Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification
Abstract
A formal logic verification-guided framework dynamically interleaves symbolic verification with natural language generation to improve reasoning accuracy and reduce errors in large language models.
Large Language Models (LLMs) show remarkable capabilities, yet their stochastic next-token prediction creates logical inconsistencies and reward hacking that formal symbolic systems avoid. To bridge this gap, we introduce a formal logic verification-guided framework that dynamically interleaves formal symbolic verification with the natural language generation process, providing real-time feedback to detect and rectify errors as they occur. Distinguished from previous neuro-symbolic methods limited by passive post-hoc validation, our approach actively penalizes intermediate fallacies during the reasoning chain. We operationalize this framework via a novel two-stage training pipeline that synergizes formal logic verification-guided supervised fine-tuning and policy optimization. Extensive evaluation on six benchmarks spanning mathematical, logical, and general reasoning demonstrates that our 7B and 14B models outperform state-of-the-art baselines by average margins of 10.4% and 14.2%, respectively. These results validate that formal verification can serve as a scalable mechanism to significantly push the performance boundaries of advanced LLM reasoning.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision (2025)
- Structured Reasoning for Large Language Models (2026)
- Milestones over Outcome: Unlocking Geometric Reasoning with Sub-Goal Verifiable Reward (2026)
- P2S: Probabilistic Process Supervision for General-Domain Reasoning Question Answering (2026)
- VERGE: Formal Refinement and Guidance Engine for Verifiable LLM Reasoning (2026)
- LRAS: Advanced Legal Reasoning with Agentic Search (2026)
- ConMax: Confidence-Maximizing Compression for Efficient Chain-of-Thought Reasoning (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 2
Datasets citing this paper 2
Spaces citing this paper 0
No Space linking this paper
