Pith. sign in

REVIEW 1 cited by

Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers

Not yet reviewed by Pith; the record is open.

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 2311.07470 v2 pith:F5QJZV6K submitted 2023-11-13 cs.CL

classification cs.CL
keywords multi-modalneuronsmethoddesigneditingllmsacademiaapplied
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Understanding the internal mechanisms by which multi-modal large language models (LLMs) interpret different modalities and integrate cross-modal representations is becoming increasingly critical for continuous improvements in both academia and industry. In this paper, we propose a novel method to identify key neurons for interpretability -- how multi-modal LLMs bridge visual and textual concepts for captioning. Our method improves conventional works upon efficiency and applied range by removing needs of costly gradient computation. Based on those identified neurons, we further design a multi-modal knowledge editing method, beneficial to mitigate sensitive words or hallucination. For rationale of our design, we provide theoretical assumption. For empirical evaluation, we have conducted extensive quantitative and qualitative experiments. The results not only validate the effectiveness of our methods, but also offer insightful findings that highlight three key properties of multi-modal neurons: sensitivity, specificity and causal-effect, to shed light for future research.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Seeing It or Not? Interpretable Vision-aware Latent Steering to Mitigate Object Hallucinations

    cs.CV 2025-05 conditional novelty 6.0 of 10

    VaLSe uses attention-based visual contribution maps to steer an LVLM's latent features toward visually grounded content, reducing object hallucinations on several benchmarks while exposing flaws in CHAIR-style evaluation.

Pith tools