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

Information Retrieval (IR), the process of finding information to satisfyuser's information needs, plays an essential role in modern people's lives.Recently, large language models (LLMs) have demonstrated remarkablecapabilities across various tasks, some of which are important for IR.Nonetheless, LLMs frequently confront the issue of generating responses thatlack specificity. This has limited the overall effectiveness of LLMs for IR inmany cases. To address these issues, we present an unsupervised alignmentframework called Reinforcement Learning from Contrastive Feedback (RLCF), whichempowers LLMs to generate both high-quality and context-specific responses thatsuit the needs of IR tasks. Specifically, we construct contrastive feedback bycomparing each document with its similar documents, and then propose a rewardfunction named Batched-MRR to teach LLMs to generate responses that capturesthe fine-grained information that distinguish documents from their similarones. To demonstrate the effectiveness of RLCF, we conducted experiments in twotypical applications of LLMs in IR, i.e., data augmentation and summarization.The experimental results show that RLCF can effectively improve the performanceof LLMs in IR context.

Aligning the Capabilities of Large Language Models with the Context of Information Retrieval via Contrastive Feedback