Paper Citation Record · LEDGER

Continual SFT Matches Multimodal RLHF with Negative Supervision

As of 13 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 0 inbound Pith citation observations for arXiv:2411.14797.

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

pith.paper-citation-record.v1
2411.14797 v1

Coverage vector

measured 47 of 47 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T14:58:43.424797Z

measured 47 of 47 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

47 of 47 outbound references displayed

verified exact1
verified fuzzy16
unresolved30
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 216260a6-88c1-4992-b5d7-7eb67303aaa8 · outbound

This paper cites Qwen-vl: A versatile vision-language model for un- derstanding, localization, text reading, and beyond.

Continual SFT Matches Multimodal RLHF with Negative Supervision Qwen-vl: A versatile vision-language model for un- derstanding, localization, text reading, and beyond

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:58:44.874415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation dd7b815f-e7c0-4a0d-b68a-e89f0ae32aad · outbound

This paper cites ShareGPT4V: Improving Large Multi-Modal Models with Better Captions.

Continual SFT Matches Multimodal RLHF with Negative Supervision ShareGPT4V: Improving Large Multi-Modal Models with Better Captions

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:42.716829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3228bcd9-5962-426c-a75d-b0cfe8b77cfc · outbound

This paper cites Self-play fine-tuning converts weak language models to strong language models.

Continual SFT Matches Multimodal RLHF with Negative Supervision Self-play fine-tuning converts weak language models to strong language models

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:58:44.796661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b4e405fd-7802-465a-b135-fa84d92fe807 · outbound

This paper cites How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites.

Continual SFT Matches Multimodal RLHF with Negative Supervision How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:42.726082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7adcc2f-a2a2-4e3f-be14-bc214a52c496 · outbound

This paper cites Scaling instruction- finetuned language models.

Continual SFT Matches Multimodal RLHF with Negative Supervision Scaling instruction- finetuned language models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:42.731110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7bd5977-be98-4522-9546-98d7487d143d · outbound

This paper cites DreamLLM: Synergistic multimodal com- prehension and creation.

Continual SFT Matches Multimodal RLHF with Negative Supervision DreamLLM: Synergistic multimodal com- prehension and creation

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:58:44.676044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6fb41568-fb5b-43c1-93ad-7c7ab2d28a3e · outbound

This paper cites Towards Analyzing and Understanding the Limitations of DPO: A Theoretical Perspective.

Continual SFT Matches Multimodal RLHF with Negative Supervision Towards Analyzing and Understanding the Limitations of DPO: A Theoretical Perspective

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:42.740552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60aff75b-b0e4-404a-9576-bd5797658670 · outbound

This paper cites GQA: A new dataset for real-world visual reasoning and compositional question answering.

Continual SFT Matches Multimodal RLHF with Negative Supervision GQA: A new dataset for real-world visual reasoning and compositional question answering

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:58:44.592976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c9148c5a-5ee2-4f7d-b2e3-1c9ce62084fb · outbound

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

Continual SFT Matches Multimodal RLHF with Negative Supervision Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:42.863703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afb2b299-70bc-4c87-a29e-5d634b8226a5 · outbound

This paper cites Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language Models.

Continual SFT Matches Multimodal RLHF with Negative Supervision Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:42.961623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67336aec-9136-451a-a5fc-e9949679a539 · outbound

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

Continual SFT Matches Multimodal RLHF with Negative Supervision Evaluating object hallucination in large vision-language models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:42.966247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca51b88d-cb91-4471-a5e1-e991a12a02ff · outbound

This paper cites Microsoft coco: Common objects in context.

Continual SFT Matches Multimodal RLHF with Negative Supervision Microsoft coco: Common objects in context

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:58:44.544074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation af73828a-48da-4410-ab60-3ae07928687a · outbound

This paper cites Improved Baselines with Visual Instruction Tuning.

Continual SFT Matches Multimodal RLHF with Negative Supervision Improved Baselines with Visual Instruction Tuning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:42.975249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6780e922-21a2-4532-b766-7fd447b1d05d · outbound

This paper cites Llava-next: Im- proved reasoning, ocr, and world knowledge, 2024.

Continual SFT Matches Multimodal RLHF with Negative Supervision Llava-next: Im- proved reasoning, ocr, and world knowledge, 2024

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:42.980350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2f0c405-731c-449b-9866-dd977f7744f6 · outbound

This paper cites Visual instruction tuning.

Continual SFT Matches Multimodal RLHF with Negative Supervision Visual instruction tuning

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:58:44.518424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d472d0a2-332d-4488-a741-661c935fcb61 · outbound

This paper cites MMBench: Is Your Multi-modal Model an All-around Player?.

Continual SFT Matches Multimodal RLHF with Negative Supervision MMBench: Is Your Multi-modal Model an All-around Player?

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:42.989080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a30925e4-dab7-415a-a62f-7d9533e6f59d · outbound

This paper cites Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer.

Continual SFT Matches Multimodal RLHF with Negative Supervision Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:42.993918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a149c74-bc1f-48bd-bcf7-914f3eab9554 · outbound

This paper cites Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment.

Continual SFT Matches Multimodal RLHF with Negative Supervision Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:42.998808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c36a4d7-0de0-47d1-8af0-179aa8c5939c · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering.

Continual SFT Matches Multimodal RLHF with Negative Supervision Learn to explain: Multimodal reasoning via thought chains for science question answering

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:43.005337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54b27ab6-d0a3-4c2e-8615-17d4a70fdf94 · outbound

This paper cites Ocr-vqa: Visual question answering by reading text in images.

Continual SFT Matches Multimodal RLHF with Negative Supervision Ocr-vqa: Visual question answering by reading text in images

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:43.009885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0073ea85-db72-4aca-bd51-d7b67566ff5c · outbound

This paper cites Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization.

Continual SFT Matches Multimodal RLHF with Negative Supervision Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:43.014298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc6b0de0-f74a-44f4-a4ec-85938236add7 · outbound

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

Continual SFT Matches Multimodal RLHF with Negative Supervision Direct preference optimization: Your language model is secretly a reward model

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:58:44.482432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b85c0898-0943-4897-8bac-4a5da5a97b5c · outbound

This paper cites Object hallucination in image cap- tioning.

Continual SFT Matches Multimodal RLHF with Negative Supervision Object hallucination in image cap- tioning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:43.023292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c428b956-4f77-4182-9193-6431105f8112 · outbound

This paper cites Multitask prompted training enables zero-shot task generalization.

Continual SFT Matches Multimodal RLHF with Negative Supervision Multitask prompted training enables zero-shot task generalization

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:58:44.455332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation bacfa353-f4bd-4eb7-8b4c-ab861d80a813 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Continual SFT Matches Multimodal RLHF with Negative Supervision Proximal Policy Optimization Algorithms

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:43.084563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e495b535-fcf1-4180-a3d4-a1768ff997bc · outbound

This paper cites Towards vqa models that can read.

Continual SFT Matches Multimodal RLHF with Negative Supervision Towards vqa models that can read

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:58:44.438925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9360bab2-3464-492d-95d0-f3c01d58014a · outbound

This paper cites Improving Multi-modal Large Language Model through Boosting Vision Capabilities.

Continual SFT Matches Multimodal RLHF with Negative Supervision Improving Multi-modal Large Language Model through Boosting Vision Capabilities

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-08-12T14:58:43.881132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0628616f-3067-4613-8c82-ca2b18bf89e4 · outbound

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

Continual SFT Matches Multimodal RLHF with Negative Supervision Aligning Large Multimodal Models with Factually Augmented RLHF

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:43.100804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0a32663-3ec7-471b-90af-7515e6269bf9 · outbound

This paper cites CogVLM: Visual Expert for Pretrained Language Models.

Continual SFT Matches Multimodal RLHF with Negative Supervision CogVLM: Visual Expert for Pretrained Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:43.106019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fda87008-9453-4592-8f8a-c60a3b90b76f · outbound

This paper cites Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement.

Continual SFT Matches Multimodal RLHF with Negative Supervision Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:43.111187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85960aff-4a04-42e4-9bca-69303c6d15c0 · outbound

This paper cites Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models.

Continual SFT Matches Multimodal RLHF with Negative Supervision Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:43.116549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba68516c-f71c-4423-bcd3-ffdb9bd47ce9 · outbound

This paper cites Finetuned language models are zero-shot learn- ers.

Continual SFT Matches Multimodal RLHF with Negative Supervision Finetuned language models are zero-shot learn- ers

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:58:44.360844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e6e2386f-5a81-483e-8f08-7af1aca2430c · outbound

This paper cites an unresolved cited work.

Continual SFT Matches Multimodal RLHF with Negative Supervision Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:43.127468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d472179-5ac1-45cd-a058-aaaf1c45f832 · outbound

This paper cites Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models.

Continual SFT Matches Multimodal RLHF with Negative Supervision Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:43.132410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c9d3f91-9754-4836-83aa-61b750e7b016 · outbound

This paper cites Is dpo superior to ppo for llm alignment? a comprehensive study.

Continual SFT Matches Multimodal RLHF with Negative Supervision Is dpo superior to ppo for llm alignment? a comprehensive study

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:58:44.258968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f9cbea60-90fa-4966-b69b-2fd59088d728 · outbound

This paper cites MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities.

Continual SFT Matches Multimodal RLHF with Negative Supervision MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:43.142427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation add161f7-45d0-4945-9a34-7804831dca39 · outbound

This paper cites Token-level direct prefer- ence optimization.

Continual SFT Matches Multimodal RLHF with Negative Supervision Token-level direct prefer- ence optimization

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:58:44.192399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 18c45ca8-5129-42e9-9460-eeec3061e06f · outbound

This paper cites ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning.

Continual SFT Matches Multimodal RLHF with Negative Supervision ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:43.151627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad2f2b85-ab4b-4fc2-8a3a-d7efb8b3cadf · outbound

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

Continual SFT Matches Multimodal RLHF with Negative Supervision Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:43.156556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 117b7452-cfa3-4742-9915-59877dfd51ff · outbound

This paper cites Lima: Less is more for alignment.

Continual SFT Matches Multimodal RLHF with Negative Supervision Lima: Less is more for alignment

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:58:44.177098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e6314292-d25f-44ef-ba1e-b1b1035789f1 · outbound

This paper cites Calibrated Self-Rewarding Vision Language Models.

Continual SFT Matches Multimodal RLHF with Negative Supervision Calibrated Self-Rewarding Vision Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:43.287932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32679ab4-f065-4208-9c03-054790116fd6 · outbound

This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.

Continual SFT Matches Multimodal RLHF with Negative Supervision MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:43.351600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36e81391-2f15-4795-b1f8-4a5ccb92b691 · outbound

This paper cites Multi-label self- supervised learning with scene images.

Continual SFT Matches Multimodal RLHF with Negative Supervision Multi-label self- supervised learning with scene images

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:58:44.159954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 3e34811d-7d7c-42f2-9bb1-df6772bee8f3 · outbound

This paper cites Quantized feature distillation for network quantization.

Continual SFT Matches Multimodal RLHF with Negative Supervision Quantized feature distillation for network quantization

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:58:44.143565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d8ef4bab-6bf2-4feb-ac9e-bff7cffd3016 · outbound

This paper cites Self-Supervised Visual Preference Alignment.

Continual SFT Matches Multimodal RLHF with Negative Supervision Self-Supervised Visual Preference Alignment

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:43.414905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44b228c8-8180-46e1-9277-8d27eca911cc · outbound

This paper cites Llava-phi: Efficient multi-modal assistant with small language model.

Continual SFT Matches Multimodal RLHF with Negative Supervision Llava-phi: Efficient multi-modal assistant with small language model

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:58:44.127762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 52625be0-87db-4cb8-a6ca-fd175383b8a7 · outbound

This paper cites Multi: Multimodal understanding leaderboard with text and images.

Continual SFT Matches Multimodal RLHF with Negative Supervision Multi: Multimodal understanding leaderboard with text and images

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-12T14:58:43.424797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.