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 emerged as valuable tools for many naturallanguage understanding tasks. In safety-critical applications such ashealthcare, the utility of these models is governed by their ability togenerate outputs that are factually accurate and complete. In this work, wepresent dialog-enabled resolving agents (DERA). DERA is a paradigm madepossible by the increased conversational abilities of LLMs, namely GPT-4. Itprovides a simple, interpretable forum for models to communicate feedback anditeratively improve output. We frame our dialog as a discussion between twoagent types - a Researcher, who processes information and identifies crucialproblem components, and a Decider, who has the autonomy to integrate theResearcher's information and makes judgments on the final output.  We test DERA against three clinically-focused tasks. For medical conversationsummarization and care plan generation, DERA shows significant improvement overthe base GPT-4 performance in both human expert preference evaluations andquantitative metrics. In a new finding, we also show that GPT-4's performance(70%) on an open-ended version of the MedQA question-answering (QA) dataset(Jin et al. 2021, USMLE) is well above the passing level (60%), with DERAshowing similar performance. We release the open-ended MEDQA dataset athttps://github.com/curai/curai-research/tree/main/DERA.

DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving Agents