English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Large Language Models (LLMs) have shown human-like reasoning abilities butstill struggle with complex logical problems. This paper introduces a novelframework, Logic-LM, which integrates LLMs with symbolic solvers to improvelogical problem-solving. Our method first utilizes LLMs to translate a naturallanguage problem into a symbolic formulation. Afterward, a deterministicsymbolic solver performs inference on the formulated problem. We also introducea self-refinement module, which utilizes the symbolic solver's error messagesto revise symbolic formalizations. We demonstrate Logic-LM's effectiveness onfive logical reasoning datasets: ProofWriter, PrOntoQA, FOLIO,LogicalDeduction, and AR-LSAT. On average, Logic-LM achieves a significantperformance boost of 39.2% over using LLM alone with standard prompting and18.4% over LLM with chain-of-thought prompting. Our findings suggest thatLogic-LM, by combining LLMs with symbolic logic, offers a promising avenue forfaithful logical reasoning. Code and data are publicly available athttps://github.com/teacherpeterpan/Logic-LLM.

Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning