# Localized Symbolic Knowledge Distillation for Visual Commonsense Models

arXiv: https://arxiv.org/abs/2312.04837 · HTML: https://mlsanity.com/paper/2312.04837/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal distillation, one of 12 directions in Knowledge distillation.
- Builds on 57 of its 75 references that are in the map.
- First posted on arXiv 8 Dec 2023.

## Placed in

- Knowledge distillation / [Multimodal distillation](https://mlsanity.com/distill/multimodal-distillation/)

## Builds on (most cited first, 30 of 57)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022)
- [RegionCLIP: Region-based Language-Image Pretraining](https://mlsanity.com/paper/2112.09106/) (2021)
- [From Recognition to Cognition: Visual Commonsense Reasoning](https://mlsanity.com/paper/1811.10830/) (2018)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language](https://mlsanity.com/paper/2204.00598/) (2022)
- [TVQA: Localized, Compositional Video Question Answering](https://mlsanity.com/paper/1809.01696/) (2018)
- [MERLOT: Multimodal Neural Script Knowledge Models](https://mlsanity.com/paper/2106.02636/) (2021)
- [MovieQA: Understanding Stories in Movies through Question-Answering](https://mlsanity.com/paper/1512.02902/) (2015)
- [Symbolic Knowledge Distillation: from General Language Models to Commonsense Models](https://mlsanity.com/paper/2110.07178/) (2021)
- [Visual Entailment: A Novel Task for Fine-Grained Image Understanding](https://mlsanity.com/paper/1901.06706/) (2019)
- [Connecting Vision and Language with Localized Narratives](https://mlsanity.com/paper/1912.03098/) (2019)
- [WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation](https://mlsanity.com/paper/2201.05955/) (2022)

## Built on by (most cited first, 12 of 12)

- [A Survey on Knowledge Distillation of Large Language Models](https://mlsanity.com/paper/2402.13116/) (2024)
- [Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application](https://mlsanity.com/paper/2407.01885/) (2024)
- [MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answering](https://mlsanity.com/paper/2503.18491/) (2025)
- [HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding](https://mlsanity.com/paper/2412.16158/) (2024)
- [A Survey on Symbolic Knowledge Distillation of Large Language Models](https://mlsanity.com/paper/2408.10210/) (2024)
- [Re-Imagining Multimodal Instruction Tuning: A Representation View](https://mlsanity.com/paper/2503.00723/) (2025)
- [Fact :Teaching MLLMs with Faithful, Concise and Transferable Rationales](https://mlsanity.com/paper/2404.11129/) (2024)
- [MINER: Mining the Underlying Pattern of Modality-Specific Neurons in Multimodal Large Language Models](https://mlsanity.com/paper/2410.04819/) (2024)
- [Synthetic Visual Genome](https://mlsanity.com/paper/2506.07643/) (2025)
- [TriplePlay: Enhancing Federated Learning with CLIP for Non-IID Data and Resource Efficiency](https://mlsanity.com/paper/2409.05347/) (2024)
- [Generating Faithful and Salient Text from Multimodal Data](https://mlsanity.com/paper/2409.03961/) (2024)
- [Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised Dense Video Captioning](https://mlsanity.com/paper/2609.04183/) (2026)

## Abstract (arXiv)

Instruction following vision-language (VL) models offer a flexible interface that supports a broad range of multimodal tasks in a zero-shot fashion. However, interfaces that operate on full images do not directly enable the user to "point to" and access specific regions within images. This capability is important not only to support reference-grounded VL benchmarks, but also, for practical applications that require precise within-image reasoning. We build Localized Visual Commonsense models, which allow users to specify (multiple) regions as input. We train our model by sampling localized commonsense knowledge from a large language model (LLM): specifically, we prompt an LLM to collect commonsense knowledge given a global literal image description and a local literal region description automatically generated by a set of VL models. With a separately trained critic model that selects high-quality examples, we find that training on the localized commonsense corpus can successfully distill existing VL models to support a reference-as-input interface. Empirical results and human evaluations in a zero-shot setup demonstrate that our distillation method results in more precise VL models of reasoning compared to a baseline of passing a generated referring expression to an LLM.