Pith. sign in

REVIEW 4 cited by

A Concept-Based Explainability Framework for Large Multimodal Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.08074 v3 pith:2FLSW3JS submitted 2024-06-12 cs.LG cs.AIcs.CLcs.CV

Jayneel Parekh , Pegah Khayatan , Mustafa Shukor , Alasdair Newson , Matthieu Cord This is my paper · ORCID
classification cs.LGcs.AIcs.CLcs.CV
keywords conceptsmodelsmultimodallargelmmsdictionaryevaluateframework
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Large multimodal models (LMMs) combine unimodal encoders and large language models (LLMs) to perform multimodal tasks. Despite recent advancements towards the interpretability of these models, understanding internal representations of LMMs remains largely a mystery. In this paper, we present a novel framework for the interpretation of LMMs. We propose a dictionary learning based approach, applied to the representation of tokens. The elements of the learned dictionary correspond to our proposed concepts. We show that these concepts are well semantically grounded in both vision and text. Thus we refer to these as ``multi-modal concepts''. We qualitatively and quantitatively evaluate the results of the learnt concepts. We show that the extracted multimodal concepts are useful to interpret representations of test samples. Finally, we evaluate the disentanglement between different concepts and the quality of grounding concepts visually and textually. Our code is publicly available at https://github.com/mshukor/xl-vlms

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. TACO: Training-free Sound Prompted Segmentation via Semantically Constrained Audio-visual CO-factorization

    eess.AS 2024-12 conditional novelty 7.0 of 10

    TACO uses semantically constrained co-factorization of frozen CLIP/CLAP features, then prompts FC-CLIP with the identified sounding factor, achieving state-of-the-art unsupervised sound-prompted segmentation without training.

  2. Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens

    cs.CV 2024-11 conditional novelty 6.0 of 10

    The middle layers of LVLMs process visual information in two stages, and amplifying image attention in the first 'enrichment' stage reduces object hallucinations.

  3. The Hyperspherical Geometry of CLIP Latent Space: A Semantic Mixture Model

    cs.LG 2026-07 conditional novelty 5.0 of 10

    CLIP embeddings are modeled as a mixture of von Mises-Fisher distributions on the unit sphere, improving out-of-distribution detection and semantic decomposition over single-Gaussian baselines.

  4. Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey

    cs.CL 2024-12 conditional novelty 4.0 of 10

    A survey maps the field of MLLM explainability and interpretability into data, model, and training and inference perspectives.

Pith tools