De Jure: Iterative LLM Self-Refinement for Structured Extraction of Regulatory Rules

De Jure: Iterative LLM Self-Refinement for Structured Extraction of Regulatory Rules | Signal Canvas | ScienceToStartup

Page Freshness

Signal Canvas proof surface

Canonical route: /signal-canvas/de-jure-iterative-llm-self-refinement-for-structured-extraction-of-regulatory-rules

stale

Proof freshness: stale
Proof status: unverified
Display score: 7/10
Last proof check: 2026-04-03
Score updated: 2026-04-03
Score fresh until: 2026-05-03
References: 0
Source count: 0
Coverage: 33%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

Agent Handoff

Canonical ID de-jure-iterative-llm-self-refinement-for-structured-extraction-of-regulatory-rules | Route /signal-canvas/de-jure-iterative-llm-self-refinement-for-structured-extraction-of-regulatory-rules

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/signal-canvas/de-jure-iterative-llm-self-refinement-for-structured-extraction-of-regulatory-rules

MCP example

{
  "tool": "search_signal_canvas",
  "arguments": {
    "mode": "paper",
    "paper_ref": "de-jure-iterative-llm-self-refinement-for-structured-extraction-of-regulatory-rules",
    "query_text": "Summarize De Jure: Iterative LLM Self-Refinement for Structured Extraction of Regulatory Rules"
  }
}

source_context

{
  "surface": "signal_canvas",
  "mode": "paper",
  "query": "De Jure: Iterative LLM Self-Refinement for Structured Extraction of Regulatory Rules",
  "normalized_query": "2604.02276",
  "route": "/signal-canvas/de-jure-iterative-llm-self-refinement-for-structured-extraction-of-regulatory-rules",
  "paper_ref": "de-jure-iterative-llm-self-refinement-for-structured-extraction-of-regulatory-rules",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Evidence Receipt

Route status: building

Claims: 8

References: Pending verification

Proof: Verification pending

Freshness state: computing

Source paper: De Jure: Iterative LLM Self-Refinement for Structured Extraction of Regulatory Rules

PDF: https://arxiv.org/pdf/2604.02276v1

Source count: Pending verification

Coverage: 33%

Last proof check: 2026-04-03T20:50:40.241Z

Signal Canvas receipt window

Watch and verify: De Jure: Iterative LLM Self-Refinement for Structured Extraction of Regulatory Rules

/buildability/de-jure-iterative-llm-self-refinement-for-structured-extraction-of-regulatory-rules

Watchwatch

Subject: De Jure: Iterative LLM Self-Refinement for Structured Extraction of Regulatory Rules

Verdict

Watch

Verdict is Watch because viability or proof quality is intermediate and should be re-evaluated before execution.

Preparing verified analysis

GitHub Code Pulse

No public code linked for this paper yet.

Claim map

Strong 8Mixed 0Weak 0

Evidencepartial
We present De Jure, a fully automated, domain-agnostic pipeline for extracting structured regulatory rules from raw documents, requiring no human annotation, domain-specific prompting, or annotated gold data.
Implicationpartial
Explicitly stated in the abstract as a core contribution of the paper
Verificationpartial
partial
Evidencepartial
De Jure operates through four sequential stages: normalization of source documents into structured Markdown; LLM-driven semantic decomposition into structured rule units; multi-criteria LLM-as-a-judge evaluation across 19 dimensions spanning metadata, definitions, and rule semantics; and iterative repair of low-scoring extractions within a bounded regeneration budget
Implicationpartial
Directly described in the abstract as the pipeline's operational stages
Verificationpartial
partial
Evidencepartial
On the finance domain, De Jure yields consistent and monotonic improvement in extraction quality, reaching peak performance within three judge-guided iterations.
Implicationpartial
Explicitly stated in the abstract with specific performance characteristics
Verificationpartial
partial
Evidencepartial
De Jure generalizes effectively to healthcare and AI governance, maintaining high performance across both open- and closed-source models.
Implicationpartial
Directly stated in the abstract with domain generalization claims
Verificationpartial
partial
Evidencepartial
In a downstream compliance question-answering evaluation via RAG, responses grounded in De Jure extracted rules are preferred over prior work in 73.8% of cases at single-rule retrieval depth, rising to 84.0% under broader retrieval
Implicationpartial
Explicitly stated with precise numeric results in the abstract
Verificationpartial
partial
Evidencepartial
These results demonstrate that explicit, interpretable evaluation criteria can substitute for human annotation in complex regulatory domains
Implicationpartial
Strongly implied conclusion from the abstract's final statement
Verificationpartial
partial
Evidencepartial
multi-criteria LLM-as-a-judge evaluation across 19 dimensions spanning metadata, definitions, and rule semantics
Implicationpartial
Directly stated in the abstract with specific detail about evaluation dimensions
Verificationpartial
partial
Evidencepartial
confirming that extraction fidelity translates directly into downstream utility
Implicationpartial
Directly stated conclusion based on the RAG evaluation results
Verificationpartial
partial

Author intelligence and commercialization panels stay hidden until the proof receipt is verified, cites at least 3 references, includes at least 2 sources, and clears 50% coverage. The paper narrative and citation surfaces remain public while verification is pending.

De Jure: Iterative LLM Self-Refinement for Structured Extraction of Regulatory Rules

Use Signal Canvas as the narrative proof surface

Use this Signal Canvas via API or MCP

Signal Canvas proof surface