALM: Retrieval-Augmented Language Model Pre-Training","date":"2020-02-10","arxiv_id":"2002.08909","repositories_listed":6,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/imagine-this-scripts-to-compositions-to","title":"Imagine This! Scripts to Compositions to Videos","date":"2018-04-10","arxiv_id":"1804.03608","repositories_listed":5,"syntology":null},{"url":"/paper/scaling-synthetic-data-creation-with","title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","date":"2024-06-28","arxiv_id":"2406.20094","repositories_listed":4,"syntology":{"n":4,"n_ran":1,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/meim-multi-partition-embedding-interaction","title":"MEIM: Multi-partition Embedding Interaction Beyond Block Term Format for Efficient and Expressive Link Prediction","date":"2022-09-30","arxiv_id":"2209.15597","repositories_listed":4,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":7}},{"url":"/paper/commonsenseqa-a-question-answering-challenge","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","date":"2018-11-02","arxiv_id":"1811.00937","repositories_listed":4,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/vila-on-pre-training-for-visual-language","title":"VILA: On Pre-training for Visual Language Models","date":"2023-12-12","arxiv_id":"2312.07533","repositories_listed":3,"syntology":null},{"url":"/paper/dense-x-retrieval-what-retrieval-granularity","title":"Dense X Retrieval: What Retrieval Granularity Should We Use?","date":"2023-12-11","arxiv_id":"2312.06648","repositories_listed":3,"syntology":null},{"url":"/paper/symbol-llm-towards-foundational-symbol","title":"Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models","date":"2023-11-15","arxiv_id":"2311.09278","repositories_listed":3,"syntology":null},{"url":"/paper/aligning-ai-with-shared-human-values","title":"Aligning AI With Shared Human Values","date":"2020-08-05","arxiv_id":"2008.02275","repositories_listed":3,"syntology":{"n":7,"n_ran":1,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/aser-a-large-scale-eventuality-knowledge","title":"ASER: A Large-scale Eventuality Knowledge Graph","date":"2019-05-01","arxiv_id":"1905.00270","repositories_listed":3,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/wise-a-world-knowledge-informed-semantic","title":"WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation","date":"2025-03-10","arxiv_id":"2503.07265","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":5}},{"url":"/paper/bottlehumor-self-informed-humor-explanation","title":"BottleHumor: Self-Informed Humor Explanation using the Information Bottleneck Principle","date":"2025-02-22","arxiv_id":"2502.18331","repositories_listed":2,"syntology":null},{"url":"/paper/seallms-3-open-foundation-and-chat","title":"SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian Languages","date":"2024-07-29","arxiv_id":"2407.19672","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/visa-reasoning-video-object-segmentation-via","title":"VISA: Reasoning Video Object Segmentation via Large Language Models","date":"2024-07-16","arxiv_id":"2407.11325","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/a-synthetic-dataset-for-personal-attribute","title":"A Synthetic Dataset for Personal Attribute Inference","date":"2024-06-11","arxiv_id":"2406.07217","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/elements-of-world-knowledge-ewok-a-cognition","title":"Elements of World Knowledge (EWOK): A cognition-inspired framework for evaluating basic world knowledge in language models","date":"2024-05-15","arxiv_id":"2405.09605","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/mygo-discrete-modality-information-as-fine","title":"Tokenization, Fusion, and Augmentation: Towards Fine-grained Multi-modal Entity Representation","date":"2024-04-15","arxiv_id":"2404.09468","repositories_listed":2,"syntology":null},{"url":"/paper/can-llms-tuning-methods-work-in-medical","title":"Can LLMs' Tuning Methods Work in Medical Multimodal Domain?","date":"2024-03-11","arxiv_id":"2403.06407","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":7}},{"url":"/paper/grillbot-in-practice-lessons-and-tradeoffs","title":"GRILLBot In Practice: Lessons and Tradeoffs Deploying Large Language Models for Adaptable Conversational Task Assistants","date":"2024-02-12","arxiv_id":"2402.07647","repositories_listed":2,"syntology":null},{"url":"/paper/bring-your-own-kg-self-supervised-program","title":"Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQA","date":"2023-11-14","arxiv_id":"2311.07850","repositories_listed":2,"syntology":null},{"url":"/paper/freshllms-refreshing-large-language-models","title":"FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation","date":"2023-10-05","arxiv_id":"2310.03214","repositories_listed":2,"syntology":null},{"url":"/paper/topical-chat-towards-knowledge-grounded-open-1","title":"Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations","date":"2023-08-23","arxiv_id":"2308.11995","repositories_listed":2,"syntology":null},{"url":"/paper/expel-llm-agents-are-experiential-learners","title":"ExpeL: LLM Agents Are Experiential Learners","date":"2023-08-20","arxiv_id":"2308.10144","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/lisa-reasoning-segmentation-via-large","title":"LISA: Reasoning Segmentation via Large Language Model","date":"2023-08-01","arxiv_id":"2308.00692","repositories_listed":2,"syntology":null},{"url":"/paper/pk-chat-pointer-network-guided-knowledge","title":"PK-Chat: Pointer Network Guided Knowledge Driven Generative Dialogue Model","date":"2023-04-02","arxiv_id":"2304.00592","repositories_listed":2,"syntology":null},{"url":"/paper/scaling-autoregressive-models-for-content","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","date":"2022-06-22","arxiv_id":"2206.10789","repositories_listed":2,"syntology":{"n":9,"n_ran":3,"n_unverified":6,"n_pointer_only":3}}],"syntology_records":18,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}