Pith. sign in

REVIEW 9 cited by

Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2304.03439 v3 pith:C5CZKSBZ submitted 2023-04-07 cs.CL cs.AI

Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4

classification cs.CL cs.AI
keywords reasoninggpt-4logicaldatasetschatgptbenchmarksperformancelanguage
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Generalizing Numerical Reasoning in Table Data through Operation Sketches and Self-Supervised Learning

    cs.LG 2026-04 unverdicted novelty 6.0

    TaNOS improves cross-domain numerical reasoning over tables by combining header anonymization, operation sketches, and self-supervised pretraining, achieving 80.13% accuracy on FinQA with 10% of training data.

  2. Learning to Ask: When LLM Agents Meet Unclear Instruction

    cs.CL 2024-08 unverdicted novelty 6.0

    Introduces NoisyToolBench benchmark and Ask-when-Needed framework to improve LLM tool-use performance when user instructions are unclear or incomplete.

  3. LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

    cs.SE 2024-03 unverdicted novelty 6.0

    LiveCodeBench collects 400 recent contest problems to create a contamination-free benchmark evaluating LLMs on code generation and related capabilities like self-repair and execution.

  4. Novelty-based Tree-of-Thought Search for LLM Reasoning and Planning

    cs.AI 2026-05 unverdicted novelty 5.0

    Novelty estimation via LLM prompts enables pruning in Tree-of-Thought search, reducing overall token usage on language planning benchmarks.

  5. Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization

    cs.AI 2026-05 unverdicted novelty 5.0

    SCM-GRPO grounds multi-hop fact verification in structural causal models and applies GRPO reinforcement learning to optimize reasoning chain length, outperforming baselines on HoVer and EX-FEVER.

  6. Generalizing Numerical Reasoning in Table Data through Operation Sketches and Self-Supervised Learning

    cs.LG 2026-04 unverdicted novelty 5.0

    TaNOS decouples table semantics from numerical structure via anonymization, sketches, and program-first self-supervision, yielding 80.13% FinQA accuracy with 10% data and near-zero cross-domain gap versus over 10pp fo...

  7. Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization

    cs.AI 2026-05 unverdicted novelty 4.0

    The SCM-GRPO framework models multi-hop fact verification as causal inference and applies reinforcement learning to optimize reasoning depth, reporting outperformance on HoVer and EX-FEVER.

  8. Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization

    cs.AI 2026-05 unverdicted novelty 4.0

    An SCM-GRPO framework grounds multi-hop reasoning in structural dependency graphs and optimizes chain length via rule-based RL, outperforming baselines on HoVer and EX-FEVER.

  9. A Goal-Oriented Chatbot for Engaging the Elderly Through Family Photo Conversations

    cs.HC 2026-02 unverdicted novelty 4.0

    A goal-oriented chatbot uses family photos to generate W-questions and open prompts for elderly reminiscence, analyzes topics to suggest follow-up photos, and supplies caregivers with conversation insights via a web portal.