Trendoday

LLMs Don't Know What They Know: Benchmarking Temporal Self-Knowledge for Financial Backtesting

Financial backtests of large language models (LLMs) are meaningful only if the model did not already know the outcomes it is asked to predict. Practitioners guard against this by trusting a vendor's s

  • Upvotes16
–Rank now
#8Peak rank
2Days on list
247Score · 7d
Nov 9, 2026First seen
Rank · 7 days

About this paper

A benchmark of dated U.S. financial facts shows that large language models often understate their knowledge and that common safeguards cannot reliably certify that historical backtests are free of information leakage.

Financial backtests of large language models (LLMs) are meaningful only if the model did not already know the outcomes it is asked to predict. Practitioners guard against this by trusting a vendor's stated knowledge cutoff, by asking the model what it knows, or by instructing it to answer as of a past date. To verify whether any of these safeguards can be trusted, we introduce FinDendro, a benchmark of 2,226 dated U.S. facts from 1999 to 2026, covering monthly macroeconomic series, month-end stock prices and Federal Reserve decisions. Each fact yields four prompts: a value question, Recall and Predict questions that pair each candidate value with a claim of knowing or guessing without a…

large language models (LLMs)knowledge cutofffrontier modelsself-reported knowledgemodel training windowtemporal knowledge boundariesleak-free backtestsFinDendro benchmark
Upvotes
16
Authors
15
Published
Nov 4, 2026

Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.

Trending history

LLMs Don't Know What They Know: Benchmarking Temporal Self-Knowledge for Financial Backtesting was first seen on Hugging Face · Daily papers on Nov 9, 2026. Since then it has appeared in 11 checks on 2 different days. Its best position was #8 of 30, reached on Nov 10, 05:28 UTC. It dropped off the list after Nov 10, 13:28 UTC.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 17:2822:2803:2808:2813:28 Nov 9, 17:28 UTC · #13Nov 9, 19:28 UTC · #12Nov 9, 21:28 UTC · #15Nov 9, 23:28 UTC · #12Nov 10, 01:28 UTC · #10Nov 10, 03:28 UTC · #9Nov 10, 05:28 UTC · #8Nov 10, 07:28 UTC · #10Nov 10, 09:28 UTC · #9Nov 10, 11:28 UTC · #8Nov 10, 13:28 UTC · #10

Last 14 days

Best rank per day (UTC).

Nov 3today

Metric history

Platform metric as reported by Hugging Face.

0112132 17:2822:2803:2808:2813:28 Nov 9, 17:28 UTC · 16Nov 9, 19:28 UTC · 18Nov 9, 21:28 UTC · 18Nov 9, 23:28 UTC · 23Nov 10, 01:28 UTC · 24Nov 10, 03:28 UTC · 25Nov 10, 05:28 UTC · 27Nov 10, 07:28 UTC · 30Nov 10, 09:28 UTC · 31Nov 10, 11:28 UTC · 32Nov 10, 13:28 UTC · 32

Questions

Is LLMs Don't Know What They Know: Benchmarking Temporal Self-Knowledge for Financial Backtesting trending on HF Daily Papers right now?

Not at the moment. It was last on the list on Nov 10, 13:28 UTC, after 2 days of trending.

What is the highest rank LLMs Don't Know What They Know: Benchmarking Temporal Self-Knowledge for Financial Backtesting reached?

#8 on Hugging Face · Daily papers, on Nov 10, 05:28 UTC. Trendoday checks this list every 120 minutes.

How long has LLMs Don't Know What They Know: Benchmarking Temporal Self-Knowledge for Financial Backtesting been trending?

It was first seen on Nov 9, 2026 and has been on the list on 2 days (11 checks) since.