# Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study

arXiv: https://arxiv.org/abs/2506.04810 · HTML: https://mlsanity.com/paper/2506.04810/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 33 of its 46 references that are in the map.
- First posted on arXiv 5 Jun 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 30 of 33)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://mlsanity.com/paper/2305.12295/) (2023)
- [Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought](https://mlsanity.com/paper/2210.01240/) (2022)
- [Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning](https://mlsanity.com/paper/2205.09712/) (2022)
- [ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language](https://mlsanity.com/paper/2012.13048/) (2020)
- [Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning](https://mlsanity.com/paper/2502.14768/) (2025)
- [FOLIO: Natural Language Reasoning with First-Order Logic](https://mlsanity.com/paper/2209.00840/) (2022)
- [ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning](https://mlsanity.com/paper/2212.07919/) (2022)
- [LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers](https://mlsanity.com/paper/2310.15164/) (2023)
- [On Memorization of Large Language Models in Logical Reasoning](https://mlsanity.com/paper/2410.23123/) (2024)
- [GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements](https://mlsanity.com/paper/2402.10963/) (2024)
- [Faithful Logical Reasoning via Symbolic Chain-of-Thought](https://mlsanity.com/paper/2405.18357/) (2024)
- [ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness](https://mlsanity.com/paper/2304.10703/) (2023)
- [LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models](https://mlsanity.com/paper/2404.15522/) (2024)
- [Harnessing the Power of Large Language Models for Natural Language to First-Order Logic Translation](https://mlsanity.com/paper/2305.15541/) (2023)
- [Generating Natural Language Proofs with Verifier-Guided Search](https://mlsanity.com/paper/2205.12443/) (2022)
- [On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective](https://mlsanity.com/paper/2502.14296/) (2025)
- [Multi-LogiEval: Towards Evaluating Multi-Step Logical Reasoning Ability of Large Language Models](https://mlsanity.com/paper/2406.17169/) (2024)
- [Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models](https://mlsanity.com/paper/2310.00836/) (2023)
- [SceMQA: A Scientific College Entrance Level Multimodal Question Answering Benchmark](https://mlsanity.com/paper/2402.05138/) (2024)
- [DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacy](https://mlsanity.com/paper/2310.18659/) (2023)
- [Defending Jailbreak Prompts via In-Context Adversarial Game](https://mlsanity.com/paper/2402.13148/) (2024)
- [Divide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical Reasoning](https://mlsanity.com/paper/2410.08047/) (2024)
- [Social Science Meets LLMs: How Reliable Are Large Language Models in Social Simulations?](https://mlsanity.com/paper/2410.23426/) (2024)
- [LabSafety Bench: Benchmarking LLMs on Safety Issues in Scientific Labs](https://mlsanity.com/paper/2410.14182/) (2024)
- [Language Models can be Logical Solvers](https://mlsanity.com/paper/2311.06158/) (2023)
- [Learning to Reason via Mixture-of-Thought for Logical Reasoning](https://mlsanity.com/paper/2505.15817/) (2025)

## Built on by (most cited first, 17 of 17)

- [R-Zero: Self-Evolving Reasoning LLM from Zero Data](https://mlsanity.com/paper/2508.05004/) (2025)
- [Parallel-R1: Towards Parallel Thinking via Reinforcement Learning](https://mlsanity.com/paper/2509.07980/) (2025)
- [Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation](https://mlsanity.com/paper/2509.15194/) (2025)
- [CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models](https://mlsanity.com/paper/2509.09675/) (2025)
- [Are Tools All We Need? Unveiling the Tool-Use Tax in LLM Agents](https://mlsanity.com/paper/2605.00136/) (2026)
- [SLR: Automated Synthesis for Scalable Logical Reasoning](https://mlsanity.com/paper/2506.15787/) (2025)
- [Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning](https://mlsanity.com/paper/2605.21127/) (2026)
- [ReEfBench: Quantifying the Reasoning Efficiency of LLMs](https://mlsanity.com/paper/2601.03550/) (2026)
- [TDA-RC: Task-Driven Alignment for Knowledge-Based Reasoning Chains in Large Language Models](https://mlsanity.com/paper/2604.04942/) (2026)
- [Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data](https://mlsanity.com/paper/2604.18493/) (2026)
- [Quantifying LLM Biases Across Instruction Boundary in Mixed Question Forms](https://mlsanity.com/paper/2509.20278/) (2025)
- [Concept Generalization in Humans and Large Language Models: Insights from the Number Game](https://mlsanity.com/paper/2512.20162/) (2025)
- [Correct Prediction, Wrong Steps? Consensus Reasoning Knowledge Graph for Robust Chain-of-Thought Synthesis](https://mlsanity.com/paper/2604.14121/) (2026)
- [Discovering a Shared Logical Subspace: Steering LLM Logical Reasoning via Alignment of Natural-Language and Symbolic Views](https://mlsanity.com/paper/2604.19716/) (2026)
- [SciR: A Controllable Benchmark for Scientific Reasoning in LLMs](https://mlsanity.com/paper/2606.13020/) (2026)
- [GTA: Graph Theory Agent and Benchmark for Algorithmic Graph Reasoning with LLMs](https://mlsanity.com/paper/2609.12265/) (2026)
- [SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance](https://mlsanity.com/paper/2609.30192/) (2026)

## Abstract (arXiv)

Logical reasoning is a core capability for large language models (LLMs), yet existing benchmarks that rely solely on final-answer accuracy fail to capture the quality of the reasoning process. To address this, we introduce FineLogic, a fine-grained evaluation framework that assesses logical reasoning across three dimensions: overall accuracy, stepwise soundness, and representation-level probing. Leveraging this framework, we conduct a comprehensive study on how different supervision formats in fine-tuning shape reasoning abilities. We fine-tune LLMs on four supervision styles: one in natural language and three symbolic variants. We find a key trade-off: natural language supervision excels at generalization to out-of-distribution and long-chain problems, whereas symbolic supervision is superior at instilling structurally sound, atomic reasoning steps. Furthermore, our probing analysis indicates that fine-tuning primarily refines the model's step-by-step generation process, rather than improving its ability to converge on an answer early. Together, our framework and analysis provide a more rigorous lens for evaluating and improving logical reasoning in LLMs. The code is available at https://github.com/YujunZhou/FineLogic.