# Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4

arXiv: https://arxiv.org/abs/2304.03439 · HTML: https://mlsanity.com/paper/2304.03439/

## Key facts

- Cited by 202 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 18 of its 25 references that are in the map.
- First posted on arXiv 7 Apr 2023.

## Placed in

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

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [Is ChatGPT a General-Purpose Natural Language Processing Task Solver?](https://mlsanity.com/paper/2302.06476/) (2023)
- [Augmenting Neural Networks with First-order Logic](https://mlsanity.com/paper/1906.06298/) (2019)
- [Can neural networks understand monotonicity reasoning?](https://mlsanity.com/paper/1906.06448/) (2019)
- [From LSAT: The Progress and Challenges of Complex Reasoning](https://mlsanity.com/paper/2108.00648/) (2021)
- [HELP: A Dataset for Identifying Shortcomings of Neural Models in Monotonicity Reasoning](https://mlsanity.com/paper/1904.12166/) (2019)
- [TaxiNLI: Taking a Ride up the NLU Hill](https://mlsanity.com/paper/2009.14505/) (2020)
- [ConjNLI: Natural Language Inference Over Conjunctive Sentences](https://mlsanity.com/paper/2010.10418/) (2020)
- [Natural Language Inference in Context -- Investigating Contextual Reasoning over Long Texts](https://mlsanity.com/paper/2011.04864/) (2020)

## Built on by (most cited first, 30 of 202)

- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://mlsanity.com/paper/2305.12295/) (2023)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution](https://mlsanity.com/paper/2401.03065/) (2024)
- [How is ChatGPT's behavior changing over time?](https://mlsanity.com/paper/2307.09009/) (2023)
- [SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models](https://mlsanity.com/paper/2307.10635/) (2023)
- [Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs](https://mlsanity.com/paper/2402.03927/) (2024)
- [PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts](https://mlsanity.com/paper/2306.04528/) (2023)
- [Evaluating Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2310.19736/) (2023)
- [Can LLM-Generated Misinformation Be Detected?](https://mlsanity.com/paper/2309.13788/) (2023)
- [Multi-Step Reasoning with Large Language Models, a Survey](https://mlsanity.com/paper/2407.11511/) (2024)
- [Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation](https://mlsanity.com/paper/2305.15852/) (2023)
- [From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought](https://mlsanity.com/paper/2306.12672/) (2023)
- [LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities](https://mlsanity.com/paper/2305.13168/) (2023)
- [MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation](https://mlsanity.com/paper/2308.08239/) (2023)
- [A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation](https://mlsanity.com/paper/2305.11391/) (2023)
- [AgentSims: An Open-Source Sandbox for Large Language Model Evaluation](https://mlsanity.com/paper/2308.04026/) (2023)
- [Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey](https://mlsanity.com/paper/2404.01869/) (2024)
- [GPTEval: A Survey on Assessments of ChatGPT and GPT-4](https://mlsanity.com/paper/2308.12488/) (2023)
- [GPT4GEO: How a Language Model Sees the World's Geography](https://mlsanity.com/paper/2306.00020/) (2023)
- [GroupDebate: Enhancing the Efficiency of Multi-Agent Debate Using Group Discussion](https://mlsanity.com/paper/2409.14051/) (2024)
- [Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond](https://mlsanity.com/paper/2306.09841/) (2023)
- [Are ChatGPT and GPT-4 General-Purpose Solvers for Financial Text Analytics? A Study on Several Typical Tasks](https://mlsanity.com/paper/2305.05862/) (2023)
- [Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injection](https://mlsanity.com/paper/2308.10819/) (2023)
- [Give Us the Facts: Enhancing Large Language Models with Knowledge Graphs for Fact-aware Language Modeling](https://mlsanity.com/paper/2306.11489/) (2023)
- [From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning](https://mlsanity.com/paper/2310.00492/) (2023)
- [Strategic Behavior of Large Language Models: Game Structure vs. Contextual Framing](https://mlsanity.com/paper/2309.05898/) (2023)
- [Fighting Fire with Fire: The Dual Role of LLMs in Crafting and Detecting Elusive Disinformation](https://mlsanity.com/paper/2310.15515/) (2023)

## Abstract (arXiv)

Harnessing logical reasoning ability is a comprehensive natural language understanding endeavor. With the release of Generative Pretrained Transformer 4 (GPT-4), highlighted as "advanced" at reasoning tasks, we are eager to learn the GPT-4 performance on various logical reasoning tasks. This report analyses multiple logical reasoning datasets, with popular benchmarks like LogiQA and ReClor, and newly-released datasets like AR-LSAT. We test the multi-choice reading comprehension and natural language inference tasks with benchmarks requiring logical reasoning. We further construct a logical reasoning out-of-distribution dataset to investigate the robustness of ChatGPT and GPT-4. We also make a performance comparison between ChatGPT and GPT-4. Experiment results show that ChatGPT performs significantly better than the RoBERTa fine-tuning method on most logical reasoning benchmarks. With early access to the GPT-4 API we are able to conduct intense experiments on the GPT-4 model. The results show GPT-4 yields even higher performance on most logical reasoning datasets. Among benchmarks, ChatGPT and GPT-4 do relatively well on well-known datasets like LogiQA and ReClor. However, the performance drops significantly when handling newly released and out-of-distribution datasets. Logical reasoning remains challenging for ChatGPT and GPT-4, especially on out-of-distribution and natural language inference datasets. We release the prompt-style logical reasoning datasets as a benchmark suite and name it LogiEval.