Allora Labs’ Post

Thrilled to share that our latest paper, "FEIR: Quantifying and Reducing Envy and Inferiority for Fair Recommendation of Limited Resources," has been accepted for publication in ACM Transactions on Intelligent Systems and Technology (January 2024)! In collaboration with my dear colleagues Bo Kang, Jefrey Lijffijt, Tijl De Bie, we've ventured into the complex world of fairness in recommendation systems. Our work introduces innovative metrics, namely 'inferiority' and 'envy', to tackle the unique challenges present in sectors where opportunities are limited, such as e-recruitment and online dating. The FEIR framework we propose goes beyond traditional methods by ensuring a fair distribution of resources, balancing the trade-offs between accuracy and fairness. Through extensive experiments, we demonstrate how FEIR significantly improves fairness in recommendations, contributing to more equitable outcomes in real-world scenarios. A big thank you to my co-authors and everyone who supported us through this journey. Read our full paper here: https://lnkd.in/eS6WEtwR

Here is the finished part 2 of this paper's read through! If you are curious about the more technical aspects of industry standard RAG, check it out. https://lnkd.in/gPBG8PE4

📝 New article @ISTJrnal ""Multi-objective optimization and integrated indicator-driven two-stage project recommendation in time-dependent software ecosystem"" by Xin Shen, Xiangjuan Yao, Dunwei Gong, Huijie Tu 👉 Get your copy at "

This post introduces #LangChain support for Nomic Embed Vision, enabling multi-modal #RAG. It showcases how to embed images and text with #Nomic AI Vision and Text, then retrieve with #similarity search, and pass into a multimodal #LLM for answer synthesis. Multi-modal highlights the integration of different types of data, such as images and text, for enhanced #AI processing. RAG refers to the retrieval-augmented generation, a method that improves answer synthesis by leveraging external information. Similarity search is crucial for identifying relevant information across modalities before synthesis by a multimodal LLM.

📝 New article @ISTJrnal "Application of Knowledge Graph in Software Engineering Field: a systematic literature review" by Lu Wang, Chenhan Sun, Chongyang Zhang, Weikun Nie, Kaiyuan Huang 👉 Get your copy at

Discover the realm of tech jargon through the #TechDogs tech dictionary. Understand the word of the day with its simplified definition. Word of the day - Gedanken https://bit.ly/3PtXzpB

Very much in the Redactive lane tldr; [the focus is on automating processes, reducing manual steps in workflows, and improving overall cost containment at scale], Clyde Fernandez and Matt Hallam, let's take a look.

📝 New article @ISTJrnal "Towards the Definition of a Research Agenda on Mobile Application Testing based on a Tertiary Study" by Pedro Henrique Kuroishi, José Carlos Maldonado, Auri Marcelo Rizzo Vincenzi 👉 Get your copy at

I am glad to share that our paper "Balanced Quality Score (BQS): Measuring Popularity Debiasing in Recommendation" has just been accepted to the ACM Journal "Transactions on Intelligent Systems and Technology" and it is freely available in open access! 🎉 In the paper, we introduce a formal, data-driven, and parameter-free strategy for classifying items into low, medium, and high popularity categories. Then we introduce BQS, a quality measure that rewards the debiasing techniques that successfully push a recommender system to suggest niche items, without losing points in its predictive capability in terms of global accuracy. Check it out ➡ https://lnkd.in/dz_kHq_f. Thanks to all the co-authors! Marco Minici, Ettore Ritacco, @Luciano Caroprese, Francesco Sergio Pisani, Giuseppe Manco

📝 New article @ISTJrnal "Why and How Bug Blocking Relations are Breakable: An Empirical Study on Breakable Blocking Bugs" by Hao Ren, Yanhui Li, Lin Chen, Yuming Zhou, Changhai Nie 👉 Get your copy at