ARXIV:2601.05201 · VISION-LANGUAGE MODEL ANALYSIS · SUBMITTED 19 MAR · 18:48 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Mechanisms of Prompt-Induced Hallucination in Vision-Language Models

arXiv

This research analyzes how vision-language models get influenced by textual prompts, leading to hallucinations, and identifies attention heads that can mitigate this issue.

Blocked on Code›Score3.0Evidence unverified

Opportunity summary

Pain This research analyzes how vision-language models get influenced by textual prompts, leading to hallucinations, and identifies attention heads that can mitigate this issue.

Evidence 0 refs | 0 sources | 33% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

This research analyzes how vision-language models get influenced by textual prompts, leading to hallucinations, and identifies attention heads that can mitigate this issue. We study this failure mode in a controlled object-counting setting, where…

METHOD

Full abstract

Large vision-language models (VLMs) are highly capable, yet often hallucinate by favoring textual prompts over visual evidence. We study this failure mode in a controlled object-counting setting, where the prompt overstates the number of objects in the image (e.g., asking a model to describe four waterlilies when only three are present). At low object counts, models often correct the overestimation, but as the number of objects increases, they increasingly conform to the prompt regardless of the discrepancy. Through mechanistic analysis of three VLMs, we identify a small set of attention heads whose ablation substantially reduces prompt-induced hallucinations (PIH) by at least 40% without additional training. Across models, PIH-heads mediate prompt copying in model-specific ways. We characterize these differences and show that PIH ablation increases correction toward visual evidence. Our findings offer insights into the internal mechanisms driving prompt-induced hallucinations, revealing model-specific differences in how these behaviors are implemented.

RESULT

ScienceToStartup currently rates this 3.0/10 on the public viability pass. We characterize these differences and show that PIH ablation increases correction toward visual evidence.

WHY NOW

Vision-Language Model Analysis moved forward this cycle; last verified April 2026. Public score 3.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score3.0

PainThis research analyzes how vision-language models get influenced by textual prompts, leading to hallucinations, and identifies attention heads that can mitigate this issue.

Evidence0 refs | 0 sources | 33% coverage

Blockermissing authors

Analysis summary

This research analyzes how vision-language models get influenced by textual prompts, leading to hallucinations, and identifies attention heads that can mitigate this issue.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

ARXIV:2601.05201 · VISION-LANGUAGE MODEL ANALYSIS · SUBMITTED 19 MAR · 18:48 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Mechanisms of Prompt-Induced Hallucination in Vision-Language Models

arXiv

This research analyzes how vision-language models get influenced by textual prompts, leading to hallucinations, and identifies attention heads that can mitigate this issue.

Blocked on Code›Score3.0Evidence unverified

Opportunity summary

Pain This research analyzes how vision-language models get influenced by textual prompts, leading to hallucinations, and identifies attention heads that can mitigate this issue.

Evidence 0 refs | 0 sources | 33% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

METHOD

Full abstract

RESULT

ScienceToStartup currently rates this 3.0/10 on the public viability pass. We characterize these differences and show that PIH ablation increases correction toward visual evidence.

WHY NOW

Vision-Language Model Analysis moved forward this cycle; last verified April 2026. Public score 3.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score3.0

PainThis research analyzes how vision-language models get influenced by textual prompts, leading to hallucinations, and identifies attention heads that can mitigate this issue.

Evidence0 refs | 0 sources | 33% coverage

Blockermissing authors

Analysis summary

This research analyzes how vision-language models get influenced by textual prompts, leading to hallucinations, and identifies attention heads that can mitigate this issue.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Paper Pack

10.48550/arXiv.2601.05201

Mechanisms of Prompt-Induced Hallucination in Vision-Language Models

This research analyzes how vision-language models get influenced by textual prompts, leading to hallucinations, and identifies attention heads that can mitigate this issue.

Abstract

Source availability

PDF linked

The paper record includes a public PDF URL.

Extraction status

Parse run linked

A document parse run is attached to this paper.

Proof status

unverified

0 refs; 0 sources; 33% coverage.

What was readable

linkedon file16 anchorsderived fallback40 indexednot indexed

Derived fallback: Estimated from adjacent evidence; not verified from source.

Viability

3.0

Time to MVP

MVP estimate missing

Commercial

No commercial flags on file

Export

Preparing verified analysis

lens / founder

PROBLEM

METHOD

RESULT

ScienceToStartup currently rates this 3.0/10 on the public viability pass. We characterize these differences and show that PIH ablation increases correction toward visual evidence.

WHY NOW

Vision-Language Model Analysis moved forward this cycle; last verified April 2026. Public score 3.0/10.

Claim map

Abstract-backed public claims while anchored extraction refreshes.

Strong 0Mixed 0Weak 4

Evidencepartial
This research analyzes how vision-language models get influenced by textual prompts, leading to hallucinations, and identifies attention heads that can mitigate this issue. We study this failure mode in a controlled object-counting setting, where the prompt overstates the number of objects in the image (e.g., asking a model to describe four waterlilies when only three are present).
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Large vision-language models (VLMs) are highly capable, yet often hallucinate by favoring textual prompts over visual evidence. We study this failure mode in a controlled object-counting setting, where the prompt overstates the number of objects in the image (e.g., asking a model to describe four waterlilies when only three are present).
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
ScienceToStartup currently rates this 3.0/10 on the public viability pass. We characterize these differences and show that PIH ablation increases correction toward visual evidence.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Vision-Language Model Analysis moved forward this cycle; last verified April 2026. Public score 3.0/10.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial

Constellation map

Paper-native neighborhood for concepts, methods, materials, markets, and competitors. Missing lanes stay labeled instead of disappearing behind commercialization gates.

Open full Signal Canvas

Concepts

not indexed

Methods

Materials

PDF linkedDocument parse run

Markets

Vision-Language Model Analysis

Competitors

not indexed

Competitive landscape

This research analyzes how vision-language models get influenced by textual prompts, leading to hallucinations, and identifies attention heads that can mitigate this issue.

Segment

Vision-Language Model Analysis

Adoption evidence

No public code link in the paper record yet

Commercial read

3.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Buzz

No indexed public discussion is attached to 2601.05201 yet. That is a visibility signal, not a blank module: the monitor is watching the public channels below.

Hacker News

Not indexed yet

Bluesky

Not indexed yet

PDF

Preview the source document here, or use the hero PDF action for a new tab.

References(40)

Reference metadata pending (16c39d1ac20e33b38d81ce02d01bcdc72c4f9a47)

Reference metadata pending (3074967720b017ca36c1c650d9243f94568705eb)

Reference metadata pending (7ad77f44694d384368c7582f14d9c6ecf268b0dc)

Reference metadata pending (0a51f0355e43ae02bdb6656045fc5f3c9ccc60b4)

Reference metadata pending (9a678b67b7b938b9b56239498db2a13dfc146775)

Reference metadata pending (0311c49963ff756256bf1ac4363bf89b9314b13b)

Reference metadata pending (7a540746b254ed04424d720c52326271b0d08908)

Reference metadata pending (9568effdf3cf8b6076ca3c810d2cbc6f9b19bd51)

Reference metadata pending (97b64825cb5bca3d3a6d5910efd7c1182a542a01)

Reference metadata pending (66583ad76bc1ce493ed3b530b9a56f87a7e684ca)

Reference metadata pending (a81fb149aa23673ec73b236c8bf5afc369541649)

Reference metadata pending (15827d3552d7060a16a4cb6a5060650282d21983)

Reference metadata pending (a3113c980d432c17d78579ddb4df288fac8cea1a)

Reference metadata pending (d3e5d695737dd59d409f2e24aa96d6410734471f)

Reference metadata pending (3ef9dbd95a174d4c175fcd603f62b8cc197e8d7e)

Reference metadata pending (bd5271b1ac4eff77e4e3deb801f2ba77ccb5c1f6)

Reference metadata pending (a22b23b65cdbc0335b872ed7c7a7206c710f8997)

Reference metadata pending (1a71f7b216b710b936da666027014adb83af8e7a)

Reference metadata pending (89d857fdd842e2a632b76a8f38cf8d0f03aef46f)

Reference metadata pending (ab8e6df5001dbb9b48445220099425aff536b3e8)

Showing 20 of 40 references

CITED BY

No citing papers are indexed in the public S2S graph yet. This is an explicit zero-signal state, not a hidden lookup.

Foundation

Prior WorkVision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering

3.0

Prior WorkAnatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models

3.0

Extension

Builds On ThisMitigating Object Hallucinations in Vision-Language Models through Region-Aware Attention Recalibration

0.0

Commercially relevant

Higher ViabilityWhen Prompts Override Vision: Prompt-Induced Hallucinations in LVLMs

5.0

Higher ViabilityPrefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models

7.0

Higher ViabilityLLM-as-Judge Framework for Evaluating Tone-Induced Hallucination in Vision-Language Models

6.0

Higher ViabilityFinding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy

7.0

Higher ViabilityHALP: Detecting Hallucinations in Vision-Language Models without Generating a Single Token

7.0

Higher ViabilityGlobal Context or Local Detail? Adaptive Visual Grounding for Hallucination Mitigation

5.0

Higher ViabilityWhat Makes LVLMs Hallucinate Less? Unveiling the Architectural Factors Behind Hallucination Robustness

7.0

Conflicting

none indexed

Owned Distribution

Subscribe to the weekly brief

Get the weekly shortlist of commercializable papers, benchmark movers, and proof receipts that matter for product execution.

Agent drawer

5 surfaces preserved for agents. Humans can ignore.

Developer contracts, payload previews, evidence maps, and run controls stay here instead of the Read, Build, and Track workspace.

Run context

Paper: 2601.05201
Route: /paper/mechanisms-of-prompt-induced-hallucination-in-vision-language-models
Active tab: read
Artifact: mechanisms-of-prompt-induced-hallucination-in-vision-language-models

Available agents

Read extractor
Build planner
Track monitor
Competitive mapper
Related-paper scout

API/MCP endpoints

REST paper pack API/api/v1/paper/mechanisms-of-prompt-induced-hallucination-in-vision-language-models/paper-pack
REST build passport API/api/v1/paper/mechanisms-of-prompt-induced-hallucination-in-vision-language-models/build-passport
REST OpenAPI/api/openapi.json
MCP descriptor/api/mcp
MCP resourcesciencetostartup://surfaces/paper-workspace

Tool contracts

paper_packbuild_passportopportunity_kernelforesightsource_proofevidence_state

Payload preview

Inspect payload

{
  "contract_version": "paper-r2",
  "paper_id": "164fbe76-16eb-43f4-abf1-f1c4888d4d4c",
  "arxiv_id": "2601.05201",
  "canonical_route": "/paper/mechanisms-of-prompt-induced-hallucination-in-vision-language-models",
  "active_tab": "synced from current hash by the drawer client",
  "selected_artifact": "mechanisms-of-prompt-induced-hallucination-in-vision-language-models",
  "endpoints": {
    "paper_pack": "/api/v1/paper/mechanisms-of-prompt-induced-hallucination-in-vision-language-models/paper-pack",
    "build_passport": "/api/v1/paper/mechanisms-of-prompt-induced-hallucination-in-vision-language-models/build-passport",
    "mcp_resource": "sciencetostartup://surfaces/paper-workspace"
  }
}

Schema validation

paper-r2 contract: present
JSON-LD twin: SSR emitted
OpenAPI path parity: /api/openapi.json
MCP resource parity: paper-workspace

Job trace

queued: drawer opened by user action
running: inspect or copy payload
succeeded: payload available in SSR
failed: route errors appear in evidence cards

Evidence map

sources used: page freshness, source proof anchors, JSON-LD
missing sources: exposed by PaperPack and EvidenceState chips
derived fallbacks: marked unverified before handoff

Page Freshness

Canonical route, proof status, last verified, refs, sources, and coverage.

Page Freshness

Paper proof surface

Canonical route: /paper/mechanisms-of-prompt-induced-hallucination-in-vision-language-models

stale

Proof freshness: stale
Proof status: unverified
Display score: 3/10
Last proof check: 2026-03-19
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 0
Source count: 0
Coverage: 33%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

OpenAlex: pending — this preprint is not yet indexed by OpenAlex.

Agent Handoff

Endpoint list, payload shape, route context, and copyable handoff data.

Agent Handoff

Mechanisms of Prompt-Induced Hallucination in Vision-Language Models

Canonical ID mechanisms-of-prompt-induced-hallucination-in-vision-language-models | Route /paper/mechanisms-of-prompt-induced-hallucination-in-vision-language-models

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/paper/mechanisms-of-prompt-induced-hallucination-in-vision-language-models

MCP example

{
  "tool": "get_paper",
  "arguments": {
    "arxiv_id": "2601.05201"
  }
}

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "Mechanisms of Prompt-Induced Hallucination in Vision-Language Models",
  "normalized_query": "2601.05201",
  "route": "/paper/mechanisms-of-prompt-induced-hallucination-in-vision-language-models",
  "paper_ref": "mechanisms-of-prompt-induced-hallucination-in-vision-language-models",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Buildability Receipt

Verdict, compute envelope, blockers, signature state, and receipt links.

Paper proof page receipt window

Not build-ready: Mechanisms of Prompt-Induced Hallucination in Vision-Language Models

/buildability/mechanisms-of-prompt-induced-hallucination-in-vision-language-models

Ignoreblocked

Subject: Mechanisms of Prompt-Induced Hallucination in Vision-Language Models

Verdict

Ignore

Verdict is Ignore because current viability and proof state do not clear the buildability gate.

Time to first demo

Insufficient data

No first-demo timestamp, owner estimate, or elapsed demo receipt is attached to this surface.

Compute envelope

Structured compute envelope

Insufficient data

No data, compute, hardware, memory, latency, dependency, or serving requirement receipt is attached.

Evidence ids

Receipt path

/buildability/mechanisms-of-prompt-induced-hallucination-in-vision-language-models

Paper ref

mechanisms-of-prompt-induced-hallucination-in-vision-language-models

arXiv id

2601.05201

Freshness

Generated at

2026-03-19T18:48:05.835Z

Evidence freshness

stale

Last verification

2026-03-19T18:48:05.835Z

Sources

References

Coverage

33%

Hash state

Lineage hash

baf9081631ae173295bf268e6242892d9ae4802e0fa6647c4a9aa04e5dd284f6

Canonical opportunity-kernel lineage hash.

Signature state

External signature

unsigned_external

No founder, registry, pilot, or production-adoption signature is attached to this receipt.

Verification

not_verified

Verification is blocked until an external signature is provided.

Blockers

Missing: repo_url
Missing: references
Missing: distribution_readiness_scores
Missing: paper_extraction_scorecards
Unknown: distribution readiness has not been computed yet

Verification pending / evidence receipt incomplete

repo_url

references

Missing proof, requirement, signature, approval, adoption, or telemetry fields are blockers and must not be inferred.

Open receipt API receipt Build Loop Signal Canvas Proof divergence Divergence API Brier outcomes API

Source Proof anchors

Visual citations from the paper document graph.

Source proof

Visual citation anchors from the paper document graph.

16 anchors

proof blockPage 482%

This equation captures one of the core mathematical components of the system. for m ∈{1, 3, 5, 10}, selecting m = 3 for Qwen-

Page and bbox are available; crop image is pending.

proof blockPage 482%

This equation captures one of the core mathematical components of the system. N ≤4, the probability p(N | PB) is high while

Page and bbox are available; crop image is pending.

proof blockPage 1382%

This equation captures one of the core mathematical components of the system. ˜H(l,h) t = µ(l,h) ∀t ∈{1, . . . , T}. This intervention removes token-specific i

Page and bbox are available; crop image is pending.

JSON-LD twin

The application/ld+json payload rendered for agents.

{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@type": "WebPage",
      "@id": "https://sciencetostartup.com/paper/mechanisms-of-prompt-induced-hallucination-in-vision-language-models#webpage",
      "url": "https://sciencetostartup.com/paper/mechanisms-of-prompt-induced-hallucination-in-vision-language-models",
      "name": "Mechanisms of Prompt-Induced Hallucination in Vision-Language Models",
      "description": "This research analyzes how vision-language models get influenced by textual prompts, leading to hallucinations, and identifies attention heads that can mitigate this issue.",
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      }
    },
    {
      "@type": "ScholarlyArticle",
      "@id": "https://sciencetostartup.com/paper/mechanisms-of-prompt-induced-hallucination-in-vision-language-models#scholarlyArticle",
      "headline": "Mechanisms of Prompt-Induced Hallucination in Vision-Language Models",
      "description": "This research analyzes how vision-language models get influenced by textual prompts, leading to hallucinations, and identifies attention heads that can mitigate this issue.",
      "url": "https://sciencetostartup.com/paper/mechanisms-of-prompt-induced-hallucination-in-vision-language-models",
      "sameAs": "https://arxiv.org/abs/2601.05201",
      "identifier": {
        "@type": "PropertyValue",
        "propertyID": "arXiv",
        "value": "2601.05201"
      },
      "isAccessibleForFree": true,
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      },
      "datePublished": "2026-01-08T18:23:03.000Z",
      "citation": [
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "16c39d1ac20e33b38d81ce02d01bcdc72c4f9a47"
          },
          "url": "https://www.semanticscholar.org/paper/16c39d1ac20e33b38d81ce02d01bcdc72c4f9a47"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "3074967720b017ca36c1c650d9243f94568705eb"
          },
          "url": "https://www.semanticscholar.org/paper/3074967720b017ca36c1c650d9243f94568705eb"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "7ad77f44694d384368c7582f14d9c6ecf268b0dc"
          },
          "url": "https://www.semanticscholar.org/paper/7ad77f44694d384368c7582f14d9c6ecf268b0dc"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "0a51f0355e43ae02bdb6656045fc5f3c9ccc60b4"
          },
          "url": "https://www.semanticscholar.org/paper/0a51f0355e43ae02bdb6656045fc5f3c9ccc60b4"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "9a678b67b7b938b9b56239498db2a13dfc146775"
          },
          "url": "https://www.semanticscholar.org/paper/9a678b67b7b938b9b56239498db2a13dfc146775"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "0311c49963ff756256bf1ac4363bf89b9314b13b"
          },
          "url": "https://www.semanticscholar.org/paper/0311c49963ff756256bf1ac4363bf89b9314b13b"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "7a540746b254ed04424d720c52326271b0d08908"
          },
          "url": "https://www.semanticscholar.org/paper/7a540746b254ed04424d720c52326271b0d08908"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "9568effdf3cf8b6076ca3c810d2cbc6f9b19bd51"
          },
          "url": "https://www.semanticscholar.org/paper/9568effdf3cf8b6076ca3c810d2cbc6f9b19bd51"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "97b64825cb5bca3d3a6d5910efd7c1182a542a01"
          },
          "url": "https://www.semanticscholar.org/paper/97b64825cb5bca3d3a6d5910efd7c1182a542a01"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "66583ad76bc1ce493ed3b530b9a56f87a7e684ca"
          },
          "url": "https://www.semanticscholar.org/paper/66583ad76bc1ce493ed3b530b9a56f87a7e684ca"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "a81fb149aa23673ec73b236c8bf5afc369541649"
          },
          "url": "https://www.semanticscholar.org/paper/a81fb149aa23673ec73b236c8bf5afc369541649"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "15827d3552d7060a16a4cb6a5060650282d21983"
          },
          "url": "https://www.semanticscholar.org/paper/15827d3552d7060a16a4cb6a5060650282d21983"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "a3113c980d432c17d78579ddb4df288fac8cea1a"
          },
          "url": "https://www.semanticscholar.org/paper/a3113c980d432c17d78579ddb4df288fac8cea1a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "d3e5d695737dd59d409f2e24aa96d6410734471f"
          },
          "url": "https://www.semanticscholar.org/paper/d3e5d695737dd59d409f2e24aa96d6410734471f"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "3ef9dbd95a174d4c175fcd603f62b8cc197e8d7e"
          },
          "url": "https://www.semanticscholar.org/paper/3ef9dbd95a174d4c175fcd603f62b8cc197e8d7e"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "bd5271b1ac4eff77e4e3deb801f2ba77ccb5c1f6"
          },
          "url": "https://www.semanticscholar.org/paper/bd5271b1ac4eff77e4e3deb801f2ba77ccb5c1f6"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "a22b23b65cdbc0335b872ed7c7a7206c710f8997"
          },
          "url": "https://www.semanticscholar.org/paper/a22b23b65cdbc0335b872ed7c7a7206c710f8997"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "1a71f7b216b710b936da666027014adb83af8e7a"
          },
          "url": "https://www.semanticscholar.org/paper/1a71f7b216b710b936da666027014adb83af8e7a"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "89d857fdd842e2a632b76a8f38cf8d0f03aef46f"
          },
          "url": "https://www.semanticscholar.org/paper/89d857fdd842e2a632b76a8f38cf8d0f03aef46f"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "ab8e6df5001dbb9b48445220099425aff536b3e8"
          },
          "url": "https://www.semanticscholar.org/paper/ab8e6df5001dbb9b48445220099425aff536b3e8"
        }
      ],
      "additionalProperty": [
        {
          "@type": "PropertyValue",
          "propertyID": "viabilityScore",
          "value": 3
        },
        {
          "@type": "PropertyValue",
          "propertyID": "researchDomain",
          "value": "Vision-Language Model Analysis"
        }
      ]
    },
    {
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "position": 1,
          "name": "Home",
          "item": "https://sciencetostartup.com"
        },
        {
          "@type": "ListItem",
          "position": 2,
          "name": "Vision-Language Model Analysis",
          "item": "https://sciencetostartup.com/topics"
        },
        {
          "@type": "ListItem",
          "position": 3,
          "name": "Mechanisms of Prompt-Induced Hallucination in Vision-Languag",
          "item": "https://sciencetostartup.com/paper/mechanisms-of-prompt-induced-hallucination-in-vision-language-models"
        }
      ]
    }
  ]
}

Mechanisms of Prompt-Induced Hallucination in Vision-Language Models

Mechanisms of Prompt-Induced Hallucination in Vision-Language Models

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(40)

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(40)

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline