With the pace at which large language models continue to evolve, staying up-to-date with the field is a major challenge. We see new models, cutting-edge research, and LLM-based apps proliferate on a daily basis, and as a result, many practitioners are understandably concerned about falling behind or not using the latest and shiniest tools.
First, let’s all take a deep breath: when an entire ecosystem is moving rapidly in dozens of different directions, nobody can expect (or be expected) to know everything. We should also not forget that most of our peers are in a very similar situation, zooming in on the developments that are most essential to their work, while avoiding too much FOMO—or at least trying to.
If you’re still interested in learning about some of the biggest questions currently dominating conversations around LLMs, or are curious about the emerging themes machine learning professionals are exploring, we’re here to help. In this week’s Variable, we’re highlighting standout articles that dig deep into the current state of LLMs, both in terms of their underlying capabilities and practical real-world applications. Let’s dive in!
- Navigating the New Types of LLM Agents and Architectures.
In a lucid overview of recent work into LLM-based agents,
Aparna Dhinakaran
injects a healthy dose of clarity into this occasionally chaotic area: “How can teams navigate the new frameworks and new agent directions? What tools are available, and which should you use to build your next application?”
- Tackle Complex LLM Decision-Making with Language Agent Tree Search (LATS) & GPT-4o.
For his debut TDS article,
Ozgur Guler
presents a detailed introduction to the challenges LLMs face in decision-making tasks, and outlines a promising approach that combines the power of the GPT-4o model with Language Agent Tree Search (LATS), “a dynamic, tree-based search methodology” that can enhance the model’s reasoning abilities.
- From Text to Networks: The Revolutionary Impact of LLMs on Knowledge Graphs.
Large language models and knowledge graphs have progressed on parallel and mostly separate paths in recent years, but as
Lina Faik
points out in her new, step-by-step guide, the time has come to leverage their respective strengths simultaneously, leading to more accurate, consistent, and contextually relevant outcomes.
- No Baseline? No Benchmarks? No Biggie! An Experimental Approach to Agile Chatbot Development.
After the novelty and initial excitement of LLM-powered solutions wears off, product teams still face the challenges of keeping them working and delivering business value.
Katherine Munro
covered her approach to benchmarking and testing LLM products in a recent talk, which she’s now transformed into an accessible and actionable roadmap.
- Exploring the Strategic Capabilities of LLMs in a Risk Game Setting.
Hans Christian Ekne
’s recent deep dive also tackles the problem of evaluating LLMs, but from a different, more theoretical direction. It takes a close look at the different strategic behaviors that leading models (from Anthropic, OpenAI, and Meta) exhibit as they navigate the rules of classic board game Risk, discusses their shortcomings, and looks at the potential future of LLMs’ reasoning skills.
- How to Improve LLM Responses With Better Sampling Parameters.
We round out this week’s lineup with a hands-on, practical tutorial by
Dr.-Ing. Leon Eversberg
, who explains and visualizes the sampling strategies that define the output behavior of LLMs—and demonstrates how understanding these parameters better can help us improve the outputs that models generate.
The world of data science and machine learning is vast, and goes far beyond contemporary LLMs—which is why we encourage you to explore some of our other reading recommendations on other topics:
- If you’re a data scientist who occasionally struggles with breaking down an abstract business problem
“into smaller, clearly defined analyses,” don’t miss
Tessa Xie
’s valuable insights, based on her previous experience as a consultant.
- The groundbreaking BERT model might be turning 6 soon, but its impact remains relevant
to many ML practitioners today.
Daniel Warfield
’s definitive explainer invites us to explore its inner workings in great detail.
- Have we reached the point where one model can teach and train another (smaller) model
?
Laurin Heilmeyer
explores new horizons around this question and the potential benefits in this approach for smaller, resource-strapped organizations.
- Role switches are rarely easy; as
Claudia Ng
makes clear, though, there are steps you can take to make the journey smoother and faster, as she did in her recent transition from data analyst to data scientist
.
- New to the concept of continual learning? We encourage you to explore
Alicja Dobrzeniecka
’s article on multimodal vision-language models and the possibilities of applying CL
to the Contrastive Language-Image Pretraining (CLIP) model.
- Data professionals encounter graphs in their work all the time, but don’t often stop to think about what makes great ones stand out.
Melonie Richey, Ph.D.
fills in this gap in a clear and example-filled primer
.
Thank you for supporting the work of our authors! As we mentioned above, we love publishing articles from new authors, so if you’ve recently written an interesting project walkthrough, tutorial, or theoretical reflection on any of our core topics, don’t hesitate to share it with us
.
