Papers by Takehiro Takayanagi

2 papers
From Heard to Lived Opinions: Simulating Opinion Dynamics with Grounded LLM Agents in Economic Environments (2026.findings-acl)

Copied to clipboard

Challenge: Existing studies on opinion dynamics (OD) focus primarily on opinion exchange, with opinion change driven by linguistic interaction.
Approach: They propose a OD simulation framework that grounds LLM-based agents in an economic environment and allows them to act and receive environmental feedback.
Outcome: The proposed framework shows that LLM-based agents can act and receive environmental feedback at both individual and population levels while generating larger distributional shifts.
Can GPT-4 Sway Experts’ Investment Decisions? (2025.findings-naacl)

Copied to clipboard

Challenge: In the post-Turing era, evaluating large language models involves assessing generated text based on readers’ decisions rather than merely its indistinguishability from human-produced content.
Approach: They propose to use GPT-4 to evaluate generated text from the aspects of grammar, convincingness, logical coherence, and usefulness to determine its validity.
Outcome: The proposed model can generate persuasive analyses affecting the decisions of amateurs and experts.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations