In 2024, ChatGPT marked its one-year anniversary, highlighting significant advancements in large language models (LLMs) and their applications. The post summarizes key developments, including tool use and reasoning. It emphasizes the emerging concept of LLMs creating and utilizing their own tools, as well as the vibrant research landscape that explores the capabilities and limitations of LLMs in the context of reasoning and problem-solving. Key trends and predictions for the future of LLM reasoning are outlined, alongside references to additional relevant blog posts.
“`html
Solving Reasoning Problems with LLMs in 2023
Introduction
It’s the beginning of 2024 and ChatGPT just celebrated its one-year birthday. One year is a super long time for the community of large language models, where a myriad of interesting works have taken place. Let’s revisit the progress and discuss topics for the coming year.
This post was co-authored with Michael Galkin (Intel AI Lab), Abulhair Saparov (New York University), Shibo Hao (UC San Diego) and Yihong Chen (University College London & Meta AI Research). Many insights in this post were formed during the fruitful discussions with Emily Xue (Google), Hanjun Dai (Google DeepMind) and Bruno Ribeiro (Purdue University).
Tool Use
In-context learning enables using more tools
One limitation of LLM tool usage is the necessity of sufficient human annotations. Whenever we want to teach an LLM to use a tool, we need enough annotated tool calls to finetune the LLM. In the Toolformer paper by Meta, the authors use in-context learning to create a model that annotates tool calls for the input query. This model is then used to generate tool calls on an unlabeled dataset. While the generations may be far from perfect, incorrect calls can be filtered by executing the tools and filtering the outputs based on the ground truth answer. The correct calls are collected and used to finetune the model. In this way, we can teach Transformers to use any tool based on a conventional dataset and merely 5 additional annotations — easy work for any engineer.
What needs to be solved in 2024?
2023 has been an exciting year for tool use and reasoning, and we expect the new year to be more exciting. Let’s wrap up this post with predictions from the authors.
Zhaocheng Zhu:
1️⃣ Reasoning with LLMs still requires ad-hoc engineering efforts for each specific task. By contrast, once humans acquire the skills for a task, they can quickly adapt the skills to similar tasks with very few or even no samples (e.g. from chess to poker). If we can create LLM solutions that generalize across tasks, it will save a lot of engineering efforts and boost the performance in low-resource domains.
Meme Time
Following the tradition of Michael Galkin, no blog post is truly complete without a meme. DALL·E 3 is almost a meme wizard if it can spell words correctly. Guess what prompts are used for each panel?
Read More
If this blog left you wanting to learn more about LLM reasoning, take a look at the following awesome blog posts.
Towards Complex Reasoning: the Polaris of Large Language Models by Yao Fu.
LLM Powered Autonomous Agents by Lilian Weng.
Solving Reasoning Problems with LLMs in 2023 was originally published in Towards Data Science on Medium, where people are continuing the conversation by highlighting and responding to this story.
Spotlight on a Practical AI Solution:
Consider the AI Sales Bot from itinai.com/aisalesbot designed to automate customer engagement 24/7 and manage interactions across all customer journey stages.
Discover how AI can redefine your sales processes and customer engagement. Explore solutions at itinai.com.
“`
