# [107th TrustML Young Scientist Seminar] Talk by Prof. Mengyue Yang (University of Bristol) "Grounded LLM Reasoning: From Causal Reasoning to World Models"

> TrustML seminar on grounding LLM reasoning with causality, from chain-of-thought evaluation to world models and causality-seeking agents.

- When: Fri, November 13, 2026 13:30–14:30 JST
- Where: Meeting Room C, RIKEN Nihonbashi Office (in-person limited to AIP researchers) and online · Hybrid
- Region: Kanto (Tokyo)
- Organizer: RIKEN Center for Advanced Intelligence Project
- Language: EN
- Source: Doorkeeper — https://c5dc59ed978213830355fc8978.doorkeeper.jp/events/200397
- Page: https://japantech.info/events/doorkeeper-200397/

## Summary

Prof. Mengyue Yang of the University of Bristol talks about how causality can ground the reasoning of large language models. She introduces causal sufficiency and necessity as criteria for evaluating chain-of-thought reasoning.

The talk also covers the limits of outcome-based reinforcement learning, learning from natural-language feedback, and world models that support intervention, counterfactual reasoning and planning, including recent work on causality-seeking agents.

The session is hybrid, with online access and a room at the RIKEN Nihonbashi Office. In-person attendance is limited to AIP researchers.

## About the community

The TrustML Young Scientist Seminar is a numbered research talk series hosted by RIKEN AIP, featuring early-career researchers working on trustworthy machine learning.

#llm #causal-reasoning #world-models #reinforcement-learning #trustworthy-ml #seminar