Pith. sign in

REVIEW 4 cited by

Neuron-Level Knowledge Attribution in Large Language 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 2312.12141 v4 pith:5WCAGBTT submitted 2023-12-19 cs.CL cs.LG

Zeping Yu , Sophia Ananiadou This is my paper
classification cs.CLcs.LG
keywords neuronsknowledgemethodmethodsacrossattributionfinalidentifying
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Identifying important neurons for final predictions is essential for understanding the mechanisms of large language models. Due to computational constraints, current attribution techniques struggle to operate at neuron level. In this paper, we propose a static method for pinpointing significant neurons. Compared to seven other methods, our approach demonstrates superior performance across three metrics. Additionally, since most static methods typically only identify "value neurons" directly contributing to the final prediction, we propose a method for identifying "query neurons" which activate these "value neurons". Finally, we apply our methods to analyze six types of knowledge across both attention and feed-forward network (FFN) layers. Our method and analysis are helpful for understanding the mechanisms of knowledge storage and set the stage for future research in knowledge editing. The code is available on https://github.com/zepingyu0512/neuron-attribution.

Discussion (0). Sign in 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. DTRNet: Dynamic Token Routing Network to Reduce Quadratic Costs in Transformers

    cs.LG 2025-08 conditional novelty 6.0 of 10

    A learned router sends about 90% of tokens through a linear projection path instead of quadratic attention, keeps the MLP for every token, and matches dense Transformer accuracy at roughly 85% of the FLOPs.

  2. GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace

    cs.CL 2025-05 conditional novelty 6.0 of 10

    Detoxifying LLMs by deleting a global, cross-layer 'toxic subspace' from feed-forward weights reduces toxic outputs more than layer-local subspace methods.

  3. Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMs

    cs.CL 2025-05 conditional novelty 5.0 of 10

    Neuron-Fusion selectively restores large-change neurons from a fine-tuned multimodal model and suppresses small changes, improving language retention with modest visual trade-offs.

  4. NEAT: Concept driven Neuron Attribution in LLMs

    cs.CL 2025-08 reject novelty 4.0 of 10

    NEAT identifies concept neurons by feeding a single mean hidden-state vector through the model and ranking neurons by their effect on concept-word probabilities.

Pith tools