ML-QuantSubscribe

RePEcML & AI Methods

The market's mirror: Revealing investor disagreement with LLMS

Using LLM personas, disagreement over news headlines predicts trading volume, with income and education disagreement most predictive and fundamentals generating least disagreement.

Read the paper PDF
View as MarkdownOpen in ClaudeOpen in ChatGPTOpen in PerplexitySite index for AI (llms.txt)

Featured in No. 138 on 6 Nov 2026 · 4 days after release

LLM Persona Responses Closely Match Human Responses Out of Sample
Figure 6: LLM Persona Responses Closely Match Human Responses Out of Sample. This figure reports a synthetic replication of human survey responses using Llama persona responses. Following Iliewa, Kempf, and Spalt (2024), which became public in the post-training window, we assign the LLM personas th…
Released
2 Nov 2026
First featured
No. 138 · 6 Nov 2026
Published in
Not yet, as far as Semantic Scholar knows
Fanfare
3 of 5
Identifier
RePEc:zbw:cbscwp:344253
Authors
Vineet Bhagwat et al.

Citations and venue from Semantic Scholar (ODC-BY), refreshed weekly. Summary: Quant Letter (CC BY 4.0).

    Type to search. Try rough volatility, LLM agents or FinGPT.

    ↑↓ move↵ openesc closeFull search page