Pith Number

pith:JHTW7AMA

pith:2024:JHTW7AMALJK4JSDR3OR2WJXT3F

not attested not anchored not stored refs resolved

Aligning Modalities in Vision Large Language Models via Preference Fine-tuning

Chelsea Finn, Chenhang Cui, Huaxiu Yao, Rafael Rafailov, Yiyang Zhou

Preference fine-tuning on automatically generated hallucinated responses aligns vision and language modalities in large models while cutting hallucinations.

arxiv:2402.11411 v1 · 2024-02-18 · cs.LG · cs.CL · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{JHTW7AMALJK4JSDR3OR2WJXT3F}

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

In experiments across broad benchmarks, we show that we can not only reduce hallucinations, but improve model performance across standard benchmarks, outperforming prior approaches.

C2weakest assumption

The two-stage automated generation of dispreferred responses (GPT-4V hallucination injection and image distortion) produces high-quality preference pairs that accurately reflect and correct the model's hallucination behavior when used in DPO.

C3one line summary

POVID generates AI-created preference data to fine-tune vision-language models with DPO, reducing hallucinations and improving benchmark scores.

References

155 extracted · 155 resolved · 22 Pith anchors

[18] InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning , author=. 2023 , eprint= 2023

[20] Langley , title = 2000

[21] T. M. Mitchell. The Need for Biases in Learning Generalizations. 1980 1980

[22] M. J. Kearns , title =

[23] Machine Learning: An Artificial Intelligence Approach, Vol. I. 1983 1983

Formal links

2 machine-checked theorem links

Cited by

19 papers in Pith

Deep Pre-Alignment for VLMs

InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output

Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization

Bad Seeing or Bad Thinking? Rewarding Perception for Vision-Language Reasoning

20/20 Vision Language Models: A Prescription for Better VLMs through Data Curation Alone

Receipt and verification

First computed	2026-05-17T23:38:14.301452Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

49e76f81805a55c4c871dba3ab26f3d953edb4d0e81b5a42139b8ca28b71f008

Aliases

arxiv: 2402.11411 · arxiv_version: 2402.11411v1 · doi: 10.48550/arxiv.2402.11411 · pith_short_12: JHTW7AMALJK4 · pith_short_16: JHTW7AMALJK4JSDR · pith_short_8: JHTW7AMA

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/JHTW7AMALJK4JSDR3OR2WJXT3F \
  | 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: 49e76f81805a55c4c871dba3ab26f3d953edb4d0e81b5a42139b8ca28b71f008

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "684c4ab3db146800bb4720a51e3c130124f5c1e1b7bb92be651fce3d29e8a9af",
    "cross_cats_sorted": [
      "cs.CL",
      "cs.CV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2024-02-18T00:56:16Z",
    "title_canon_sha256": "95495881af9bfc34909c83f89fd32e4e9c83ca55cee19e4cb282e8de90b75049"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2402.11411",
    "kind": "arxiv",
    "version": 1
  }
}