Confidence indicator

신뢰도 표시

A small badge showing how confident the model is in an answer — high, medium, low.

Also known as: Certainty meterConfidence badge
···
html
<div class="wrap">
  <div class="row"><span class="q">2025년 3분기 실적 성장률은?</span></div>
  <div class="bubble">전년 동기 대비 약 12% 성장한 것으로 보고됐어요.</div>
  <div class="conf" id="conf" data-lv="high"><span class="dots"><i></i><i></i><i></i></span><span class="lbl">높은 신뢰도 — 공개 실적 발표 인용</span></div>
</div>
css
.wrap{width:min(300px,94%);display:grid;gap:8px}
.q{font-size:11px;color:var(--muted)}
.bubble{padding:9px 12px;border-radius:12px;border-bottom-left-radius:4px;background:var(--surface);border:1px solid var(--line);color:var(--fg);font-size:12px;line-height:1.55}
.conf{display:flex;align-items:center;gap:7px;font-size:10.5px;color:var(--muted)}
.dots{display:flex;gap:3px}
.dots i{width:6px;height:6px;border-radius:2px;background:var(--line)}
.conf[data-lv=high] .dots i{background:#0f9d78}
.conf[data-lv=medium] .dots i:nth-child(1),.conf[data-lv=medium] .dots i:nth-child(2){background:#f5a524}
.conf[data-lv=low] .dots i:nth-child(1){background:#e5484d}
js
const conf = document.getElementById('conf'), lbl = conf.querySelector('.lbl');
const states = [
  ['high', '높은 신뢰도 — 공개 실적 발표 인용'],
  ['medium', '보통 신뢰도 — 일부는 추정치예요'],
  ['low', '낮은 신뢰도 — 최신 자료가 부족해요'],
];
let i = 0;
setInterval(() => {
  i = (i + 1) % states.length;
  const [lv, text] = states[i];
  conf.dataset.lv = lv;
  lbl.textContent = text;
}, 1800);

Not every answer a model gives carries the same certainty. An answer directly quoting a source document and one guessed from a pattern with no grounding differ in reliability, yet both render as equally confident-sounding sentences on screen. This indicator makes that difference visible so a low-confidence answer isn't taken at face value.

A category like high/medium/low, or a short bar, is safer than a raw percentage ("87% confident") — a model's internal probability and its actual chance of being right are different things, and showing a number invites people to read it as precise statistics it isn't.

When confidence is low, don't stop at the badge — pairing it with why ("this topic has little recent information") or a next step (double-check, view sources) turns the indicator from a source of anxiety into something actually useful.

When to use

Use it in high-stakes domains — medical, legal, financial — or for answers grounded in retrieved documents. If the confidence estimate itself is unreliable (models are often bad at knowing what they don't know), it's better left out than bolted on.

Open as page ↗

Suggest an entry

Tell us about a term, effect or component that’s missing. We read every suggestion.