Papers by Takehiro Takayanagi
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. |