{"url":"/dataset/situation-puzzle","name":"Situation Puzzle","full_name":null,"description_markdown":"LLMs' lateral thinking capabilities remain under-explored and challenging to measure due to the complexity of assessing creative thought processes and the scarcity of relevant data. To address these challenges, we introduce **SPLAT**, a benchmark leveraging **S**ituation **P**uzzles to evaluate and elicit **LA**teral **T**hinking of LLMs. This benchmark, containing 975 graded situation puzzles across three difficulty levels.","description_withheld":null,"homepage":"https://github.com/chenqi008/LateralThinking","introduced_date":"2024-10-09","introduced_date_note":null,"introduced_by":{"paper":"/paper/weak-eval-strong-evaluating-and-eliciting","title":"Weak-eval-Strong: Evaluating and Eliciting Lateral Thinking of LLMs with Situation Puzzles","first_author":"Qi Chen","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Common Sense Reasoning","url":"/task/common-sense-reasoning","datasets_with_task":"/datasets/task/common-sense-reasoning"},{"name":"Riddle Sense","url":"/task/riddle-sense","datasets_with_task":"/datasets/task/riddle-sense"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Situation Puzzle"],"data_loaders":[{"repo":"https://github.com/chenqi008/LateralThinking","url":"https://github.com/chenqi008/LateralThinking","frameworks":["pytorch"]}],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}