Pith Number

pith:PSKIOVTH

pith:2026:PSKIOVTH3OSE3VZCPTMMBIBFOW

not attested not anchored not stored refs pending

SaFeR-Steer: Evolving Multi-Turn MLLMs via Synthetic Bootstrapping and Feedback Dynamics

An Zhang, Hanyu Li, Haolong Hu, Huahui Yi, Kun Wang, Qiankun Li, Tiancheng He, Yang Liu, Zhigang Zeng

SaFeR-Steer trains multi-turn multimodal models to hold safety and helpfulness against escalating attacks through synthetic bootstrapping and tutor feedback.

arxiv:2604.16358 v2 · 2026-03-18 · cs.LG · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{PSKIOVTH3OSE3VZCPTMMBIBFOW}

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

Starting from Qwen2.5-VL-3B/7B, SaFeR-Steer substantially improves Safety/Helpfulness on both single-turn (48.30/45.86 -> 81.84/70.77 for 3B; 56.21/60.32 -> 87.89/77.40 for 7B) and multi-turn benchmarks (12.55/27.13 -> 55.58/70.27 for 3B; 24.66/46.48 -> 64.89/72.35 for 7B), shifting failures to later turns.

C2weakest assumption

That the synthetic bootstrapping process and tutor-in-the-loop GRPO produce data and gradients that generalize to real-world multi-turn attacks rather than overfitting to the generated distribution or the specific tutor model.

C3one line summary

SaFeR-Steer boosts single-turn and multi-turn safety/helpfulness scores in Qwen2.5-VL models via staged synthetic bootstrapping and tutor-in-the-loop GRPO on a new STEER dataset.

Receipt and verification

First computed	2026-05-28T02:04:47.903904Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

7c94875667dba44dd7227cd8c0a0257580243f89bf2e37c6043c5ed0a04e4bde

Aliases

arxiv: 2604.16358 · arxiv_version: 2604.16358v2 · doi: 10.48550/arxiv.2604.16358 · pith_short_12: PSKIOVTH3OSE · pith_short_16: PSKIOVTH3OSE3VZC · pith_short_8: PSKIOVTH

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/PSKIOVTH3OSE3VZCPTMMBIBFOW \
  | 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: 7c94875667dba44dd7227cd8c0a0257580243f89bf2e37c6043c5ed0a04e4bde

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "01084c11191a11914693f030ba9811d9905f01d853b535a544793ac371bc6d3c",
    "cross_cats_sorted": [
      "cs.CL"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-03-18T09:28:29Z",
    "title_canon_sha256": "72f46ab6d5f941f24e43ae73fcf421145ce251a8b0b3013c6b065c1aabaaeefa"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.16358",
    "kind": "arxiv",
    "version": 2
  }
}