{"url":"/task/multiple-choice","name":"Multiple-choice","slug":"multiple-choice","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":1107,"papers_with_code":483,"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":12,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/truthfulqa","name":"TruthfulQA","full_name":"","num_papers_in_archive":607},{"url":"/dataset/mathvista","name":"MathVista","full_name":"Mathematical Reasoning of in Visual Contexts","num_papers_in_archive":242},{"url":"/dataset/belebele","name":"Belebele","full_name":"","num_papers_in_archive":68},{"url":"/dataset/math-v","name":"MATH-V","full_name":"","num_papers_in_archive":12},{"url":"/dataset/neptune","name":"Neptune","full_name":"Neptune Long Video Understanding Benchmark","num_papers_in_archive":12},{"url":"/dataset/mindgames","name":"Mindgames","full_name":"","num_papers_in_archive":4},{"url":"/dataset/tasksource","name":"Tasksource","full_name":"","num_papers_in_archive":3},{"url":"/dataset/mminstruct-gpt4v","name":"MMInstruct-GPT4V","full_name":"MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity","num_papers_in_archive":1},{"url":"/dataset/ollabench-v-0-2","name":"OllaBench v.0.2","full_name":"OllaBench for Interdependent Cybersecurity v.0.2","num_papers_in_archive":1},{"url":"/dataset/probability-words-nli","name":"Probability words NLI","full_name":"Natural language inference with words estimative of probability (WEP)","num_papers_in_archive":1},{"url":"/dataset/tumtraffic-videoqa","name":"TUMTraffic-VideoQA","full_name":"","num_papers_in_archive":1},{"url":"/dataset/worldcuisines","name":"WorldCuisines","full_name":"","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":483,"tagged_in_all":1107,"items":[{"url":"/paper/vqa-visual-question-answering","title":"VQA: Visual Question Answering","date":"2015-05-03","arxiv_id":"1505.00468","repositories_listed":21,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":6}},{"url":"/paper/blip-2-bootstrapping-language-image-pre","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","date":"2023-01-30","arxiv_id":"2301.12597","repositories_listed":17,"syntology":{"n":8,"n_ran":4,"n_unverified":4,"n_pointer_only":1}},{"url":"/paper/video-llava-learning-united-visual-1","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","date":"2023-11-16","arxiv_id":"2311.10122","repositories_listed":6,"syntology":{"n":7,"n_ran":4,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/gpt-takes-the-bar-exam","title":"GPT Takes the Bar Exam","date":"2022-12-29","arxiv_id":"2212.14402","repositories_listed":5,"syntology":null},{"url":"/paper/flamingo-a-visual-language-model-for-few-shot-1","title":"Flamingo: a Visual Language Model for Few-Shot Learning","date":"2022-04-29","arxiv_id":"2204.14198","repositories_listed":5,"syntology":{"n":24,"n_ran":18,"n_unverified":6,"n_pointer_only":7}},{"url":"/paper/automating-turkish-educational-quiz","title":"Automating Turkish Educational Quiz Generation Using Large Language Models","date":"2024-06-05","arxiv_id":"2406.03397","repositories_listed":4,"syntology":null},{"url":"/paper/tinybenchmarks-evaluating-llms-with-fewer","title":"tinyBenchmarks: evaluating LLMs with fewer examples","date":"2024-02-22","arxiv_id":"2402.14992","repositories_listed":4,"syntology":{"n":39,"n_ran":10,"n_unverified":29,"n_pointer_only":17}},{"url":"/paper/steering-llama-2-via-contrastive-activation","title":"Steering Llama 2 via Contrastive Activation Addition","date":"2023-12-09","arxiv_id":"2312.06681","repositories_listed":4,"syntology":{"n":22,"n_ran":14,"n_unverified":8,"n_pointer_only":9}},{"url":"/paper/case-commonsense-augmented-score-with-an","title":"CASE: Commonsense-Augmented Score with an Expanded Answer Space","date":"2023-11-03","arxiv_id":"2311.01684","repositories_listed":4,"syntology":null},{"url":"/paper/from-recognition-to-cognition-visual","title":"From Recognition to Cognition: Visual Commonsense Reasoning","date":"2018-11-27","arxiv_id":"1811.10830","repositories_listed":4,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"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/mapeval-a-map-based-evaluation-of-geo-spatial","title":"MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models","date":"2024-12-31","arxiv_id":"2501.00316","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/videollama-2-advancing-spatial-temporal","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","date":"2024-06-11","arxiv_id":"2406.07476","repositories_listed":3,"syntology":{"n":17,"n_ran":7,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/mvbench-a-comprehensive-multi-modal-video","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","date":"2023-11-28","arxiv_id":"2311.17005","repositories_listed":3,"syntology":{"n":10,"n_ran":7,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/gpqa-a-graduate-level-google-proof-q-a","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","date":"2023-11-20","arxiv_id":"2311.12022","repositories_listed":3,"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/seed-bench-benchmarking-multimodal-llms-with","title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","date":"2023-07-30","arxiv_id":"2307.16125","repositories_listed":3,"syntology":null},{"url":"/paper/mmbench-is-your-multi-modal-model-an-all","title":"MMBench: Is Your Multi-modal Model an All-around Player?","date":"2023-07-12","arxiv_id":"2307.06281","repositories_listed":3,"syntology":null},{"url":"/paper/fine-tuning-language-models-with-just-forward-1","title":"Fine-Tuning Language Models with Just Forward Passes","date":"2023-05-27","arxiv_id":"2305.17333","repositories_listed":3,"syntology":{"n":17,"n_ran":9,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/quality-question-answering-with-long-input","title":"QuALITY: Question Answering with Long Input Texts, Yes!","date":"2021-12-16","arxiv_id":"2112.08608","repositories_listed":3,"syntology":null},{"url":"/paper/what-disease-does-this-patient-have-a-large","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","date":"2020-09-28","arxiv_id":"2009.13081","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/learning-to-attend-on-essential-terms-an","title":"Learning to Attend On Essential Terms: An Enhanced Retriever-Reader Model for Open-domain Question Answering","date":"2018-08-28","arxiv_id":"1808.09492","repositories_listed":3,"syntology":null},{"url":"/paper/revisiting-visual-question-answering","title":"Revisiting Visual Question Answering Baselines","date":"2016-06-27","arxiv_id":"1606.08390","repositories_listed":3,"syntology":null},{"url":"/paper/videoeval-pro-robust-and-realistic-long-video","title":"VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation","date":"2025-05-20","arxiv_id":"2505.14640","repositories_listed":2,"syntology":{"n":14,"n_ran":5,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/2503-00096","title":"BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology","date":"2025-02-28","arxiv_id":"2503.00096","repositories_listed":2,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/vidcomposition-can-mllms-analyze-compositions","title":"VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?","date":"2024-11-17","arxiv_id":"2411.10979","repositories_listed":2,"syntology":null},{"url":"/paper/llava-onevision-easy-visual-task-transfer","title":"LLaVA-OneVision: Easy Visual Task Transfer","date":"2024-08-06","arxiv_id":"2408.03326","repositories_listed":2,"syntology":null},{"url":"/paper/2408-01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","date":"2024-08-03","arxiv_id":"2408.01800","repositories_listed":2,"syntology":{"n":14,"n_ran":9,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/2408-01337","title":"MuChoMusic: Evaluating Music Understanding in Multimodal Audio-Language Models","date":"2024-08-02","arxiv_id":"2408.01337","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/uncertainty-is-fragile-manipulating","title":"Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models","date":"2024-07-15","arxiv_id":"2407.11282","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":4}},{"url":"/paper/intentionqa-a-benchmark-for-evaluating","title":"IntentionQA: A Benchmark for Evaluating Purchase Intention Comprehension Abilities of Language Models in E-commerce","date":"2024-06-14","arxiv_id":"2406.10173","repositories_listed":2,"syntology":null}],"syntology_records":19,"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"}}