Vish Khanna

May 23, 2024RAG
10-Step RAG System Audit to Eradicate Bias and Toxicity: image 1 10-Step RAG System Audit to Eradicate Bias and Toxicity
As the use of Retrieval-Augmented Generation (RAG) systems becomes more common in countless industries, ensuring their performance and fairness has become more critical than ever. RAG systems, which enhance content generation by integrating retrieval mechanisms, are powerful tools to improve...

By Vish Khanna

May 23, 2024Generative AI
10-Step RAG System Audit to Eradicate Bias and Toxicity: image 2 Prevent Costly GenAI Errors with Rigorous Output Evaluation — Here’s How
Output evaluation is the process through which the functionality and efficiency of AI-generated responses are rigorously assessed against a set of predefined criteria. It ensures that AI systems are not only technically proficient but also tailored to meet the nuanced demands of specific...

By Vish Khanna

May 16, 2024RAG
10-Step RAG System Audit to Eradicate Bias and Toxicity: image 3 Why RAG Systems Struggle with Acronyms – And How to Fix It
Acronyms allow us to compact a wealth of information into a few letters. The goal of such a linguistic shortcut is obvious – quicker and more efficient communication, saving time and reducing complexity in both spoken and written language. But it comes at a price – due to their condensed nature...

By Vish Khanna

May 15, 2024RAG
10-Step RAG System Audit to Eradicate Bias and Toxicity: image 4 10 Ways Duplicate Content Can Cause Errors in RAG Systems
Effective data management is crucial for the optimal performance of Retrieval-Augmented Generation (RAG) models. Duplicate content can significantly impact the accuracy and efficiency of these systems, leading to errors in response to user queries. Understanding the repercussions of duplicate...

By Vish Khanna

May 12, 2024AI Education
10-Step RAG System Audit to Eradicate Bias and Toxicity: image 5 Choose Your AI Weapon: Deep Learning or Traditional Machine Learning
Deep learning vs. traditional machine learning: Which model is right for your needs? Each approach has its unique strengths and applications, but there are key differences between deep learning and traditional machine learning. Traditional Machine Learning Explained Traditional machine learning...

By Vish Khanna

May 5, 2024AI Challenges
Midjourney depiction of a machine learning pipeline GenAI in Banking Is a Double-edged Sword of Risk and Reward
In the banking sector, every percentage point in efficiency can translate to billions in revenue. According to McKinsey, GenAI could potentially add $340 billion in revenue to the sector’s annual global revenues. This represents a 4.7% increase in total industry revenues – a surge comparable...

By Vish Khanna

April 26, 2024RAG
Midjourney depiction of NLP applications in business and research Continuously Monitor Your RAG System to Neutralize Data Decay
Poor data quality is the largest hurdle for companies who embark on generative AI projects. If your LLMs don’t have access to the right information, they can’t possibly provide good responses to your users and customers. In the previous articles in this series, we spoke about data enrichment,...

By Vish Khanna

April 25, 2024RAG
10-Step RAG System Audit to Eradicate Bias and Toxicity: image 6 Fix RAG Content at the Source to Avoid Compromised AI Results
While Retrieval-Augmented Generation (RAG) significantly enhances the capabilities of large language models (LLMs) by pulling from vast sources of external data, they are not immune to the pitfalls of inaccurate or outdated information. In fact, according to recent industry analyses, one of the...

By Vish Khanna

April 24, 2024Generative AI
10-Step RAG System Audit to Eradicate Bias and Toxicity: image 7 Generative AI in Healthcare: A Balance between Benefits and Ethics
It’s estimated that $1 trillion in healthcare spending is wasted each year in the U.S. By automating routine tasks and making more use of clinical data, GenAI is a new opportunity to optimize healthcare expenditures and unlock part of the money lost to inefficiencies. It could organize...

By Vish Khanna

April 23, 2024RAG
10-Step RAG System Audit to Eradicate Bias and Toxicity: image 8 Strategic Data Filtering for Enhanced RAG System Accuracy and Compliance
Large language models are skilled at generating human-like content, but they’re only as valuable as the data they pull from. If your knowledge source contains duplicate, inaccurate, irrelevant, or biased information, the LLM will never behave optimally. In fact, poor data quality is so inhibiting...

By Vish Khanna

March 19, 2024News/Events
10-Step RAG System Audit to Eradicate Bias and Toxicity: image 9 Evil Geniuses Attack, The LLM Forgettery, Character Consistency and More
Augmented Shelf | Issue 2 | March 19, 2024 Welcome to Augmented Shelf, a wrap-up of the week’s AI news, trends and research that are forging the future of work. Evil Geniuses Vs. ChatDev To evaluate the vulnerability of LLM-based agents, researchers at Tsinghua University in Beijing, China, have...

By Vish Khanna

March 14, 2024AI Challenges
10-Step RAG System Audit to Eradicate Bias and Toxicity: image 10 Forget LLM Memory – Why LLMs Need Adaptive Forgetting
Large Language Models (LLMs) rely on extensive memory to store and manipulate vast datasets, a key factor that allows them to learn from past inputs and improve their linguistic abilities over time. But what if, alongside remembering, LLMs could also benefit from adaptive forgetting? The notion of...

By Vish Khanna