VERGE: Formal Refinement and Guidance Engine for Verifiable LLM Reasoning
cs.CL, cs.AI
Submitted: 2026-01-27
Updated: 2026-10-11
Terminology
Sources
- Program Synthesis with Large Language Models
- ProofNet: Autoformalizing and Formally Proving Undergraduate-Level Mathematics
- VERUS-LM: a Versatile Framework for Combining LLMs with Symbolic Reasoning
- Evaluating Large Language Models Trained on Code
- Improving Factuality and Reasoning in Language Models through Multiagent Debate
- VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical Consistency Checks
- Trust The Typical
- Large Language Models Cannot Self-Correct Reasoning Yet
- Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs
- Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate
- Let's Verify Step by Step
- ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning
- Faithful Chain-of-Thought Reasoning
- Automated Theorem Provers Help Improve Large Language Model Reasoning
- Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning
- Humanity's Last Exam
- Generative Language Modeling for Automated Theorem Proving
- Toward Guarantees for Clinical Reasoning in Vision Language Models via Formal Verification
- Solving math word problems with process- and outcome-based feedback
- CausalRAG2: Hierarchical Causal Knowledge Graph Design for RAG
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering