# Opinion: Using LLMs for confidence scores is unreliable

Digest AI · Agents & Tools · published 2026-10-21T04:27:51Z

Canonical: https://digestai.news/story/opinion-using-llms-for-confidence-scores-is-unreliable

## Summary

The author argues that asking a large language model (LLM) for a probability or confidence number is not trustworthy. Because an LLM generates each token as a continuation of the preceding text, a reported figure such as “0.85” is simply a plausible next token, not a measurement derived from evidence. The post notes that the same question can produce different scores on repeated runs, that re‑phrasing the query changes the number, and that the surrounding wording heavily influences the output, all of which break the requirements for a calibrated confidence estimate.

Instead, the author proposes building an external rule that maps observable signals—such as the number of retrieved documents, agreement between multiple replies, or historical accuracy—to a confidence value. By recording every answer and its outcome, the rule can be calibrated over time, ensuring that the same information always yields the same score and that the score reflects real performance. The piece concludes that most agents that currently expose LLM‑generated confidence numbers lack the necessary validation and should adopt a data‑driven scoring system.

## Key points

- LLM confidence numbers are just text continuations, not calibrated measurements.
- Repeated or re‑phrased queries often produce different confidence scores.
- A rule‑based system using observable evidence can provide calibrated confidence.

## Why it matters

Unreliable confidence scores can mislead users of AI agents, affecting decisions in support, automation, and safety-critical applications.

## Sources

1. [Using LLM for confidence scoring is a bad idea](https://rumple.github.io/blog/2026/10/20/asking-llm-for-confidence.html) (rumple.github.io, 2026-10-21)

## Cite

Digest AI, "Opinion: Using LLMs for confidence scores is unreliable", 21 October 2026, https://digestai.news/story/opinion-using-llms-for-confidence-scores-is-unreliable

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/opinion-using-llms-for-confidence-scores-is-unreliable.json