Paper Citation Record · LEDGER

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key

As of 18 August 2026, this Paper Citation Record lists 68 of 68 outbound references and 7 inbound Pith citation observations for arXiv:2501.09695.

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

pith.paper-citation-record.v1
2501.09695 v2

Coverage vector

measured 68 of 68 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T19:52:09.274807Z

measured 75 of 75 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:31:48.323166Z

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

68 of 68 outbound references displayed

verified exact0
verified fuzzy36
unresolved31
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

1
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 0355fbe9-dd49-4afa-9b35-d723ed5293aa · outbound

This paper cites Flamingo: a visual language model for few-shot learning.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Flamingo: a visual language model for few-shot learning

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.510538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 83e7a012-5fca-4d1e-8079-2b7e1128f38e · outbound

This paper cites InstructBLIP: Towards general-purpose vision- language models with instruction tuning.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key InstructBLIP: Towards general-purpose vision- language models with instruction tuning

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.494811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e31d6c4f-e011-43f7-871d-9a3ad7a7ad38 · outbound

This paper cites BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.478706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 84420e2e-af93-4bda-a4ad-603b52256dd3 · outbound

This paper cites GPT-4V(ision) System Card.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key GPT-4V(ision) System Card

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.461249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7b0052f2-c5e9-485f-a172-9a51eff2f088 · outbound

This paper cites Visual instruction tuning.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Visual instruction tuning

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.446028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 75adc40d-13fa-437e-8c80-1c2ec8cfd4c3 · outbound

This paper cites Improved baselines with visual instruction tuning.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Improved baselines with visual instruction tuning

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.430993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fde297f7-c4da-40af-b98e-9826d0a5a1a3 · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:08.974860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40162cf8-3d26-442e-a6a9-c379da9c22dd · outbound

This paper cites LLaV A-Med: Training a large language- and-vision assistant for biomedicine in one day.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key LLaV A-Med: Training a large language- and-vision assistant for biomedicine in one day

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.414914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation dae8e74d-edeb-4299-90d5-3f5645ed24a7 · outbound

This paper cites Dr-LLaVA: Visual Instruction Tuning with Symbolic Clinical Grounding.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Dr-LLaVA: Visual Instruction Tuning with Symbolic Clinical Grounding

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:08.984941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68c0f580-8b98-4581-bf6c-a46f59309d39 · outbound

This paper cites MAIRA-1: A specialised large multimodal model for radiology report generation.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key MAIRA-1: A specialised large multimodal model for radiology report generation

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:08.990037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40a3f50f-3014-4579-9764-2e46d542ada0 · outbound

This paper cites MAIRA-2: Grounded Radiology Report Generation.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key MAIRA-2: Grounded Radiology Report Generation

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:08.995277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16040bd1-3a26-40a3-8d89-7155e0421af4 · outbound

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

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Hallucination of Multimodal Large Language Models: A Survey

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.000330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dff200b5-18dd-40a0-9689-ecedce7cbea6 · outbound

This paper cites A Survey of Hallucination in Large Visual Language Models.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key A Survey of Hallucination in Large Visual Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.005286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6222881-c2cd-47d6-b718-aec5ff79df2e · outbound

This paper cites A Survey on Hallucination in Large Vision-Language Models.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key A Survey on Hallucination in Large Vision-Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.010301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddae57f7-538b-49c9-96b2-549c23cfa7ea · outbound

This paper cites RLHF-V: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key RLHF-V: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.398793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d26d2027-68d4-4a12-aed2-b8b2682f8dfe · outbound

This paper cites Aligning modalities in vision large lan- guage models via preference fine-tuning.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Aligning modalities in vision large lan- guage models via preference fine-tuning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.019807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27b012c0-222e-486c-b3a6-0186f928f547 · outbound

This paper cites Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.024700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caacbb61-24df-4dff-9a1d-05031c8fc5c1 · outbound

This paper cites Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.029533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cfa7c98-7c5c-4dae-8e6e-c7c24ec82615 · outbound

This paper cites Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.034994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f163df4d-9fa0-4b1a-ae4d-972aadc79dbb · outbound

This paper cites RlAIF-V: Aligning mllms through open-source AI feedback for super gpt-4v trustworthiness.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key RlAIF-V: Aligning mllms through open-source AI feedback for super gpt-4v trustworthiness

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.039831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12926189-474f-464f-8205-68390437aca9 · outbound

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

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Aligning Large Multimodal Models with Factually Augmented RLHF

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.044321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 411e3065-6806-4040-acf3-905cf7cd4655 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Proximal Policy Optimization Algorithms

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.049115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5223bd4-2e58-405c-8038-5a5b939a2850 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Direct preference optimization: Your language model is secretly a reward model

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.371595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b08d0e32-15f8-4443-b2cd-4a2acee9e705 · outbound

This paper cites Rank analysis of incomplete block designs: I.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Rank analysis of incomplete block designs: I

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.356132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b157876c-664d-4b19-bf89-7baae1af2587 · outbound

This paper cites On informa- tion and sufficiency.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key On informa- tion and sufficiency

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.340127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c73126a1-83aa-42b5-8de1-1eaa9bf6c956 · outbound

This paper cites VLFeedback: A large-scale AI feedback dataset for large vision-language models alignment.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key VLFeedback: A large-scale AI feedback dataset for large vision-language models alignment

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.325324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b20029cd-fed4-40a3-a35d-69d957f3d39a · outbound

This paper cites Huang, Nan Xu, Sheng Zhang, Hoifung Poon, and Muhao Chen.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Huang, Nan Xu, Sheng Zhang, Hoifung Poon, and Muhao Chen

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.309729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7454a1ab-d12c-4386-a0f3-c45da4812ece · outbound

This paper cites Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.078017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbc0d220-27d9-4607-9f0f-5554b38a69b6 · outbound

This paper cites Is DPO superior to PPO for llm alignment? a comprehensive study.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Is DPO superior to PPO for llm alignment? a comprehensive study

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.294339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 536a7a01-4154-42c1-a790-9b8fb69d10bf · outbound

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

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.088133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb85c325-addf-428d-b061-7b74370649ac · outbound

This paper cites Object hallucination in image cap- tioning.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Object hallucination in image cap- tioning

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.279633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f80852cb-7276-4dea-8374-938a240fce23 · outbound

This paper cites Evaluating object hallucination in large vision-language models.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Evaluating object hallucination in large vision-language models

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.264875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f3024722-b9ac-4c7b-92ae-b0805ceb1843 · outbound

This paper cites Deep reinforcement learn- ing from human preferences.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Deep reinforcement learn- ing from human preferences

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.249336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 092c30b0-2fd1-4851-8c85-2b0e8c5389f0 · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Fine-Tuning Language Models from Human Preferences

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.107531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67861b35-6d2b-4ae0-8556-1394bfd64dcc · outbound

This paper cites Training language models to follow instructions with human feedback.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Training language models to follow instructions with human feedback

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.233621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e3dbd163-2fae-4b33-9979-51f84d4dda8f · outbound

This paper cites Improving language understanding by gener- ative pre-training.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Improving language understanding by gener- ative pre-training

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.217249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b2e66355-5d1e-4f3b-aef4-ba4513a0b61b · outbound

This paper cites Language models are unsu- pervised multitask learners.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Language models are unsu- pervised multitask learners

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.202045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 70dc3c37-0fbc-455c-8947-69193be47832 · outbound

This paper cites Lan- guage models are few-shot learners.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Lan- guage models are few-shot learners

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.186975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1c05cb32-eaa0-4e7d-8989-1b64dfad60a7 · outbound

This paper cites GPT-4 Technical Report.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key GPT-4 Technical Report

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.132457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d70ee3d2-0788-41a9-8c30-2ea97a24caee · outbound

This paper cites The Llama 3 Herd of Models.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key The Llama 3 Herd of Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.137483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a223d9cb-2a4c-4a8c-8843-089a0ff2f4cf · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.142559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 238fcf81-7458-4deb-8353-c825a0bfacd4 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key LLaMA: Open and Efficient Foundation Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.147298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dba3694e-dcb7-4712-8a09-e121272f7147 · outbound

This paper cites Qwen Technical Report.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Qwen Technical Report

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.152350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b599a9a-521c-43ae-b92b-f0dfcb04e772 · outbound

This paper cites Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.157107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa1b248e-b6e8-4a73-b272-8410baa81b45 · outbound

This paper cites Qwen2 Technical Report.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Qwen2 Technical Report

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.162024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e44346a6-95a4-432b-8a02-7da27f873f22 · outbound

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

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Gemini: A Family of Highly Capable Multimodal Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.166884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83428371-49ed-4660-bc88-3037c8d5c170 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.171801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 449d45f8-84ac-4f37-9a0e-9d8c64168bd0 · outbound

This paper cites The Claude 3 model family: Opus, sonnet, haiku.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key The Claude 3 model family: Opus, sonnet, haiku

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.172053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 86c3c1fb-85b7-48cd-91da-ad62094382e7 · outbound

This paper cites ORPO: Mono- lithic preference optimization without reference model.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key ORPO: Mono- lithic preference optimization without reference model

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.157518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c536e5b5-28fe-4aaa-986f-d5e810d2aaa2 · outbound

This paper cites Contrastive preference optimization: Push- ing the boundaries of llm performance in machine trans- lation.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Contrastive preference optimization: Push- ing the boundaries of llm performance in machine trans- lation

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.142286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1335dc48-09b0-4532-a495-baa68fd38166 · outbound

This paper cites Triple Preference Optimization: Achieving Better Alignment using a Single Step Optimization.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Triple Preference Optimization: Achieving Better Alignment using a Single Step Optimization

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.191732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8721bde6-1a57-4391-bd75-7445634dc298 · outbound

This paper cites SimPO: Sim- ple preference optimization with a reference-free reward.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key SimPO: Sim- ple preference optimization with a reference-free reward

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.127155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4bb50a41-5a0c-41b1-a485-bf0739ddd5e2 · outbound

This paper cites Iterative reasoning preference optimization.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Iterative reasoning preference optimization

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.111767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation aa00cb4d-51c0-4ce7-a45e-c54bf929d7ad · outbound

This paper cites Self-Play Preference Optimization for Language Model Alignment.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Self-Play Preference Optimization for Language Model Alignment

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.205960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c64a6d8e-80f4-4c1e-a107-893d1d2e82bc · outbound

This paper cites Visual Hallucination: Definition, Quantification, and Prescriptive Remediations.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Visual Hallucination: Definition, Quantification, and Prescriptive Remediations

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.211038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d19d8510-0363-46b9-b192-eb4b40e5c6e7 · outbound

This paper cites DAMRO: Dive into the attention mechanism of LVLM to re- duce object hallucination.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key DAMRO: Dive into the attention mechanism of LVLM to re- duce object hallucination

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.095070Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 777a128e-793c-4fc8-a5d7-a112630ecce9 · outbound

This paper cites OPERA: Alleviating hallucination in multi- modal large language models via over-trust penalty and retrospection-allocation.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key OPERA: Alleviating hallucination in multi- modal large language models via over-trust penalty and retrospection-allocation

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.079048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ef0df0a2-351d-4744-9733-1cea66f6e946 · outbound

This paper cites Helpd: Miti- gating hallucination of lvlms by hierarchical feedback learn- ing with vision-enhanced penalty decoding.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Helpd: Miti- gating hallucination of lvlms by hierarchical feedback learn- ing with vision-enhanced penalty decoding

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.063157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8836109f-a025-4529-a819-c0e079dcb5fa · outbound

This paper cites Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.231256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8252da87-69f5-4ad6-a06c-6c7b12b35e32 · outbound

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

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Mitigating object hal- lucinations in large vision-language models through visual contrastive decoding

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.046929Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7d9397db-3e03-4d68-9e21-c397716597dc · outbound

This paper cites Less is more: Miti- gating multimodal hallucination from an EOS decision per- spective.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Less is more: Miti- gating multimodal hallucination from an EOS decision per- spective

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.030715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 29fe357d-f98e-42da-8ccd-ca8ebc6b1c76 · outbound

This paper cites Skip \n: A Simple Method to Reduce Hallucination in Large Vision-Language Models.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key Skip \n: A Simple Method to Reduce Hallucination in Large Vision-Language Models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-10T19:52:09.245927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6253e0e-6867-4a77-995a-fb7d4f6a39fe · outbound

This paper cites copied content.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key copied content

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:10.013451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation be1a6d8c-72ea-436e-aaa8-58f17ceca012 · outbound

This paper cites - 3 for a sentence that is largely correct but needs minor tweaks, like an accurate object described with an incorrect count or size.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key - 3 for a sentence that is largely correct but needs minor tweaks, like an accurate object described with an incorrect count or size

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:09.995124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1ae76b77-842c-4f97-9bde-ad89384f92d1 · outbound

This paper cites error type.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key error type

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:09.978184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b79640f2-de8e-40c5-8ae0-bf7a05cb8e64 · outbound

This paper cites object” should be [“dog - > cat.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key object” should be [“dog - > cat

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:09.962200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b46e3862-cb35-4393-8124-615d768b250c · outbound

This paper cites rewritten content.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key rewritten content

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T19:52:09.946461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 89adf544-ecea-4e1e-a1b3-210d7fb5f555 · outbound

This paper cites This should include the reasoning behind changes and the decision to maintain certain parts of the original sentence.

Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key This should include the reasoning behind changes and the decision to maintain certain parts of the original sentence

Reference 68

Resolution: malformed identifier; raw_fallback, observed 2026-08-10T19:52:09.929661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Pith citing papers

Observation fe31c02e-cccb-49f6-842c-5824dc8c4b81 · inbound

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

Hallucination of Multimodal Large Language Models: A Survey Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key

Reference 187

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:33:33.236473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b63e52d1-16a3-44c1-84e6-bdc841b513f5 · inbound

Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation Engineering cites this paper.

Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation Engineering Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-15T20:31:48.323166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef38660f-38ae-4928-9a1b-60b42e4376b4 · inbound

CheXPO: Preference Optimization for Chest X-ray VLMs with Counterfactual Rationale cites this paper.

CheXPO: Preference Optimization for Chest X-ray VLMs with Counterfactual Rationale Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T18:55:17.717469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33cfd47e-d5b3-4823-b6b4-d8363730ad96 · inbound

HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering cites this paper.

HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key

Reference 250

Resolution: verified exact; arxiv_id, observed 2026-05-09T23:54:45.317588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3c217c3a-5f0c-41d5-8711-5dfd85e60f74 · inbound

Self-Captioning Multimodal Interaction Tuning: Amplifying Exploitable Redundancies for Robust Vision Language Models cites this paper.

Self-Captioning Multimodal Interaction Tuning: Amplifying Exploitable Redundancies for Robust Vision Language Models Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-05-12T01:46:14.886071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a8db81a4-0bd8-45aa-8a80-ffbc685a1d5a · inbound

Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs cites this paper.

Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMs Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-07-03T10:48:02.094195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a3da02ca-4b98-4583-88b2-3700299ab982 · inbound

Vision-driven Preference Synthesis for Mitigating Hallucinations in VLMs cites this paper.

Vision-driven Preference Synthesis for Mitigating Hallucinations in VLMs Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-07-01T15:35:47.652225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.