pith:LPH6T5NM
Less is More: Geometric Unlearning for LLMs with Minimal Data Disclosure
Geometric Unlearning lets LLMs forget specific private facts using only a handful of synthetic prompts while retaining general performance.
arxiv:2605.01735 v2 · 2026-05-03 · cs.CL
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{LPH6T5NM6EZ3BVPTSI7NPVSVZ6}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Across privacy-oriented unlearning benchmarks (ToFU and UnlearnPII), GU achieves strong target suppression with minimal impact on non-target performance, demonstrating that effective unlearning can be achieved with minimal synthetic data.
The assumption that a compact low-rank geometry distilled from safe reference prompts, combined with projection-based alignment using synthetic anchors, can effectively suppress target information in the model's hidden states without access to the original training corpus or significant utility loss.
Geometric Unlearning suppresses specific knowledge in LLMs by projecting hidden planning states onto a low-rank safe geometry derived from minimal reference prompts.
Receipt and verification
| First computed | 2026-05-28T01:05:12.457391Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
5bcfe9f5acf133b0d5f3923ed7d655cfbddc63545e95bdba97fcc61944227ad5
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/LPH6T5NM6EZ3BVPTSI7NPVSVZ6 \
| 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: 5bcfe9f5acf133b0d5f3923ed7d655cfbddc63545e95bdba97fcc61944227ad5
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "cd49f95c3619721b41c2f54a7b45db22a147bc8f16cb6f123b2c130f4fe60b06",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CL",
"submitted_at": "2026-05-03T06:20:03Z",
"title_canon_sha256": "d0dca146ca6ae22b09ad7a3a1b68227629cf8b01ce07edf5f79e8523fbec5cb9"
},
"schema_version": "1.0",
"source": {
"id": "2605.01735",
"kind": "arxiv",
"version": 2
}
}