{"url":"/task/question-selection","name":"Question Selection","slug":"question-selection","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":31,"papers_with_code":18,"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":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/question-selection-on-big-bench","slug":"question-selection-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}],"subtasks":[],"parent_tasks":[{"url":"/task/reading-comprehension","name":"Reading Comprehension"}],"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":18,"of":18,"tagged_in_all":31,"items":[{"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/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/bobcat-bilevel-optimization-based","title":"BOBCAT: Bilevel Optimization-Based Computerized Adaptive Testing","date":"2021-08-17","arxiv_id":"2108.07386","repositories_listed":2,"syntology":{"n":10,"n_ran":10,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/asking-clarifying-questions-in-open-domain","title":"Asking Clarifying Questions in Open-Domain Information-Seeking Conversations","date":"2019-07-15","arxiv_id":"1907.06554","repositories_listed":2,"syntology":null},{"url":"/paper/autojudger-an-agent-driven-framework-for","title":"AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs","date":"2025-05-27","arxiv_id":"2505.21389","repositories_listed":1,"syntology":null},{"url":"/paper/qa-prompting-improving-summarization-with","title":"QA-prompting: Improving Summarization with Large Language Models using Question-Answering","date":"2025-05-20","arxiv_id":"2505.14347","repositories_listed":1,"syntology":null},{"url":"/paper/decentralized-arena-towards-democratic-and","title":"Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models","date":"2025-05-19","arxiv_id":"2505.12808","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-political-surveys-and-gpt-4-tackling","title":"Adaptive political surveys and GPT-4: Tackling the cold start problem with simulated user interactions","date":"2025-03-12","arxiv_id":"2503.09311","repositories_listed":1,"syntology":null},{"url":"/paper/pscon-toward-conversational-product-search","title":"PSCon: Product Search Through Conversations","date":"2025-02-19","arxiv_id":"2502.13881","repositories_listed":1,"syntology":null},{"url":"/paper/active-task-disambiguation-with-llms","title":"Active Task Disambiguation with LLMs","date":"2025-02-06","arxiv_id":"2502.04485","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-inspired-cold-start-with-sufficient","title":"Diffusion-Inspired Cold Start with Sufficient Prior in Computerized Adaptive Testing","date":"2024-11-19","arxiv_id":"2411.12182","repositories_listed":1,"syntology":null},{"url":"/paper/fast-and-adaptive-questionnaires-for-voting","title":"Fast and Adaptive Questionnaires for Voting Advice Applications","date":"2024-04-02","arxiv_id":"2404.01872","repositories_listed":1,"syntology":null},{"url":"/paper/survey-of-computerized-adaptive-testing-a","title":"Survey of Computerized Adaptive Testing: A Machine Learning Perspective","date":"2024-03-31","arxiv_id":"2404.00712","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/balancing-test-accuracy-and-security-in","title":"Balancing Test Accuracy and Security in Computerized Adaptive Testing","date":"2023-05-18","arxiv_id":"2305.18312","repositories_listed":1,"syntology":null},{"url":"/paper/what-makes-a-question-inquisitive-a-study-on-1","title":"“What makes a question inquisitive?” A Study on Type-Controlled Inquisitive Question Generation","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/comqa-compositional-question-answering-via","title":"ComQA:Compositional Question Answering via Hierarchical Graph Neural Networks","date":"2021-01-16","arxiv_id":"2101.06400","repositories_listed":1,"syntology":null},{"url":"/paper/crowdsourced-collective-entity-resolution","title":"Crowdsourced Collective Entity Resolution with Relational Match Propagation","date":"2020-02-21","arxiv_id":"2002.09361","repositories_listed":1,"syntology":null},{"url":"/paper/modelling-sentence-pairs-with-tree-structured","title":"Modelling Sentence Pairs with Tree-structured Attentive Encoder","date":"2016-10-10","arxiv_id":"1610.02806","repositories_listed":1,"syntology":null}],"syntology_records":3,"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"}}