Paper Citation Record · LEDGER

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs

As of 18 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 6 inbound Pith citation observations for arXiv:2507.18043.

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

pith.paper-citation-record.v1
2507.18043 v2

Coverage vector

measured 55 of 55 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T14:45:08.726791Z

measured 61 of 61 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-11T11:07:46.258643Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

55 of 55 outbound references displayed

verified exact7
verified fuzzy17
unresolved31
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation b21dbeae-8672-45f1-bbd8-86efa39101db · outbound

This paper cites GPT-4 Technical Report.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.572148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2a132a2-d174-4d2f-a068-fb19a78fa2e2 · outbound

This paper cites A diagnostic study of explainability techniques for text classification.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs A diagnostic study of explainability techniques for text classification

Reference 2

Resolution: verified exact; doi, observed 2026-08-06T14:45:08.801516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7a2f0d49-3cf4-4906-bbe9-11933ca3da4b · outbound

This paper cites Madtp: Multimodal alignment-guided dynamic token pruning for accelerating vision-language transformer.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Madtp: Multimodal alignment-guided dynamic token pruning for accelerating vision-language transformer

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:45:09.468380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3201bf3e-025a-4982-93a6-c4fe254e9f0f · outbound

This paper cites Xprompt: Explaining large language model's generation via joint prompt attribution.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Xprompt: Explaining large language model's generation via joint prompt attribution

Reference 4

Resolution: verified exact; raw_fallback, observed 2026-08-06T14:45:09.267613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 472e75fd-80c5-4a34-abf7-c13dfc1fc7ab · outbound

This paper cites ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.585297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7946dc7-3893-4d32-9ef0-0b864639c556 · outbound

This paper cites Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-08-06T14:45:09.167867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6a213b3b-a79b-4099-a489-265448e343e6 · outbound

This paper cites Covert, Scott Lundberg, and Su-In Lee.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Covert, Scott Lundberg, and Su-In Lee

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:45:09.459771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7d61dc24-08f8-4ab9-9abf-82d767099187 · outbound

This paper cites The Llama 3 Herd of Models.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs The Llama 3 Herd of Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.594726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f0f6360-46fd-4638-bf8b-25ea3bd72a8f · outbound

This paper cites Frustratingly easy test-time adaptation of vision-language models.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Frustratingly easy test-time adaptation of vision-language models

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:45:09.451008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 76e45a9b-8330-462b-908d-a21adb85346c · outbound

This paper cites Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.600409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ab32076-071c-4558-8c3c-479fce448f6c · outbound

This paper cites T oxi G en: A large-scale machine-generated dataset for adversarial and implicit hate speech detection.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs T oxi G en: A large-scale machine-generated dataset for adversarial and implicit hate speech detection

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.603323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2da50cd6-d2d0-4cdc-9454-8fc2e2f81509 · outbound

This paper cites Measuring massive multitask language understanding.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Measuring massive multitask language understanding

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.606012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04a805b3-bdef-4baa-b9c3-9a167c888880 · outbound

This paper cites Non-linear inference time intervention: Improving llm truthfulness.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Non-linear inference time intervention: Improving llm truthfulness

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:45:09.437357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d17db6cb-0ee8-4567-9910-42f85b2e7710 · outbound

This paper cites Lo RA : Low-rank adaptation of large language models.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Lo RA : Low-rank adaptation of large language models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.611121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25c45511-6ade-4fc4-bf25-a37e90e5a1c9 · outbound

This paper cites an unresolved cited work.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.614115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43ee9a39-71cc-4eca-baab-d752563cdeb2 · outbound

This paper cites A unified understanding and evaluation of steering methods.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs A unified understanding and evaluation of steering methods

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.616809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3582b7c4-0072-4d99-95cb-f8f3687d2099 · outbound

This paper cites Guided integrated gradients: An adaptive path method for removing noise.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Guided integrated gradients: An adaptive path method for removing noise

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:45:09.415402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation efa84903-f5b9-434b-8227-86218e39290e · outbound

This paper cites Analyzing Finetuning Representation Shift for Multimodal LLMs Steering.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Analyzing Finetuning Representation Shift for Multimodal LLMs Steering

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-08-06T14:45:09.072091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 71fc0b72-392e-40eb-ad55-08afc769ee97 · outbound

This paper cites Mitigating object hallucinations in large vision-language models through visual contrastive decoding.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Mitigating object hallucinations in large vision-language models through visual contrastive decoding

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:45:09.405497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2b00a94e-42cd-4214-a91e-cc483e2c660c · outbound

This paper cites Inference-time intervention: Eliciting truthful answers from a language model.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Inference-time intervention: Eliciting truthful answers from a language model

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:45:09.395690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c3260a3d-e4c9-42e8-b920-f6b1b8176bde · outbound

This paper cites Learning without forgetting.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Learning without forgetting

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:45:09.385719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation cd2dd1af-1e0c-49bc-bd2a-2b4f748b7f53 · outbound

This paper cites T ruthful QA : Measuring how models mimic human falsehoods.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs T ruthful QA : Measuring how models mimic human falsehoods

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.634281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f7a930d-396f-4b96-8eb2-45c9931602cd · outbound

This paper cites A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.637173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22c972f3-8ab0-4eed-a648-6646e4c90cbe · outbound

This paper cites Llava-next: Improved reasoning, ocr, and world knowledge, January 2024 a.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Llava-next: Improved reasoning, ocr, and world knowledge, January 2024 a

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.640083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7532f68-77b1-4b10-8712-fc3f60676dca · outbound

This paper cites Reducing Hallucinations in Vision-Language Models via Latent Space Steering.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Reducing Hallucinations in Vision-Language Models via Latent Space Steering

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.642780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ff7d5fc-9ae2-44c6-bbe3-9bc4f78136a1 · outbound

This paper cites In-context vectors: Making in context learning more effective and controllable through latent space steering.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs In-context vectors: Making in context learning more effective and controllable through latent space steering

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:45:09.371802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 08649fc5-66b9-4b34-a3b9-caac353363b6 · outbound

This paper cites Gradient episodic memory for continual learning.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Gradient episodic memory for continual learning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.648568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 307e13ad-cde6-43d4-bb0d-cd12def26bbb · outbound

This paper cites The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.651325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5d6b8ea-6ce1-4d61-a002-fdd8235e00d4 · outbound

This paper cites Faitheval: Can your language model stay faithful to context, even if ''the moon is made of marshmallows''.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Faitheval: Can your language model stay faithful to context, even if ''the moon is made of marshmallows''

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:45:09.357480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 90409f6c-d5da-4fb9-9a06-071da951e821 · outbound

This paper cites Risk-aware distributional intervention policies for language models.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Risk-aware distributional intervention policies for language models

Reference 30

Resolution: verified exact; raw_fallback, observed 2026-08-06T14:45:09.026204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c87a7114-afc0-463e-ad52-323906112331 · outbound

This paper cites Multi-Attribute Steering of Language Models via Targeted Intervention.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Multi-Attribute Steering of Language Models via Targeted Intervention

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.659788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf484691-5e92-4699-a0c7-f686fe385641 · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Steering Llama 2 via Contrastive Activation Addition

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.662726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e31f871-3e83-46f5-a1c1-0675b521466f · outbound

This paper cites Combining feature and instance attribution to detect artifacts.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Combining feature and instance attribution to detect artifacts

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.665561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3ab98e7-b1de-46dc-bcbc-c66f88fff68c · outbound

This paper cites Householder pseudo-rotation: A novel approach to activation editing in LLM s with direction-magnitude perspective.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Householder pseudo-rotation: A novel approach to activation editing in LLM s with direction-magnitude perspective

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.668433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f429a8e2-4c78-4c9c-bf63-850a4535e52a · outbound

This paper cites Rewarded soups: towards pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Rewarded soups: towards pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:45:09.348565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d909c43d-62fc-492d-bd0f-027cb67db8d8 · outbound

This paper cites Steering llama 2 via contrastive activation addition.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Steering llama 2 via contrastive activation addition

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.674114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 250a1e14-e315-43cd-a800-c86a6dff5b33 · outbound

This paper cites A consistent and efficient evaluation strategy for attribution methods.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs A consistent and efficient evaluation strategy for attribution methods

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:45:09.339433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9949bf89-c3a2-4818-b9ed-35abec54c628 · outbound

This paper cites Are vision-language transformers learning multimodal representations? a probing perspective.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Are vision-language transformers learning multimodal representations? a probing perspective

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:45:09.330728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3e589c6d-1c9c-4c44-917a-7f39cbedc15f · outbound

This paper cites Smith, and Simon Shaolei Du.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Smith, and Simon Shaolei Du

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:45:09.321912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d4b3c61d-32f4-4365-84f7-f216dfbea6e6 · outbound

This paper cites SmoothGrad: removing noise by adding noise.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs SmoothGrad: removing noise by adding noise

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.685271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc9b94f9-54e9-4fac-98a5-39e8de287198 · outbound

This paper cites Efficient open-set test time adaptation of vision language models.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Efficient open-set test time adaptation of vision language models

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:45:09.312946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c2d1f33e-2cb3-4dbf-803e-9a075293b848 · outbound

This paper cites LVP runing: An effective yet simple language-guided vision token pruning approach for multi-modal large language models.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs LVP runing: An effective yet simple language-guided vision token pruning approach for multi-modal large language models

Reference 42

Resolution: verified exact; doi, observed 2026-08-06T14:45:08.756999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a84a0dbb-863d-4fcb-9ac2-f169a35cd4f6 · outbound

This paper cites Aligning Large Multimodal Models with Factually Augmented RLHF.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Aligning Large Multimodal Models with Factually Augmented RLHF

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.693838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c2a945c-42f9-4d1e-b88d-d02ae2cd1484 · outbound

This paper cites Axiomatic attribution for deep networks.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Axiomatic attribution for deep networks

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:45:09.304142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 07fda6dd-1818-49fb-8499-74aa319d0eaa · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Gemini: A Family of Highly Capable Multimodal Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.699397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7aa9766-d119-414c-8595-a070a843e9ba · outbound

This paper cites Gemma 3 Technical Report.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Gemma 3 Technical Report

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.701915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 518427e3-aa99-4980-ba79-0eb85226a8c6 · outbound

This paper cites Qwen2.5: A party of foundation models, September 2024.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Qwen2.5: A party of foundation models, September 2024

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.704780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5393a4fa-0e7e-457a-a5d9-1b62a0130e89 · outbound

This paper cites Steering Language Models With Activation Engineering.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Steering Language Models With Activation Engineering

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.707384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9641300d-4a91-494e-b546-e32db362dc7b · outbound

This paper cites Contrastive region guidance: Improving grounding in vision-language models without training.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Contrastive region guidance: Improving grounding in vision-language models without training

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T14:45:09.289794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6c4c1097-4f9f-4e3d-9636-c38df5f3b42c · outbound

This paper cites AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-08-06T14:45:08.856617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b4d6127e-65cb-4c24-9b3a-0da6255b599a · outbound

This paper cites Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.715420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44b2cb02-fdb6-45b0-bfc3-3bae28d1c682 · outbound

This paper cites Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.718348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d841a76a-6ab2-4fe8-8b92-cefda9142c5a · outbound

This paper cites SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.721119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27dad7be-ea30-489b-bef2-e3dabe09eaff · outbound

This paper cites Bayesian Test-Time Adaptation for Vision-Language Models.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Bayesian Test-Time Adaptation for Vision-Language Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.723935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e742f20d-6cef-48ab-b058-ac76114d6c0d · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs Representation Engineering: A Top-Down Approach to AI Transparency

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T14:45:08.726791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 678ca0c8-c38f-4fe7-bc54-6f713fff697f · inbound

T2T-VICL: Cross-Task Visual In-Context Learning via Implicit Text-Driven VLMs cites this paper.

T2T-VICL: Cross-Task Visual In-Context Learning via Implicit Text-Driven VLMs GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T21:15:45.641226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47dc51af-060a-47b1-a192-6fa63f5668a5 · inbound

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models cites this paper.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs

Reference 220

Resolution: verified exact; arxiv_id, observed 2026-07-13T00:17:01.983164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d35ccd77-62a6-4cab-9aef-e20585a927c7 · inbound

The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment cites this paper.

The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-07-13T00:17:01.983164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 04ddcd88-d3ec-46b6-b58f-1dbaebb94308 · inbound

Continuous Interpretive Steering for Scalar Diversity cites this paper.

Continuous Interpretive Steering for Scalar Diversity GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-07-13T00:17:01.983164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 82b611a0-a29f-46fc-9616-bd1bb95bfcb5 · inbound

Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection cites this paper.

Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-07-13T00:17:01.983164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2f169d23-f4fd-431d-9bcb-1a53b5901c10 · inbound

PragMatch: Separating Pragmatic Incongruity from Cross-Modal Mismatch in Large Vision-Language Models cites this paper.

PragMatch: Separating Pragmatic Incongruity from Cross-Modal Mismatch in Large Vision-Language Models GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-11T11:07:46.258643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.