SOTAVerified

StrategyQA

StrategyQA aims to measure the ability of models to answer questions that require multi-step implicit reasoning.

Source: BIG-bench

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 40 papers

TitleStatusHype
Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive TasksCode1
Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-ContrastCode1
Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning StrategiesCode1
Visconde: Multi-document QA with GPT-3 and Neural RerankingCode1
Voting or Consensus? Decision-Making in Multi-Agent DebateCode0
Distilling Reasoning Capabilities into Smaller Language ModelsCode0
Rationale-Aware Answer Verification by Pairwise Self-EvaluationCode0
DeLTa: A Decoding Strategy based on Logit Trajectory Prediction Improves Factuality and Reasoning AbilityCode0
Tailoring Self-Rationalizers with Multi-Reward DistillationCode0
Teaching Smaller Language Models To Generalise To Unseen Compositional QuestionsCode0
Show:102550
← PrevPage 2 of 4Next →

No leaderboard results yet.