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

Informal reasoning ability is the ability to reason based on common sense,experience, and intuition.Humans use informal reasoning every day to extractthe most influential elements for their decision-making from a large amount oflife-like information.With the rapid development of language models, therealization of general artificial intelligence has emerged with hope. Given theoutstanding informal reasoning ability of humans, how much informal reasoningability language models have has not been well studied by scholars.In order toexplore the gap between humans and language models in informal reasoningability, this paper constructs a Detective Reasoning Benchmark, which is anassembly of 1,200 questions gathered from accessible online resources, aims atevaluating the model's informal reasoning ability in real-lifecontext.Considering the improvement of the model's informal reasoning abilityrestricted by the lack of benchmark, we further propose a Self-Question PromptFramework that mimics human thinking to enhance the model's informal reasoningability.The goals of self-question are to find key elements, deeply investigatethe connections between these elements, encourage the relationship between eachelement and the problem, and finally, require the model to reasonably answerthe problem.The experimental results show that human performance greatlyoutperforms the SoTA Language Models in Detective Reasoning Benchmark.Besides,Self-Question is proven to be the most effective prompt engineering inimproving GPT-4's informal reasoning ability, but it still does not evensurpass the lowest score made by human participants.Upon acceptance of thepaper, the source code for the benchmark will be made publicly accessible.

Go Beyond The Obvious: Probing the gap of INFORMAL reasoning ability between Humanity and LLMs by Detective Reasoning Puzzle Benchmark