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

Actively inferring user preferences, for example by asking good questions, isimportant for any human-facing decision-making system. Active inference allowssuch systems to adapt and personalize themselves to nuanced individualpreferences. To enable this ability for instruction-tuned large language models(LLMs), one may prompt them to ask users questions to infer their preferences,transforming the language models into more robust, interactive systems.However, out of the box, these models are not efficient at extractingpreferences: the questions they generate are not informative, requiring a highnumber of user interactions and impeding the usability of the downstreamsystem. In this work, we introduce an inference-time algorithm that helps LLMsquickly infer preferences by using more informative questions. Our algorithmuses a probabilistic model whose conditional distributions are defined byprompting an LLM, and returns questions that optimize expected entropy andexpected model change. Results in a simplified interactive web shopping settingwith real product items show that an LLM equipped with our entropy reductionalgorithm outperforms baselines with the same underlying LLM on taskperformance while using fewer user interactions.

Active Preference Inference using Language Models and Probabilistic Reasoning