复核引用
复核引用
对照源文档检查引用，抓出错误或幻觉出来的引用。一个 Choice 问题就能判断引文所在的上下文是否支撑该论断。
LLM 回答一个问题，并附上引用：每一条论断配一段源文档中的章节，以及它所依据的引文。其中有些引用是错的，甚至是幻觉出来的：引文可能压根不在文档里；也可能在文档里一字不差地存在，但它所在的上下文恰恰说的是相反的意思。
人工核对一条很慢：先找到文档，再在里面找到引文，然后还要读足够多的上下文，才能判断它是否支撑该论断。
要自动化这项检查，我们先用普通的字符串匹配找出缺失的引文，再用一个 Choice 问题，去读每条留下来的引文所在的上下文，判断它是否支撑该论断。
%%{init: {"flowchart": {"wrappingWidth": 330}}}%%
flowchart LR
cite["source document + citation"]
match{"is the quote<br/>in the source?"}
fab["mark <b>fabricated</b>"]
subgraph request[" "]
q["Choice — how does the<br/>section relate to the claim?<br/>supports → mark <b>verified</b><br/>contradicts → mark <b>contradicted</b><br/>says nothing → mark <b>unsupported</b>"]
end
gate{"confidence<br/>≥ 0.8?"}
stand["let the verdict stand"]
review["a human confirms it"]
cite --> match
%% the two edges that reach the call come first, so they stay adjacent; the
%% string match's own verdict is declared last and lands below them
match -- "found" --> request
match -- "no quote" --> request
match -- "not found" --> fab
request --> gate
gate --> stand
gate --> review下面，某 LLM 关于 RFC 7519（JSON Web Token）的回答里有 8 条引用，全都走一遍这项检查。其中 4 条准确的在置信度 0.93 及以上返回 verified。我们埋下的 4 处错误也全部被抓了出来：一条捏造的引文、一条被否定的论断，以及两条不受支撑、需转人工处理的引用。
你要在这里构建的函数 check_citation()，接收一份源文档和一条引用，返回四种判定之一：verified、unsupported、contradicted 或 fabricated。它还会返回一个置信度，用来标出哪些该让人看一眼。
准备工作
pip install ipython 'cooksafe>=0.2.0,<0.3.0'然后设置 TYPESAFE_API_KEY。每次 API 调用都会缓存进 json_cache.json，这个文件随 cookbook 一起提供，所以重跑时回放的是已发布的数字，而不会真的调用 API。把该文件删掉，就能全部真实调用。
下面的数字来自 2026-08-16 的 jev-1.12。
import json
import os
import re
from pathlib import Path
from time import perf_counter
from cooksafe import JsonCache, make_playground_link
from IPython.display import Markdown, display
from typesafe_sdk import Choice, TypeSafeClient
TYPESAFE_MODEL = "jev-1.12"
AUTO_ACCEPT = 0.8 # start high for more human review as you build trust in the model
client = TypeSafeClient(
api_key=os.environ.get("TYPESAFE_API_KEY", "cache-only"),
base_url=os.environ.get("TYPESAFE_ENDPOINT"),
timeout=120.0,
)
json_cache = JsonCache(Path("json_cache.json"))载入源文档和引用
源文档是 RFC 7519（JSON Web Token），从 rfc-editor.org 抓取，并作为 rfc7519.txt 提交在与本 cookbook 同级的位置。下面的代码会剥掉页眉页脚，再把文本切成带编号的章节。
citations.json 里的 8 条引用是某 LLM 依据该 RFC 写的。其中 4 条准确；另外 4 条我们做了改动，好让它们通不过检查。
def load_source() -> str:
"""RFC 7519 verbatim, minus the page headers and footers that interrupt its paragraphs."""
lines = []
for line in Path("rfc7519.txt").read_text().splitlines():
bare = line.lstrip("\f")
if re.match(r"Jones, et al\.\s.*\[Page \d+\]$", bare):
continue
if re.match(r"RFC 7519\s+JSON Web Token \(JWT\)\s+May 2015$", bare):
continue
lines.append(bare)
return re.sub(r"\n{3,}", "\n\n", "\n".join(lines))
def split_sections(source: str) -> dict[str, str]:
"""Map each numbered section ("4.1.3") to its text, split on the RFC's header lines."""
boundary = re.compile(r"(?m)^(?:(\d+(?:\.\d+)*)\. .+|Appendix [A-Z]\..*)$")
marks = list(boundary.finditer(source))
sections = {}
for mark, nxt in zip(marks, marks[1:] + [None]):
if mark.group(1) is None: # an appendix header only terminates the section before it
continue
sections[mark.group(1)] = source[mark.start() : nxt.start() if nxt else len(source)].strip()
return sections
SOURCE = load_source()
SECTIONS = split_sections(SOURCE)
CITATIONS = json.loads(Path("citations.json").read_text())
print(f"{len(SOURCE):,} characters, {len(SECTIONS)} numbered sections, {len(CITATIONS)} citations")
print("\nA citation with a quote:")
print(json.dumps(CITATIONS[1], indent=2))
print("\nA claim-only citation:")
print(json.dumps(next(c for c in CITATIONS if c["quote"] is None), indent=2))58,365 characters, 45 numbered sections, 8 citations
A citation with a quote:
{
"id": "aud_reject",
"claim": "If a validator does not find itself in a token's audience list, it has to reject the token.",
"quote": "If the principal processing the claim does not identify itself with a value in the \"aud\" claim when this claim is present, then the JWT MUST be rejected.",
"section": "4.1.3"
}
A claim-only citation:
{
"id": "iat_future",
"claim": "The \"iat\" claim requires validators to reject tokens whose issue time is in the future.",
"quote": null,
"section": "4.1.6"
}在源文档里找每条引文
源文档里找不到的引文，就是捏造的，找出这一点根本不需要模型。先把空白和弯引号归一化，这样引文即使跨了 RFC 的换行也能匹配上，再把它当作子串去查找。匹配成功还会顺带告诉你引文来自哪一节，而这一节就是下一步交给模型读的文本。
一条引用也可能只点名了某一节，却没有引用其中任何内容。这种情况没有东西可匹配，那就直接取它点名的那一节，去找模型。
def normalize(text: str) -> str:
"""Collapse whitespace and fold curly quotes, so a quote matches across line wraps."""
table = str.maketrans({"“": '"', "”": '"', "‘": "'", "’": "'"})
return re.sub(r"\s+", " ", text.translate(table)).strip()
def find_quote(sections: dict[str, str], quote: str) -> str | None:
"""The number of the section that contains the quote verbatim, or None."""
needle = normalize(quote)
for number in sorted(sections, key=lambda n: [int(p) for p in n.split(".")]):
if needle in normalize(sections[number]):
return number
return None
def locate(sections: dict[str, str], citation: dict) -> tuple[str, str | None]:
"""Step 1 for one citation: a status, plus the section step 2 will read."""
if citation["quote"] is None:
return "section-only", sections[citation["section"]]
number = find_quote(sections, citation["quote"])
if number is None:
return "missing", None
return "found", sections[number]
for citation in CITATIONS:
status, section = locate(SECTIONS, citation)
where = f"section of {len(section):,} chars" if section else "not in the source"
print(f"{citation['id']:<18}{status:<14}{where}")epoch_seconds found section of 3,122 chars
aud_reject found section of 761 chars
sig_reporting missing not in the source
clock_skew found section of 529 chars
exp_required found section of 529 chars
pii_encryption found section of 1,653 chars
iat_future section-only section of 270 chars
duplicate_names found section of 918 chars验证源文档是否支撑该论断
走到这一步还带着引文的引用，都和源文档一字不差。但这还不够：引文可能准确无误，而架在它上面的论断依然可能是错的。要判断这一点，就得看引文所在的上下文，也就是第 1 步找到的那一节。
对每条留下来的引用问一个 Choice 问题，覆盖一节内容与论断之间可能有的三种关系。概率最高的那个选项就是判定结果，而 AUTO_ACCEPT（上面代码里是 0.8）决定接下来怎么处理它：
- 置信度不低于 0.8：判定直接生效；
- 低于 0.8：先由人确认这个判定，之后才会有人据此行动。
一开始把阈值设高些，等你看到模型在你自己的文档上表现如何，再往下调。
QUESTIONS = {
"relation": Choice(
instructions="How does the section relate to the claim?",
criteria={
"supports": "The section states the claim or directly implies that it is true",
"contradicts": "The section states the opposite of the claim or implies it is false",
"says_nothing": "The section does not address what the claim asserts, either way",
},
),
}
RELATION_TO_VERDICT = {
"supports": "verified",
"contradicts": "contradicted",
"says_nothing": "unsupported",
}
@json_cache
def ask(claim: str, section: str) -> dict:
started = perf_counter()
response = client.system_one(
state={"claim": claim, "section": section},
questions=QUESTIONS,
model=TYPESAFE_MODEL,
)
answer = response.answers["relation"]
return {
"choice": answer.choice,
"probabilities": answer.probabilities,
"confidence": answer.confidence,
"seconds": round(perf_counter() - started, 2),
"input_tokens": response.usage.input_tokens or 0,
"output_tokens": response.usage.output_tokens or 0,
}
def verdict(status: str, answer: dict | None) -> dict:
"""Fold step 1 and step 2 into one of the four labels, plus an auto-or-review flag."""
if status == "missing":
# confidence None: no model was called, so there is no model confidence to report
return {"verdict": "fabricated", "confidence": None, "auto": True}
return {
"verdict": RELATION_TO_VERDICT[answer["choice"]],
"confidence": answer["confidence"],
"auto": answer["confidence"] >= AUTO_ACCEPT,
}
def check_citation(sections: dict[str, str], citation: dict) -> dict:
status, section = locate(sections, citation)
answer = ask(citation["claim"], section) if section is not None else None
return {"id": citation["id"], "status": status, "answer": answer, **verdict(status, answer)}逐条检查所有引用
8 条引用全部走同一套检查：
print(f"{'citation':<18}{'quote':<14}{'relation':<14}{'conf':>6} {'verdict':<13}{'action':>7}")
for citation in CITATIONS:
result = check_citation(SECTIONS, citation)
answer = result["answer"]
relation = answer["choice"] if answer else "-"
conf = f"{answer['confidence']:.2f}" if answer else "-"
action = "auto" if result["auto"] else "review"
print(
f"{result['id']:<18}{result['status']:<14}{relation:<14}{conf:>6}"
f" {result['verdict']:<13}{action:>7}"
)citation quote relation conf verdict action
epoch_seconds found supports 0.93 verified auto
aud_reject found supports 0.95 verified auto
sig_reporting missing - - fabricated auto
clock_skew found supports 0.99 verified auto
exp_required found contradicts 0.99 contradicted auto
pii_encryption found says_nothing 0.27 unsupported review
iat_future section-only says_nothing 0.56 unsupported review
duplicate_names found supports 0.99 verified auto4 条引用返回 verified，1 条 fabricated，1 条 contradicted，还有 2 条 unsupported。
epoch_seconds、aud_reject、clock_skew和duplicate_names就是那 4 条准确的引用。它们都以 0.93 或更高的置信度返回verified，远高于AUTO_ACCEPT。sig_reporting根本没送到模型那里。它的引文不在 RFC 里，所以光靠字符串匹配就判为fabricated。exp_required一字不差地引用了 4.1.4 节，而同一节写着 “Use of this claim is OPTIONAL”，所以它是contradicted，置信度 0.99。pii_encryption和iat_future分别以 0.27 和 0.56 返回unsupported，都在阈值之下，于是都转给了人。pii_encryption说明了为什么光有字符串匹配不够：它的引文在源文档里一字不差，而它来自的那一节对这条论断只字未提。
想把它用到你自己的数据上，就替换 rfc7519.txt 和 citations.json。load_source() 和 split_sections() 是按 RFC 的版式写的，换一种形态的文档就需要自己写解析。
归一化之后的字符串匹配是精确匹配：被截断或稍微改过措辞的引文，都会返回 fabricated。生产系统如果容忍不严谨的引用方式，就得改用模糊匹配。
在 Playground 里打开
这个链接里装着某条引用的论断和章节，再加上那个问题。打开它，就能在浏览器里实时跑同样的调用。
example = next(c for c in CITATIONS if c["id"] == "exp_required")
_, example_section = locate(SECTIONS, example)
playground_link = make_playground_link(
{"claim": example["claim"], "section": example_section}, QUESTIONS, models=[TYPESAFE_MODEL]
)
display(Markdown(f"🔗 [Open one citation's claim + section in the TypeSafe playground]({playground_link})"))