pith:7P4MQPRZ
Macro: Enhancing Multilingual Counterfactual Explanations through Alignment-as-Preference Optimization
A preference alignment method called Macro improves the validity of multilingual self-generated counterfactual explanations by 12.55 percent on average while maintaining minimality.
arxiv:2605.11632 v2 · 2026-05-12 · cs.CL · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{7P4MQPRZW4UKJLBA7LRVLSCG4K}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Experiments across four LLMs and seven typologically diverse languages show that Macro improves validity by 12.55% on average over the chain-of-thought baseline without degrading minimality, while avoiding the severe minimality violations of the translation-based baseline.
The composite scoring function used to construct preference pairs accurately and unbiasedly captures the validity-minimality trade-off across typologically diverse languages and different LLMs.
Macro uses Direct Preference Optimization on composite-scored preference pairs to improve validity of multilingual self-generated counterfactual explanations by 12.55% on average without degrading minimality.
Receipt and verification
| First computed | 2026-06-05T01:14:40.562797Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
fbf8c83e39b728a4ac20fae355c846e29e8ed32c83c65cb5d31723f179ba16fb
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/7P4MQPRZW4UKJLBA7LRVLSCG4K \
| 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: fbf8c83e39b728a4ac20fae355c846e29e8ed32c83c65cb5d31723f179ba16fb
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "6061ab8a4eb421fa0d89540d86fceb1b7b7ce62edd3a578dd6d1709618ca0067",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.CL",
"submitted_at": "2026-05-12T06:56:18Z",
"title_canon_sha256": "a6e1694b654f559b8075b950f5cc4ba25911443e16acdafd56ee72a1e31a47f8"
},
"schema_version": "1.0",
"source": {
"id": "2605.11632",
"kind": "arxiv",
"version": 2
}
}