Paper Citation Record · LEDGER

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models

As of 9 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 4 inbound Pith citation observations for arXiv:2505.14071.

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

pith.paper-citation-record.v1
2505.14071 v1

Coverage vector

measured 12 of 12 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:42:31.291568Z

measured 16 of 16 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:45:42.708353Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-11T23:31:16.269375Z

Reference resolution

12 of 12 outbound references displayed

verified exact0
verified fuzzy1
unresolved7
parse uncertain4
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fe765d21-e912-4ff4-8f0f-2ef3bce18cb5 · outbound

This paper cites an unresolved cited work.

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:42:33.741602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 196a1e9a-71b0-4ac1-b608-7f780741b43c · outbound

This paper cites 2 OLMo 2 Furious.

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models 2 OLMo 2 Furious

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T15:42:29.875453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46a726e3-8d5e-4299-8b80-e784596effdd · outbound

This paper cites an unresolved cited work.

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models Unresolved cited work

Reference 3

Resolution: parse uncertain; raw_fallback, observed 2026-08-07T15:42:33.003136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 59fc1de5-1f45-4072-b6a3-10035225c09d · outbound

This paper cites an unresolved cited work.

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:42:33.544136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e70cef07-cd93-415f-be82-c2b78c35f96a · outbound

This paper cites an unresolved cited work.

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models Unresolved cited work

Reference 5

Resolution: parse uncertain; raw_fallback, observed 2026-08-07T15:42:33.352863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a8625e75-cbaf-4db0-a92e-f31f3a07b8cf · outbound

This paper cites an unresolved cited work.

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models Unresolved cited work

Reference 6

Resolution: parse uncertain; raw_fallback, observed 2026-08-07T15:42:33.191352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f0c5ad1c-ce68-4f24-8fc9-2e406c1fe6c2 · outbound

This paper cites an unresolved cited work.

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models Unresolved cited work

Reference 8

Resolution: parse uncertain; raw_fallback, observed 2026-08-07T15:42:32.855076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 57c109e9-1f8c-4f8e-a646-79b430dfadd6 · outbound

This paper cites an unresolved cited work.

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:42:32.704442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4f9dcd89-fe51-427e-a717-c1ad89b1420d · outbound

This paper cites an unresolved cited work.

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:42:32.453474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 90024b35-b02d-4768-8692-0ea109b64263 · outbound

This paper cites an unresolved cited work.

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:42:32.136059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8ab9e03c-c6f7-4819-8d0d-b6877b6567b3 · outbound

This paper cites INSTRUCTION:.

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models INSTRUCTION:

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:42:31.726510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1853cc4c-7d87-4f40-9ec0-ad89cb879819 · outbound

This paper cites Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders.

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T15:42:29.746277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation e4e68646-ed60-4f23-a0a8-2c927f4350f9 · inbound

Resa: Transparent Reasoning Models via SAEs cites this paper.

Resa: Transparent Reasoning Models via SAEs Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.708353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b2fd7ac-43cd-4335-9b36-25aaee936410 · inbound

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models cites this paper.

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-04T13:45:26.425121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6092d87a-c1bf-4fb3-aa3c-e8ea842bf7e5 · inbound

Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models cites this paper.

Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:31:16.272701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 80f05176-4831-4e3c-a3bd-126c5f59d985 · inbound

Do Unified Multimodal Models Think in One Space? A Lens Through Cross-Branch Steering cites this paper.

Do Unified Multimodal Models Think in One Space? A Lens Through Cross-Branch Steering Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-01T16:36:39.333944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.