Idea Ripper // ArchiveCards: 1555 [Live] | Updated: 2026-10-14
Card #c23IR // #c23Synthesis

Two things distinguish it from a generic one, and both are controls rather than models. The availability filter D ≤ t admits only documents that existed at the decision time t , which is what stops a backtest from reading tomorrow’s filing. The claim-level verifier checks each material claim A i against its retrieved evidence bundle E i before the answer is released, which is what stops a fluent answer from being an unsupported one.

— In our words · Source: Large Language Models in Finance (Miquel Noguer i Alonso)

[Use when]

When evaluating a RAG build, check the two controls first: does retrieval enforce the decision-time cutoff, and does anything verify claims against evidence before release?

[Why it matters]

A RAG system fails in exactly two places that matter: letting the future leak in (the availability filter) and letting fluent prose out without evidence (the claim verifier). Everything else — embeddings, chunking, reranking — is optimization inside those two guardrails.

Related principles

#c19A valid evaluation must freeze not only the price history but also the prompt, retrieval store, tools, memory, model version, and…Use when reviewing or designing a backtest of an LLM-based forecasting or trading system. #c22a financial fine-tuning experiment is not defined by a model name and a training set. It is defined by a decision date, a permissible…Before greenlighting any fine-tuning run, demand the contract: what data as of when, what loss, what…

More from Large Language Models in Finance

#c13Prediction and agency should not be conflated. A credit model can estimate the probability that a borrower breaches a covenant. An agentic…Use when a team proposes a stronger model as the fix for an agent that lacks memory, permissioning, or an… #c14The technically and institutionally mature objective is bounded autonomy : the agent can plan, retrieve, calculate, and propose actions…Use when deciding what an AI agent is permitted to do in production: which actions stay read-only, which need… #c15This principle prevents a common category error. A model that says it will respect a mandate has not yet respected the mandate. A model…Use when a vendor demo, benchmark score, or red-team chat log is being offered as proof that an agent is safe…