TSAG lets LLMs use external tools for financial time series analysis, with a new benchmark showing capable agents achieve near-perfect tool accuracy and minimal hallucination.
Proceedings of the Royal Society of London , volume =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Lexical frequency is a stronger predictor of metaphor novelty than LM surprisal, with the surprisal-novelty link peaking early in training before declining as surprisal becomes more aligned with frequency.
citing papers explorer
-
Time Series Augmented Generation for Financial Applications
TSAG lets LLMs use external tools for financial time series analysis, with a new benchmark showing capable agents achieve near-perfect tool accuracy and minimal hallucination.
-
The Frequency Confound in Language-Model Surprisal and Metaphor Novelty
Lexical frequency is a stronger predictor of metaphor novelty than LM surprisal, with the surprisal-novelty link peaking early in training before declining as surprisal becomes more aligned with frequency.