{"url":"/task/general-knowledge","name":"General Knowledge","slug":"general-knowledge","description_markdown":"This task aims to evaluate the ability of a model to answer general-knowledge questions.\r\n\r\nSource: [BIG-bench](https://github.com/google/BIG-bench/tree/main/bigbench/benchmark_tasks/general_knowledge)","categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":399,"papers_with_code":173,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":7,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/general-knowledge-on-big-bench","slug":"general-knowledge-on-big-bench","dataset":"BIG-bench","dataset_url":"/dataset/big-bench","rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Chinchilla-70B (few-shot, k=5)","paper_title":"Training Compute-Optimal Large Language Models","paper_url":"/paper/training-compute-optimal-large-language","paper_date":"2022-03-29","arxiv_id":"2203.15556","code_links":[{"title":"karpathy/llama2.c","url":"https://github.com/karpathy/llama2.c"},{"title":"nkluge-correa/teenytinyllama","url":"https://github.com/nkluge-correa/teenytinyllama"}],"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":4}}}],"datasets":[{"url":"/dataset/big-bench","name":"BIG-bench","full_name":"Beyond the Imitation Game Benchmark","num_papers_in_archive":349},{"url":"/dataset/bear-big","name":"BEAR-probe","full_name":"Benchmark for Evaluating Associative Reasoning","num_papers_in_archive":1}],"subtasks":[{"url":"/task/global-facts","name":"Global Facts"},{"url":"/task/miscellaneous","name":"Miscellaneous"},{"url":"/task/movie-recommendation","name":"Movie Recommendation"},{"url":"/task/natural-questions","name":"Natural Questions"},{"url":"/task/similarities-abstraction","name":"Similarities Abstraction"},{"url":"/task/sports-understanding","name":"Sports Understanding"},{"url":"/task/triviaqa","name":"TriviaQA"}],"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":173,"tagged_in_all":399,"items":[{"url":"/paper/joey-nmt-a-minimalist-nmt-toolkit-for-novices","title":"Joey NMT: A Minimalist NMT Toolkit for Novices","date":"2019-07-29","arxiv_id":"1907.12484","repositories_listed":8,"syntology":{"n":17,"n_ran":3,"n_unverified":14,"n_pointer_only":1}},{"url":"/paper/conceptnet-55-an-open-multilingual-graph-of","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","date":"2016-12-12","arxiv_id":"1612.03975","repositories_listed":6,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/automated-phrase-mining-from-massive-text","title":"Automated Phrase Mining from Massive Text Corpora","date":"2017-02-15","arxiv_id":"1702.04457","repositories_listed":4,"syntology":null},{"url":"/paper/time-travelling-pixels-bitemporal-features","title":"Time Travelling Pixels: Bitemporal Features Integration with Foundation Model for Remote Sensing Image Change Detection","date":"2023-12-23","arxiv_id":"2312.16202","repositories_listed":3,"syntology":null},{"url":"/paper/explanations-as-features-llm-based-features","title":"Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning","date":"2023-05-31","arxiv_id":"2305.19523","repositories_listed":3,"syntology":{"n":7,"n_ran":4,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","arxiv_id":"2112.11446","repositories_listed":3,"syntology":null},{"url":"/paper/learning-to-understand-phrases-by-embedding","title":"Learning to Understand Phrases by Embedding the Dictionary","date":"2015-04-02","arxiv_id":"1504.00548","repositories_listed":3,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/survey-on-abstractive-text-summarization","title":"Survey on Abstractive Text Summarization: Dataset, Models, and Metrics","date":"2024-12-22","arxiv_id":"2412.17165","repositories_listed":2,"syntology":null},{"url":"/paper/a-comparison-of-prompt-engineering-techniques","title":"A Comparison of Prompt Engineering Techniques for Task Planning and Execution in Service Robotics","date":"2024-10-30","arxiv_id":"2410.22997","repositories_listed":2,"syntology":null},{"url":"/paper/cascade-prompt-learning-for-vision-language","title":"Cascade Prompt Learning for Vision-Language Model Adaptation","date":"2024-09-26","arxiv_id":"2409.17805","repositories_listed":2,"syntology":null},{"url":"/paper/f-lmm-grounding-frozen-large-multimodal","title":"F-LMM: Grounding Frozen Large Multimodal Models","date":"2024-06-09","arxiv_id":"2406.05821","repositories_listed":2,"syntology":null},{"url":"/paper/domainrag-a-chinese-benchmark-for-evaluating","title":"DomainRAG: A Chinese Benchmark for Evaluating Domain-specific Retrieval-Augmented Generation","date":"2024-06-09","arxiv_id":"2406.05654","repositories_listed":2,"syntology":{"n":12,"n_ran":12,"n_unverified":0,"n_pointer_only":12}},{"url":"/paper/a-new-learning-paradigm-for-foundation-model","title":"A New Learning Paradigm for Foundation Model-based Remote Sensing Change Detection","date":"2023-12-02","arxiv_id":"2312.01163","repositories_listed":2,"syntology":null},{"url":"/paper/exploring-the-potential-of-large-language-1","title":"Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs","date":"2023-07-07","arxiv_id":"2307.03393","repositories_listed":2,"syntology":null},{"url":"/paper/bert4cmr-cross-market-recommendation-with","title":"Bert4XMR: Cross-Market Recommendation with Bidirectional Encoder Representations from Transformer","date":"2023-05-24","arxiv_id":"2305.15145","repositories_listed":2,"syntology":null},{"url":"/paper/continual-learning-of-language-models","title":"Continual Pre-training of Language Models","date":"2023-02-07","arxiv_id":"2302.03241","repositories_listed":2,"syntology":null},{"url":"/paper/adapting-a-language-model-while-preserving","title":"Adapting a Language Model While Preserving its General Knowledge","date":"2023-01-21","arxiv_id":"2301.08986","repositories_listed":2,"syntology":null},{"url":"/paper/knowledge-distillation-for-detection","title":"Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling","date":"2022-11-15","arxiv_id":"2211.08071","repositories_listed":2,"syntology":null},{"url":"/paper/cc-riddle-a-question-answering-dataset-of","title":"CC-Riddle: A Question Answering Dataset of Chinese Character Riddles","date":"2022-06-28","arxiv_id":"2206.13778","repositories_listed":2,"syntology":null},{"url":"/paper/training-compute-optimal-large-language","title":"Training Compute-Optimal Large Language Models","date":"2022-03-29","arxiv_id":"2203.15556","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":4}},{"url":"/paper/beametrics-a-benchmark-for-language","title":"BEAMetrics: A Benchmark for Language Generation Evaluation Evaluation","date":"2021-10-18","arxiv_id":"2110.09147","repositories_listed":2,"syntology":null},{"url":"/paper/exploiting-adapters-for-cross-lingual-low","title":"Exploiting Adapters for Cross-lingual Low-resource Speech Recognition","date":"2021-05-18","arxiv_id":"2105.11905","repositories_listed":2,"syntology":null},{"url":"/paper/transformers-as-soft-reasoners-over-language","title":"Transformers as Soft Reasoners over Language","date":"2020-02-14","arxiv_id":"2002.05867","repositories_listed":2,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/what-does-my-qa-model-know-devising","title":"What Does My QA Model Know? Devising Controlled Probes using Expert Knowledge","date":"2019-12-31","arxiv_id":"1912.13337","repositories_listed":2,"syntology":null},{"url":"/paper/go-from-the-general-to-the-particular-multi","title":"Go From the General to the Particular: Multi-Domain Translation with Domain Transformation Networks","date":"2019-11-22","arxiv_id":"1911.09912","repositories_listed":2,"syntology":null},{"url":"/paper/integrating-semantic-knowledge-to-tackle-zero","title":"Integrating Semantic Knowledge to Tackle Zero-shot Text Classification","date":"2019-03-29","arxiv_id":"1903.12626","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/yuanfudao-at-semeval-2018-task-11-three-way","title":"Yuanfudao at SemEval-2018 Task 11: Three-way Attention and Relational Knowledge for Commonsense Machine Comprehension","date":"2018-03-01","arxiv_id":"1803.00191","repositories_listed":2,"syntology":null},{"url":"/paper/conceptnet-at-semeval-2017-task-2-extending","title":"ConceptNet at SemEval-2017 Task 2: Extending Word Embeddings with Multilingual Relational Knowledge","date":"2017-04-11","arxiv_id":"1704.03560","repositories_listed":2,"syntology":null},{"url":"/paper/unveiling-causal-reasoning-in-large-language","title":"Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?","date":"2025-06-26","arxiv_id":"2506.21215","repositories_listed":1,"syntology":{"n":12,"n_ran":3,"n_unverified":9,"n_pointer_only":12}},{"url":"/paper/taxoadapt-aligning-llm-based-multidimensional","title":"TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora","date":"2025-06-12","arxiv_id":"2506.10737","repositories_listed":1,"syntology":null}],"syntology_records":9,"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"}}