{"url":"/task/strategyqa","name":"StrategyQA","slug":"strategyqa","description_markdown":"StrategyQA aims to measure the ability of models to answer questions that require multi-step implicit reasoning.\r\n\r\nSource: [BIG-bench](https://github.com/google/BIG-bench/tree/main/bigbench/benchmark_tasks/strategyqa)","categories":[{"name":"Methodology","url":"/area/methodology"},{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":40,"papers_with_code":20,"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":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/logical-reasoning","name":"Logical Reasoning"}],"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":20,"of":20,"tagged_in_all":40,"items":[{"url":"/paper/palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","arxiv_id":"2204.02311","repositories_listed":7,"syntology":{"n":37,"n_ran":30,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/mutual-reasoning-makes-smaller-llms-stronger","title":"Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers","date":"2024-08-12","arxiv_id":"2408.06195","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/a-prefrontal-cortex-inspired-architecture-for","title":"Improving Planning with Large Language Models: A Modular Agentic Architecture","date":"2023-09-30","arxiv_id":"2310.00194","repositories_listed":3,"syntology":null},{"url":"/paper/self-consistency-improves-chain-of-thought","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","date":"2022-03-21","arxiv_id":"2203.11171","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"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/delta-a-decoding-strategy-based-on-logit","title":"DeLTa: A Decoding Strategy based on Logit Trajectory Prediction Improves Factuality and Reasoning Ability","date":"2025-03-04","arxiv_id":"2503.02343","repositories_listed":1,"syntology":null},{"url":"/paper/voting-or-consensus-decision-making-in-multi","title":"Voting or Consensus? Decision-Making in Multi-Agent Debate","date":"2025-02-26","arxiv_id":"2502.19130","repositories_listed":1,"syntology":null},{"url":"/paper/autoreason-automatic-few-shot-reasoning","title":"AutoReason: Automatic Few-Shot Reasoning Decomposition","date":"2024-12-09","arxiv_id":"2412.06975","repositories_listed":1,"syntology":null},{"url":"/paper/rationale-aware-answer-verification-by","title":"Rationale-Aware Answer Verification by Pairwise Self-Evaluation","date":"2024-10-07","arxiv_id":"2410.04838","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/unchosen-experts-can-contribute-too","title":"Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-Contrast","date":"2024-05-23","arxiv_id":"2405.14507","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/cr-lt-kgqa-a-knowledge-graph-question","title":"CR-LT-KGQA: A Knowledge Graph Question Answering Dataset Requiring Commonsense Reasoning and Long-Tail Knowledge","date":"2024-03-03","arxiv_id":"2403.01395","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/distillation-contrastive-decoding-improving","title":"Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation","date":"2024-02-21","arxiv_id":"2402.14874","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_unverified":4,"n_pointer_only":10}},{"url":"/paper/escape-sky-high-cost-early-stopping-self","title":"Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning","date":"2024-01-19","arxiv_id":"2401.10480","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":8}},{"url":"/paper/tailoring-self-rationalizers-with-multi","title":"Tailoring Self-Rationalizers with Multi-Reward Distillation","date":"2023-11-06","arxiv_id":"2311.02805","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_unverified":4,"n_pointer_only":10}},{"url":"/paper/teaching-smaller-language-models-to","title":"Teaching Smaller Language Models To Generalise To Unseen Compositional Questions","date":"2023-08-02","arxiv_id":"2308.00946","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-augmented-reasoning-distillation-1","title":"Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks","date":"2023-05-28","arxiv_id":"2305.18395","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/visconde-multi-document-qa-with-gpt-3-and","title":"Visconde: Multi-document QA with GPT-3 and Neural Reranking","date":"2022-12-19","arxiv_id":"2212.09656","repositories_listed":1,"syntology":null},{"url":"/paper/distilling-multi-step-reasoning-capabilities","title":"Distilling Reasoning Capabilities into Smaller Language Models","date":"2022-12-01","arxiv_id":"2212.00193","repositories_listed":1,"syntology":null},{"url":"/paper/did-aristotle-use-a-laptop-a-question","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","date":"2021-01-06","arxiv_id":"2101.02235","repositories_listed":1,"syntology":null}],"syntology_records":11,"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"}}