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 demonstrated remarkable capabilities inperforming complex tasks. Moreover, recent research has shown thatincorporating human-annotated rationales (e.g., Chain-of-Thought prompting)during in-context learning can significantly enhance the performance of thesemodels, particularly on tasks that require reasoning capabilities. However,incorporating such rationales poses challenges in terms of scalability as thisrequires a high degree of human involvement. In this work, we present a novelframework, Amplifying Model Performance by Leveraging In-Context Learning withPost Hoc Explanations (AMPLIFY), which addresses the aforementioned challengesby automating the process of rationale generation. To this end, we leveragepost hoc explanation methods which output attribution scores (explanations)capturing the influence of each of the input features on model predictions.More specifically, we construct automated natural language rationales thatembed insights from post hoc explanations to provide corrective signals toLLMs. Extensive experimentation with real-world datasets demonstrates that ourframework, AMPLIFY, leads to prediction accuracy improvements of about 10-25%over a wide range of tasks, including those where prior approaches which relyon human-annotated rationales such as Chain-of-Thought prompting fall short.Our work makes one of the first attempts at highlighting the potential of posthoc explanations as valuable tools for enhancing the effectiveness of LLMs.Furthermore, we conduct additional empirical analyses and ablation studies todemonstrate the impact of each of the components of AMPLIFY, which, in turn,leads to critical insights for refining in-context learning.

Post Hoc Explanations of Language Models Can Improve Language Models