REVIEW 5 cited by
Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
A key limitation in current datasets for multi-hop reasoning is that the required steps for answering the question are mentioned in it explicitly. In this work, we introduce StrategyQA, a question answering (QA) benchmark where the required reasoning steps are implicit in the question, and should be inferred using a strategy. A fundamental challenge in this setup is how to elicit such creative questions from crowdsourcing workers, while covering a broad range of potential strategies. We propose a data collection procedure that combines term-based priming to inspire annotators, careful control over the annotator population, and adversarial filtering for eliminating reasoning shortcuts. Moreover, we annotate each question with (1) a decomposition into reasoning steps for answering it, and (2) Wikipedia paragraphs that contain the answers to each step. Overall, StrategyQA includes 2,780 examples, each consisting of a strategy question, its decomposition, and evidence paragraphs. Analysis shows that questions in StrategyQA are short, topic-diverse, and cover a wide range of strategies. Empirically, we show that humans perform well (87%) on this task, while our best baseline reaches an accuracy of $\sim$66%.
Forward citations
Cited by 5 Pith papers
-
Efficient Reasoning on the Edge
LoRA adapters, budget-forced GRPO, dynamic switching, parallel verification and FPTQuant enable practical chain-of-thought reasoning on quantized Qwen2.5-7B for edge devices.
-
Multilingual Test-Time Scaling via Initial Thought Transfer
MITT, a prefix-tuning method for multilingual test-time scaling, is evaluated on questions whose English reasoning was used for training, confounding the reported gains.
-
Error Reflection Prompting: Can Large Language Models Successfully Understand Errors?
Error Reflection Prompting, a chain-of-thought variant that includes an incorrect answer and error recognition, is claimed to improve LLM reasoning performance and interpretability.
-
Mixture of Reasonings: Teach Large Language Models to Reason with Adaptive Strategies
MoR fine-tunes Qwen2.5 on GPT-4o-selected reasoning templates, claiming up to 13.5% accuracy gains, but the reported gains are not robustly supported.
-
Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey
A comprehensive review that categorizes methods for shortening and adaptively triggering chain-of-thought reasoning in large language models.
Discussion (0). Sign in to comment.