Paper Citation Record · LEDGER

SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification

As of 5 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 2 inbound Pith citation observations for arXiv:2602.13600.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2602.13600 v2

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T23:33:16.687441Z

measured 17 of 17 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-12T00:17:46.528896Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-07-04T10:09:44.415018Z

Reference resolution

15 of 15 outbound references displayed

verified exact0
verified fuzzy0
unresolved14
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e4382789-4f06-4374-8035-9c43e06223f3 · outbound

This paper cites Qwen3-VL Technical Report.

SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification Qwen3-VL Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T23:33:14.940131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d978bc6-0e08-46f7-85d7-95f63966899b · outbound

This paper cites AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation.

SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T23:33:15.723808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad62665e-8710-47df-89e6-01bcfd4cdd9a · outbound

This paper cites InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency.

SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T23:33:15.832341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7bc94e8-617e-42b2-a805-f1e1d61896c4 · outbound

This paper cites Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance.

SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T23:33:15.935160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed78946e-2ef0-4321-814d-3a54309d0d58 · outbound

This paper cites Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention.

SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T23:33:16.095675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7aa333e-a41b-498d-99ce-10f3da614e3a · outbound

This paper cites Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method.

SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T23:33:16.220178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f3d3142-7539-4156-a400-f446b6445f33 · outbound

This paper cites Please describe the image in detail.

SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification Please describe the image in detail

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T23:33:16.372672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5042b1b8-54f7-4e09-b60a-37e01b07c9ba · outbound

This paper cites Is there a chair in the image?.

SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification Is there a chair in the image?

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T23:33:16.527014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c46efce-b0a4-48e5-990e-c8ddfcc95489 · outbound

This paper cites 15 AdaVBoost: Mitigating Hallucinations in LVLMs via Token-Level Adaptive Visual Attention Boosting C.

SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification 15 AdaVBoost: Mitigating Hallucinations in LVLMs via Token-Level Adaptive Visual Attention Boosting C

Reference 15

Resolution: malformed identifier; no resolver link, observed 2026-08-02T23:33:16.687441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 325a4fab-0c09-4c11-86de-22bdea499000 · outbound

This paper cites More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models.

SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models

Reference 2014

Resolution: unresolved; no resolver link, observed 2026-08-02T23:33:15.351162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d8ebbac-b1e1-4c67-b4a2-be66c87c5f92 · outbound

This paper cites Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models.

SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-02T23:33:15.126775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2324d115-2e3c-4e65-9058-042523fbfe70 · outbound

This paper cites Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities.

SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-02T23:33:15.612666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3c83b9e-94f2-4d28-9a26-142f962fa1a9 · outbound

This paper cites an unresolved cited work.

SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification Unresolved cited work

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-02T23:33:15.499967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49bdc69f-48cb-457a-9b20-d147e52ddeec · outbound

This paper cites F., Yaldiz, D.

SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification F., Yaldiz, D

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-02T23:33:15.203629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 773eec9c-3011-4f97-a1af-38f282a22120 · outbound

This paper cites Hallucination of Multimodal Large Language Models: A Survey.

SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification Hallucination of Multimodal Large Language Models: A Survey

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-02T23:33:15.016223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 317d63c9-2ef9-4c8d-b381-0569fdb99e7e · inbound

Listening makes Vision Clear for VLMs cites this paper.

Listening makes Vision Clear for VLMs SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification

Reference 39

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T10:09:44.416594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f3b96e57-7054-4b3d-900c-b5529aa7bfbf · inbound

Attending to Multimodal Generation One Token at a Time cites this paper.

Attending to Multimodal Generation One Token at a Time SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-12T00:17:46.528896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.