Asking LLMs to Verify First is Almost Free Lunch

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Shiguang, Yao, Quanming
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911709676961792
author Wu, Shiguang
Yao, Quanming
author_facet Wu, Shiguang
Yao, Quanming
contents 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 complementary to standard forward Chain-of-Thought (CoT), which restricts the logical search space of the answer by pruning the LLM's output distribution. We further generalize VF prompting 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 and various LLMs confirm that VF prompting with random answer consistently outperforms standard CoT with minimal computational overhead, and Iter-VF outperforms existing TTS strategies. VF is also effective on SOTA thinking models. For example, by using the simple VF prompting, we obtain a new SOTA 94.9% accuracy on GPQA-Diamond with Gemini-3-Pro-Preview where VF reduces its errors by ~30% relatively.
format Preprint
id arxiv_https___arxiv_org_abs_2511_21734
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Asking LLMs to Verify First is Almost Free Lunch
Wu, Shiguang
Yao, Quanming
Computation and Language
Artificial Intelligence
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 complementary to standard forward Chain-of-Thought (CoT), which restricts the logical search space of the answer by pruning the LLM's output distribution. We further generalize VF prompting 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 and various LLMs confirm that VF prompting with random answer consistently outperforms standard CoT with minimal computational overhead, and Iter-VF outperforms existing TTS strategies. VF is also effective on SOTA thinking models. For example, by using the simple VF prompting, we obtain a new SOTA 94.9% accuracy on GPQA-Diamond with Gemini-3-Pro-Preview where VF reduces its errors by ~30% relatively.
title Asking LLMs to Verify First is Almost Free Lunch
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2511.21734