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

This paper presents an in-depth analysis of Large Language Models (LLMs),focusing on LLaMA, a prominent open-source foundational model in naturallanguage processing. Instead of assessing LLaMA through its generative output,we design multiple-choice tasks to probe its intrinsic understanding inhigh-order tasks such as reasoning and computation. We examine the modelhorizontally, comparing different sizes, and vertically, assessing differentlayers. We unveil several key and uncommon findings based on the designedprobing tasks: (1) Horizontally, enlarging model sizes almost could notautomatically impart additional knowledge or computational prowess. Instead, itcan enhance reasoning abilities, especially in math problem solving, and helpsreduce hallucinations, but only beyond certain size thresholds; (2) In verticalanalysis, the lower layers of LLaMA lack substantial arithmetic and factualknowledge, showcasing logical thinking, multilingual and recognitive abilities,with top layers housing most computational power and real-world knowledge.

Is Bigger and Deeper Always Better? Probing LLaMA Across Scales and Layers