Angad Arora

#Llama3 is released now. Some insights: 1. 15T tokens processed 2. 8B and 70B instruct and fine-tuned variants 3. 400B variant under training (multimodal) 4. 24,576 NVIDIA H100 Tensor Core GPUs linked with an NVIDIA Quantum-2 InfiniBand network. model-card: https://lnkd.in/dJzjzdmW #AGI #Llama3 #GenAI #opensource

4

When selecting the answer for an multi choice question, LLMs prefer the choices in a given position, or with a specific choice symbol. This is known as selection bias. It hugely reduce the capability of using LLM to do labeling. Luckily, selection bias has been tackled by our intern Froilan (Hyeong Kyu) during his summer internship! Check this amazing work lead by him! Here are some key findings: 1. Selection bias is more extreme when the model’s response is incorrect. 2. Most of selection bias observed to be in the final output layer of the decode. Thus, pruning those nodes reduce selection bias. 3. Adding an "I don't know" option help LLM reduce selection bias even for black box LLM! Amazon Science

24

Optillm: An optimizing inference proxy for LLMs Optillm is an optimizing inference proxy that has over a dozen techniques that aim to improve the accuracy of the responses using test-time compute. Over the last couple of months we have set several SOTA results using smaller and less capable models like gpt-4o-mini. Recently, we have added support for plugins that enable capabilities like memory, privacy and code execution to optillm. Plugins are just python scripts that you can also write yourself, optillm would then load them at start from the directory. You can now also combine the plugins and techniques using & and | operators. E.g. We recently evaluated the new FRAMES benchmark from Google. Using a combination of plugins and techniques (we used readurls&memory-gpt-4o-mini) we were able to get 65.7% accuracy on the benchmark which is very close to what Google reported in their paper with Gemini Flash 1.5 (66.5) which has a context length that is almost 10 times that of gpt-4o-mini. Do check out Optillm at https://lnkd.in/gN6_kNky

21

1 Comment

The BayLearn 2024 abstract submission deadline has been extended to Aug 5, 2024. If you are working on cutting-edge ML research, please consider submitting an abstract. BayLearn 2024 will be an in-person event, held on Oct 10, 2024: https://baylearn.org This is a great opportunity for student researchers to showcase their latest research work and get good feedback. Submissions are non-archival and the review process is quite informal. #machinelearning #research

68

Fully agree to Pascals Summary! (Pascal's summary quote below 👇) The results? Despite the hype around LLMs' impressive performance on medical text processing and licensing exams, they still couldn't beat tried-and-true models like SVM and XGBoost when it came to real-world clinical predictions. This held true regardless of the LLMs' size, prompting strategy, or fine-tuning. So what's going on? The researchers suggest that LLMs may have a "deficiency in clinical reasoning and decision-making" compared to purpose-built models. It's a reminder that, while LLMs are undoubtedly powerful, they're not a magic bullet for every healthcare application. As the study's authors put it: "We call for caution when practitioners adopt LLMs in clinical applications."

1

🚀 Making LLMs work for you - A Guide to Become 10x Programmer/MLE/DS I am sure many of you use LLMs for your day-to-day work. Mostly, I have seen people use LLMs while writing code (Copilot), or as an alternative to Copilot to catch bugs, but they have become much more useful than that, provided you know how to use them well. Here are a few ways I have been using LLMs in my daily work that are helping me increase my productivity: 📚 1. Quick Paper Assessment with ELI5 Summaries - Paper abstracts are called abstracts for a reason. Asking an LLM for an ELI5 summary makes it much easier to know if I want to read a paper. 💻 2. Implementing Research Papers in Code - Try giving an LLM like Claude/ChatGPT a research paper and ask to code it. You would be surprised. Tip: Claude performs much better for this task. 🔄 3. Upgrading Code Structure and Readability - Do you want to add typing hints when writing your Python code, or do you need comments in your code, or do you have a big function that you want to be converted to classes in your code? LLMs can do it all, and you would be amazed at the code-conversion power they have. ⚡ 4. Optimizing Code Performance - The thing with LLMs is that if you tell them what to do, they can do it well. For example, if you give them a non-optimized piece of code that runs correctly, they will be able to write it in a much-optimized way. For example, I just used an LLM to convert a matrix multiplication in PyTorch to sparse MM as I was getting an OOM memory error because one of the matrices became too large. I am not even joking, but that would have taken at least 1-2 hours for me to come up with. 📝 5. Automated Documentation - Got bored of writing documentation for what you did but have the code? LLMs also work the other way around. Want to write a summary of what you did in a week, you can use an LLM for that. Saves so much time that gets wasted in formatting. 🧪 6. Streamlined Test Framework Creation - Let LLMs handle the boilerplate for Unit tests & Integration tests while you focus on core logic. 🌐 7. Language-Agnostic Development - You can paste a function in Python and ask for its equivalent in Rust, complete with language-specific best practices and error handling. This dramatically reduces the learning curve when working with new languages and helps maintain productivity during language transitions. 🤝 Apart from all of the above, LLMs work well as mentors as well as interns. LLMs are great when you just need someone to bounce ideas with. I sometimes just talk to an LLM as I would to a colleague talking about the problems I have and how I can solve them. And they come up with the right ideas or send me in the right direction a lot of times. They also act as a personal assistant for free, who can deal with writing messages, creating charts, and doing all sorts of uninteresting work for you. 💭 What's your favorite way to use LLMs? Let me know in the comments! #MachineLearning #AI #Programming

47

I remember when this all started. Faris - invited me to catch up at our favorite spot around Blok M. I had no idea he’d just wrapped up a procedure at Pondok Indah Hospital! (He really knows how to add drama to our catch-ups.) We’d been on separate paths and projects since "the winding down project", but there he was, reminding me of our dream to ride this AI wave together again. It was a plan we’d hatched with Sahal Zain & Gurnoor Dhillon when the world of AI was still mostly theoretical and jargon-heavy. Somehow, the conversation continued with Gurnoor Dhillon while he was waiting for his meeting with someone who would eventually become one of CalvinBall’s key early adopters. It felt like everything was coming together, like a series of seemingly random dots connecting to form a bigger picture. Seeing how far we’ve come as a team at CalvinBall Technologies is truly exciting. What started as theoretical discussions has now evolved into practical Gen AI solutions that are solving everyday problems and hold endless possibilities to shape the industry. 👨‍🚀 👩‍🚀 Here’s to pushing boundaries and achieving new milestones together! Gurnoor Dhillon, Sandeep Ramesh, Faris -, Sahal Zain, Eva Zuliya, Ratu Nadiah Khairunnisa 🚀 #GenAI #AIInnovation #TechJourney #ArtificialIntelligence #TechTransformation #CalvinballTech #Calvinballers

55

2 Comments

We just released a blog on whether the use of multimodal feature transfer can detect deception (phenomena like sarcasm, irony, and condescension) in conversation. The short answer... Yes. This particular write-up profiles a subset of our work at Symbl.ai on multimodal large language models, and is research led by one of our summer interns, Benjamin R. (from Prof. Larry Heck's AVA Lab at Georgia Institute of Technology). We have a paper currently under submission on this work, and we can't wait to share the full details with all of you soon. Blog Link: https://lnkd.in/g6m_wFDi #multimodal #featuretransfer #LLMs #deception #conversation #sarcasm #irony #language #AI #ML #NLP #LargeLanguageModels #SummerInternship #ResearchPapers #ACL #Llama2 #SymblDotAI

16

Collaborative AI is gaining momentum at both MNC and Startups, they are investing into this EvolutionNext Robotics AI Transformative Experiential Learning Journey. I am extremely glad to put Singapore on the World map, by anchoring Robotics AI companies here, creating Jobs of the FutureNow as Roboticist. Do support my Leadership Initiative for Singapore as National Interest; help me enable our next-generation Singaporeans to take on Science, Technology, Engineering and Mathematics STEM Education and longer-term Career Practice into Industry 5.0 as Machine Intelligence of Human-Robot Collaborative, Human-centric Autonomy. * My STEM OneCareer Pinnacle and Finale as a 55-years old, always just another very ordinary Singapore-born Singaporean Scientist Engineer in Singapore, essentially a Nobody here 🌸

13

2 Comments

The AI & LLM Revolution Boon or Bane for Society? 🤖 🌍   As we witness the rapid evolution of AI and Large Language Models (LLMs) in recent times, with Meta recently making Llama 3 open source and Vinod Khosla's insane predictions about AI, it's time to pause and reflect on the implications of these advancements on various aspects of our lives.. 🌐   1. Personal Finance 💰: AI and LLMs have the potential to revolutionize personal finance management, making it more accessible and efficient. However, they could also lead to job losses in the financial sector, affecting the livelihoods of many - economic instability?   2. Education 🎓: LLMs can revolutionize education by providing personalized learning experiences, but could they also widen the digital divide?   3. Jobs 🏭: As AI and LLMs infiltrate various industries, how will non-IT and non-engineering professionals adapt to these changes? How can we ensure a smooth transition for affected workforce?   4. Social Life 🤝: Will AI & LLM enhance our social interactions or lead to increased isolation and dependence on technology? AI-powered social media platforms could enhance our online interactions, but they might also contribute to the erosion of privacy and the spread of misinformation.   5. Agriculture 🌾: AI-driven precision farming could boost productivity, but will it also lead to ecological and environmental concerns?   6. Basic Needs 🍲: Can AI help address food security and access to clean water, or will it exacerbate existing inequalities?   7. Work-Life Balance ⚖️: AI can automate mundane tasks, but will it also blur the lines between work and personal life?   8. Health 🏥: AI can revolutionize healthcare, but will it also lead to over-reliance on technology and loss of human touch in patient care? AI-driven healthcare solutions could revolutionize diagnostics and treatment, but they might also raise ethical concerns and exacerbate existing healthcare disparities.   9. Environment, and Ecology 🌳 - AI-driven innovations can help us address pressing global challenges such as climate change and disease outbreaks. However, will they consume vast amounts of energy and resources?   10. Security & Safety 🛡️: AI can improve security measures, but will it also lead to increased surveillance and potential misuse of personal data?   11. Politics & Power 🏛️: AI can help streamline governance, leading to more informed decision-making, will they be exploited for political gains?   Are we on the cusp of a transformative era? As we ponder these questions, it's crucial to remember that responsible AI governance could be the ultimate solution to ensure these technologies benefit society. 🤖   What are your thoughts on this? 🤔 #AI #LLM #ArtificialIntelligence #LargeLanguageModels #Society #Impact #FutureOfWork #Education #PersonalFinance #Environment #Healthcare #Security #Politics #BoonOrBane #BubbleOrRevolution #ResponsibleAI #Governance

3

There is a lot of interest in combining Graph Models and Language Models recently. In 2022, I led an initiative at Twitter (now X) in collaboration with Vivek Kulkarni, Ahmed El-Kishky, Sneha Mehta, and executed by our wonderful summer intern Jinning Li called "NTULM: Enriching Social Media Text Representations with Non-Textual Units" on combining large scale graph content at Twitter with Tweet's text content for building better quality Tweet Embeddings. The internal version of the project required addressing quite a few challenges: 1. Finding the node embeddings for NTUs using Twitter Scale Heterogeneous Graph 2. Training BERT with the above scale node embeddings This work was a follow up to my previous collaboration led by Vivek Kulkarni in 2021 on combining social context like time and geography in language models called "LMSOC: An Approach for Socially Sensitive Pretraining". There are a lot of interesting follow ups in this area and combining Graphs with generative LLMs is something which is very effective on real world datasets. NTULM Talk: https://lnkd.in/g2zvmnhh NTULM Paper: https://lnkd.in/gQq6VCQP LMSOC: https://lnkd.in/ghamVwVk

29

1 Comment

What a great talk from Swapnil Sayan Saha, on Physics-Aware Tiny Machine Learning! https://lnkd.in/g9g4YWs4 There's exciting times ahead as Physics-aware TinyML is becoming increasingly important in merging the power of machine learning with operating in the physical world. By integrating real-world physics models into ultra-low-power devices, this approach dramatically enhances the accuracy and efficiency of TinyML applications. From improving energy efficiency in smart sensors to enabling more accurate anomaly detection in industrial applications, this approach to machine learning at the edge helps machines better understand their environment - without sacrificing power or performance. As we explore the possibilities, this combination of physics and Edge AI opens up new opportunities in fields like healthcare, environmental monitoring, and autonomous systems. It's a huge leap toward making AI more sustainable and impactful, and allows us to build more useful AI-enabled systems that operate in (and on!) the physical world. #TinyML #EdgeAI #PhysicsAwareAI #AIInnovation #Sustainability #MachineLearning

4

Implementing Reinforcement Learning (RL) in the context of Large Language Models (LLMs) posed challenges, particularly in designing reward engineering and penalization components. In traditional RL, reward engineering is straightforward, often defined through a scalar reward function. However, implementing the same concept in RL with LLMs required a critic model that evaluates the questions and answers, critiquing them in a manner that simulates the reward function. A recent research paper on Natural Language Reinforcement Learning (NLRL) provides an intriguing perspective on the reward problem in RL by translating traditional RL concepts into natural language constructs. Here's a summary of how it addresses the reward problem: Language-Based Value Functions: Unlike traditional RL, which uses scalar rewards, NLRL employs language-based value functions. These functions articulate the effectiveness of policies and actions in a more interpretable, natural language format. This approach addresses the need for richer, more informative feedback than simple numerical scores. Iterative Refinement of Language Policies and Critics: NLRL incorporates a structured training pipeline where language-based policies and critics are iteratively refined using textual feedback. This method allows the system to handle the complexities of defining rewards in natural language, improving its understanding and evaluation of actions over time through textual feedback loops. Use of Large Language Models (LLMs): The framework leverages the advanced capabilities of LLMs to interpret, generate, and evaluate complex language-based information. This is essential for implementing language-based value functions and policies, enabling the system to generate and refine responses that align closely with desired outcomes. Distilling Enhanced Actions and Evaluations: NLRL employs a process where enhanced evaluations from the language-based value function approximator and improved actions from the language policy improvement operator are distilled. This allows for continuous refinement and learning. Compatibility with Existing LLMs: The framework is designed to be compatible with current LLMs, enabling it to leverage pre-existing language models to process and generate linguistic data effectively. This compatibility is crucial for translating the traditional reward engineering process into a language-based framework. The NLRL framework's introduction of natural language as a medium for representing and evaluating policies and rewards offers a novel solution to the reward problem in RL. By shifting from numerical reward systems to a more flexible, expressive, and intuitive system based on language, NLRL enhances interpretability and adaptability, paving the way for more diverse RL applications. Innovation Hacks AI Inc. #llm #refincorcementlearning #ai

4

I’m honored to have my insights on synthetic data validation for Large Language Models (LLMs) featured in Label Your Data’s latest article from Featured. Now that many companies build specific models (e.g., Llama 3.1 405B) to facilitate synthesis dataset generation, integrating human expertise into the LLM development process is important. Human-in-the-loop (HITL) approaches ensure that domain experts guide and refine model outputs, leading to more accurate and contextually relevant results. As a GenAI researcher, I believe the concern of running of training data for future LLMs development in the future, raised by experts in the field like Chip Huyen, is valid and deserve significant awareness. The expert-informed data synthesis validation helps mitigate biases and enhances the model’s ability to handle complex, nuanced scenarios, for example thinking about if a biotech company needs to generate synthesis customer reviews for a niche healthcare product not lanuched yet or a forensic psychiatry research group aims to generate crime vignettes to assess the public’s perception of crime types and punishment relevant to demographic groups. Thank you again to the Label Your Data team for highlighting this important aspect of AI development. #AI #GenAI #SyntheticData #LLM #DataValidation #HITL #ResponsibleAI

23

Quentin H. and Yanwei (Wayne) Zhang on the Faire Data team recently did some great work fine-tuning Llama3 model to enhance search relevance. Here are some key insights from the work: • While prompt engineering is valuable, LLM fine-tuning is essential for a domain specific task like understanding semantic search relevance. • Fine-tuned open-source LLMs like Llama3 can deliver impressive performance, scalability, and cost-efficiency compared to using proprietary models. • Effective application of a fine-tuned LLM demands a well-defined problem, robust, high-quality labeled data, and ongoing model refinement. Ground-truth labeled data is crucial for maximizing model performance. • Fine-tuned Llama3-8b achieves performance on par with the larger Llama2–13b model. Read the blog post to dive deeper into these findings! https://lnkd.in/ecP_3E7S We are also hiring (https://lnkd.in/dHfRZcPi) #LLM #AI #Finetuning #LLAMA3 #SearchRelevance #Hiring

93

3 Comments

Ensemble of smaller LLMs (PoLL) is less biased, faster, 7x cheaper when evaluating LLMs performance. Works great on QA & Arena-hard evals arxiv.org/abs/2404.18796

9

📊 The Power of High-Quality, Diverse, Real-World Data Fine-Tuning LLMs 🌍 When it comes to training Large Language Models (LLMs), the mantra isn’t just “more data”—it’s better data. While having more data can be beneficial, it’s the quality, diversity, and real-world relevance of the data that truly drive impactful results. Here’s why: 1️⃣ Higher Quality: clean, well-curated data improves model accuracy and reduces noise, making the model more reliable and stable. Poor-quality data often leads to inconsistent responses and increased hallucinations. Unbiased labeling consistency is key. 2️⃣ Diversity: it ensures the model can generalize across different contexts and user scenarios. This makes the model more robust, safe and inclusive, which is especially important in NLP for avoiding bias and ensuring representation. 3️⃣ Real-World Datasets: training on real datasets helps models perform better in real-world applications, as it learns from actual patterns and usage scenarios, making the model more practical and effective. For LLMs, there’s a general playbook to prepare data effectively: (1) Collect Instruction-Response Pairs: gather examples of how tasks should be answered, covering various domains and complexity levels. (2) Concatenate Pairs: organize the data into structured sequences, allowing the model to learn from end-to-end interactions. (3) Tokenize: process the data into tokens, using padding and/ or truncation as needed to maintain uniform length. I particularly love 🤗 transformers library's AutoTokenizer to identify which tokenizer to use on every model. (4) Split into Train/Dev/Test Sets: partition your data into training, validation, and testing sets to ensure proper model evaluation and tuning. Ultimately, data quality prevails over quantity, specially as we live in the LLMs era when models have been pre-trained with almost all the public data available in the 🌎 . A well-prepared dataset tailored to your application will make all the difference in the performance and reliability of your model. #AI #MachineLearning #DataQuality #LLM #NLP #ModelTraining #DataPreparation

5

Myths about Large Language Models (LLMs) like #Chatgpt #Gemini #llama and others - LLMs can understand like humans: LLMs work on pattern matching using algorithms. LLMs cannot understand the questions as humans do and so the response might not be always 100% as expected. - Accuracy of LLMs:While models try for accuracy, the information given might be incorrect or misleading. Model does not verify facts of the response - More data will improve response of LLMs:While more data can improve quality to some extent, fine tuning, transfer learning, tunning some parameters, modifying architecture of data flow, etc. can improve performance of LLMs. - LLMs can be creative like humans: LLMs can generate text, images or videos. While LLMs can augment human creativity but it cannot replace complexity of human creativity. - LLMs are invulnerable to errors or manipulation: LLMs can make mistakes and can be manipulated with adverse inputs to generate misleading information. - LLMs will surpass human intelligence: Artificial general intelligence (AGI) is still far off from reality and hence LLMs are far from achieving human-like intelligence. * views expressed are personal

42

3 Comments