Why Do Researchers Care About Small Language Models?
Plus, more links to make you a little bit smarter today.
Making a new video every week until I make $5 million - Week 9
Why Apache Kafka is the Best Tool for Data Streaming
In continuing our series on data engineering, the next rational step felt obvious: Apache Kafka. Whether it’s logging events, collecting metrics, or enabling real-time analytics, Apache Kafka has become a go-to solution for building dependable event streaming systems.
Why I Blog and How I Automate it
I’m interested in consuming information in order to create new information (one of my motivations for pursuing a Ph.D.). I generally read articles/papers or watch videos, and then create papers/articles/code and have discussions as a result. While creating blog posts could be considered ‘giving back’, I think most of the benefit is personal because it (if well-written) forces me to make sense of and distill the ideas therein sufficiently such that someone else can understand me, which requires confronting various weaknesses and problems with the idea and improving on them (This is also one reason why I believe feedback systems are important).
Why Do Researchers Care About Small Language Models?
Larger models can pull off a wider variety of feats, but the reduced footprint of smaller models makes them attractive tools.
Why do financial prices exhibit Brownian motion despite predictable order flow?
In financial market microstructure, there are two enigmatic empirical laws: (i) the market-order flow has predictable persistence due to metaorder splitters by institutional investors, well formulated as the Lillo-Mike-Farmer model.
When to Accept Automated Predictions and When to Defer to Human Judgment?
Ensuring the reliability and safety of automated decision-making is crucial. It is well-known that data distribution shifts in machine learning can produce unreliable outcomes. This paper proposes a new approach for measuring the reliability of predictions under distribution shifts. We analyze how the outputs of a trained neural network change using clustering to measure distances between outputs and class centroids. We propose this distance as a metric to evaluate the confidence of predictions under distribution shifts. We assign each prediction to a cluster with centroid representing the mean softmax output for all correct predictions of a given class. We then define a safety threshold for a class as the smallest distance from an incorrect prediction to the given class centroid. We evaluate the approach on the MNIST and CIFAR-10 datasets using a Convolutional Neural Network and a Vision Transformer, respectively. The results show that our approach is consistent across these data sets and network models, and indicate that the proposed metric can offer an efficient way of determining when automated predictions are acceptable and when they should be deferred to human operators given a distribution shift.
When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments
Can AI Agents simulate real-world trading environments to investigate the impact of external factors on stock trading activities (e.g., macroeconomics, policy changes, company fundamentals, and global events)? These factors, which frequently influence trading behaviors, are critical elements in the quest for maximizing investors' profits. Our work attempts to solve this problem through large language model based agents. We have developed a multi-agent AI system called StockAgent, driven by LLMs, designed to simulate investors' trading behaviors in response to the real stock market. The StockAgent allows users to evaluate the impact of different external factors on investor trading and to analyze trading behavior and profitability effects. Additionally, StockAgent avoids the test set leakage issue present in existing trading simulation systems based on AI Agents. Specifically, it prevents the model from leveraging prior knowledge it may have acquired related to the test data. We evaluate different LLMs under the framework of StockAgent in a stock trading environment that closely resembles real-world conditions. The experimental results demonstrate the impact of key external factors on stock market trading, including trading behavior and stock price fluctuation rules. This research explores the study of agents' free trading gaps in the context of no prior knowledge related to market data. The patterns identified through StockAgent simulations provide valuable insights for LLM-based investment advice and stock recommendation. The code is available at this https URL.