Asking LLMs to Verify First is Almost Free Lunch
Shiguang Wu, Quanming Yao

TL;DR
The paper introduces Verification-First (VF), a cost-effective prompting strategy for LLMs that improves reasoning accuracy by verifying answers before solution generation, outperforming traditional methods across multiple tasks.
Contribution
It proposes VF and Iter-VF strategies that leverage reverse reasoning to enhance LLM reasoning without significant additional costs.
Findings
VF with random answers outperforms standard CoT
Iter-VF surpasses existing test-time scaling methods
Method is effective across diverse benchmarks and models
Abstract
To enhance the reasoning capabilities of Large Language Models (LLMs) without high costs of training, nor extensive test-time sampling, we introduce Verification-First (VF), a strategy that prompts models to verify a provided candidate answer, even a trivial or random one, before generating a solution. This approach triggers a "reverse reasoning" process that is cognitively easier and complementary to standard forward Chain-of-Thought (CoT), effectively invoking the model's critical thinking to reduce logical errors. We further generalize the VF strategy to Iter-VF, a sequential test-time scaling (TTS) method that iteratively cycles the verification-generation process using the model's previous answer. Extensive experiments across various benchmarks (from mathematical reasoning to coding and agentic tasks) and various LLMs (from open-source 1B to cutting-edge commercial ones) confirm…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Multimodal Machine Learning Applications · Natural Language Processing Techniques
