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

Despite the great success of large language models (LLMs) in various tasks,they suffer from generating hallucinations. We introduce Truth Forest, a methodthat enhances truthfulness in LLMs by uncovering hidden truth representationsusing multi-dimensional orthogonal probes. Specifically, it creates multipleorthogonal bases for modeling truth by incorporating orthogonal constraintsinto the probes. Moreover, we introduce Random Peek, a systematic techniqueconsidering an extended range of positions within the sequence, reducing thegap between discerning and generating truth features in LLMs. By employing thisapproach, we improved the truthfulness of Llama-2-7B from 40.8\% to 74.5\% onTruthfulQA. Likewise, significant improvements are observed in fine-tunedmodels. We conducted a thorough analysis of truth features using probes. Ourvisualization results show that orthogonal probes capture complementarytruth-related features, forming well-defined clusters that reveal the inherentstructure of the dataset.

Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning