Research on enterprise AI August 2023

.It may have been August but there was no noticeable diminution of the rate of publication of research papers on arXiv relating to the enterprise applications of AI, with a particular focus on search applications.  This is far from a comprehensive listing and is inevitably biased towards my own areas of research interest. This month I have listed the search research under a specific heading. I would be the first to acknowledge that the distinction is very blurred!

Enterprise-wide applications 

To Classify is to Interpret: Building Taxonomies from Heterogeneous Data through Human-AI Collaboration

Lessons in Reproducibility: Insights from NLP Studies in Materials Science

Three Bricks to Consolidate Watermarks for Large Language Models

AI Literature Review Suite

Should we trust web scraped data?

What has ChatGPT read? The origins of archaeological citations used by a generative artificial intelligence application

Large Language Model Prompt Chaining for Long Legal Document Classification

NLLG Quarterly arXiv Report 06/23: What are the most influential current AI Papers?

Through the Lens of Core Competency: Survey on Evaluation of Large Language Models

GPTEval: A Survey on Assessments of ChatGPT and GPT-4

Beyond Document Page Classification: Design, Datasets, and Challenges

Search and information retrieval

On the Effects of Regional Spelling Conventions in Retrieval Models

Generative Query Reformulation for Effective Adhoc Search

Evaluation of Conversational Agents for Aerospace Domain

Large Language Models for Information Retrieval: A Survey

Informed Named Entity Recognition Decoding for Generative Language Models

Improving Neural Ranking Models with Traditional IR Methods

Vector Search with OpenAI Embeddings: Lucene Is All You Need

Is ChatGPT a Biomedical Expert? Exploring the Zero-Shot Performance of Current GPT Models in Biomedical Tasks

Martin White 19 September 2023