Pith Number

pith:BTFLURS4

pith:2026:BTFLURS4YQY6C57TYM6TIEOM26

not attested not anchored not stored refs resolved

LLMs as annotators of credibility assessment in Danish asylum decisions: evaluating classification performance and errors beyond aggregated metrics

Anna Murphy H{\o}genhaug, Asta S. Stage Jarlner, Desmond Elliott, Galadrielle Humblot-Renaux, Maria Vlachou, Marieke Anne Heyl, Mohammad N. S. Jahromi, Rohat Bakuri-J{\o}rgensen, Thomas B. Moeslund, Thomas Gammeltoft-Hansen

Large language models can annotate credibility assessments in Danish asylum decisions at moderate accuracy but show inconsistent errors that vary by model and prompt.

arxiv:2605.13412 v1 · 2026-05-13 · cs.CL · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{BTFLURS4YQY6C57TYM6TIEOM26}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Our results confirm the potential of LLMs for cost-effective labeling of asylum decisions, but highlight the imperfect and inconsistent nature of LLM annotators, and the need to look beyond the predictions of a single, arbitrarily chosen model.

C2weakest assumption

That the expert annotations in the RAB-Cred dataset constitute reliable ground truth for the subtle legal concept of credibility assessment, and that this task can be adequately captured by the chosen classification labels without deeper domain-specific legal context.

C3one line summary

LLMs can provide cost-effective annotation of credibility in Danish asylum texts but produce inconsistent errors that vary by model and prompt, requiring checks beyond single-model accuracy.

References

84 extracted · 84 resolved · 0 Pith anchors

[1] Aho and Jeffrey D 1972

[2] Large Language Models in Legal Systems: A Survey , volume =

[3] 2025 , MONTH = Nov, KEYWORDS = 2025

[4] arXiv preprint arXiv:2410.07504 , year=

[5] Computer Law & Security Review , volume= 2025

Receipt and verification

First computed	2026-05-18T02:44:47.430236Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

0ccaba465cc431e177f3c33d3411ccd7848e40b0b631ab3ce0aead8a2c69e36f

Aliases

arxiv: 2605.13412 · arxiv_version: 2605.13412v1 · doi: 10.48550/arxiv.2605.13412 · pith_short_12: BTFLURS4YQY6 · pith_short_16: BTFLURS4YQY6C57T · pith_short_8: BTFLURS4

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/BTFLURS4YQY6C57TYM6TIEOM26 \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 0ccaba465cc431e177f3c33d3411ccd7848e40b0b631ab3ce0aead8a2c69e36f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "9dc71b2c58d95f426074e14203d3c496f8b9ede6377ad6e4f18de31809318681",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-13T12:07:47Z",
    "title_canon_sha256": "0f7f6b0785516664d695a3cb4cb200ad8d270b92c75fe8fd0a8a0fe53f622a78"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13412",
    "kind": "arxiv",
    "version": 1
  }
}