AXRP - the AI X-risk Research Podcast

38.0 - Zhijing Jin on LLMs, Causality, and Multi-Agent Systems

Nov 14, 2024

Zhijing Jin, an Assistant Professor at the University of Toronto, specializes in the intersection of natural language processing and causal inference. In this engaging discussion, she investigates whether language models truly understand causality or just recognize correlations. Zhijing explores the limitations of these models in reasoning, their application in multi-agent systems, and the complexities of digital societies. She poses intriguing questions about AI governance and cooperation, emphasizing the delicate balance required for sustainable agent interactions.

22:42

Creator website

Episode guests

Zhijing Jin

AI Summary

AI Chapters

Episode notes

Podcast summary created with Snipd AI

Quick takeaways

The intersection of language processing and causal inference in AI research is crucial for aligning AI behaviors with human values.

Exploring multi-agent systems highlights challenges in cooperation among AI agents, revealing potential risks when managing shared resources.

Deep dives

Intersection of Natural Language Processing and Causal Inference

The discussion highlights a unique intersection between natural language processing (NLP) and causal inference in AI research. The speaker expresses a deep interest in semantics, emphasizing how understanding the meaning of language can connect to broader AI capabilities. Initially viewed as niche, this area has grown in relevance as the complexities of AI behavior have become apparent, prompting researchers to consider alignment with human values. The speaker credits colleagues and institutions for fostering their interest in alignment and causal methodologies, showcasing a collaborative effort in tackling these advanced topics.

Intro

2min

Navigating Causality in AI and Language Models

13min

Exploring the Limitations of Language Models in Reasoning Tasks

2min

Exploring Multi-Agent Systems and Digital Societal Dynamics

2min

Exploring Multi-Agent Systems and the Tragedy of the Commons

4min

Do language models understand the causal structure of the world, or do they merely note correlations? And what happens when you build a big AI society out of them? In this brief episode, recorded at the Bay Area Alignment Workshop, I chat with Zhijing Jin about her research on these questions.

Patreon: https://www.patreon.com/axrpodcast

Ko-fi: https://ko-fi.com/axrpodcast

The transcript: https://axrp.net/episode/2024/11/14/episode-38_0-zhijing-jin-llms-causality-multi-agent-systems.html

FAR.AI: https://far.ai/

FAR.AI on X (aka Twitter): https://x.com/farairesearch

FAR.AI on YouTube: https://www.youtube.com/@FARAIResearch

The Alignment Workshop: https://www.alignment-workshop.com/

Topics we discuss, and timestamps:

00:35 - How the Alignment Workshop is

00:47 - How Zhijing got interested in causality and natural language processing

03:14 - Causality and alignment

06:21 - Causality without randomness