Attribution-based Sparse Activation in Large Language Models.

Jifeng Song, Xiangyu Yin, Boyuan Yang, Kai Huang, Weichen Liu, Wei Gao

Abstract read

In one paragraph

Article in Proceedings of Machine Learning and Systems ..., 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.

0numbers the graph read from it

0cells of the map it votes in

0citing papers in PubMed

–field-weighted citation impact

1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

0 citing papers in PubMed.

No citing paper in PubMed yet.

4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

6 authors.

Jifeng SongDepartment of Electrical and Computer Engineering, University of Pittsburgh, USA.

Xiangyu YinDepartment of Electrical and Computer Engineering, University of Pittsburgh, USA.

Boyuan YangDepartment of Electrical and Computer Engineering, University of Pittsburgh, USA.

Kai HuangDepartment of Electrical and Computer Engineering, University of Pittsburgh, USA.

Weichen LiuDepartment of Electrical and Computer Engineering, University of Pittsburgh, USA.

Wei GaoDepartment of Electrical and Computer Engineering, University of Pittsburgh, USA.

Funding

Advancing telemedicine in pulmonology: acoustic-waveform respiratory evaluation (AWARE) via sensing and machine learning on smartphonesR01HL170368 · NHLBI · INDIANA UNIVERSITY INDIANAPOLIS · PI Erick Forno, Wei Gao · 2024 to 2026

$1.9M

SCH: Real-Time Evaluation of Acute Myocardial Infarction with Multi-Lead ECG Monitoring from Wearable PPG MeasurementsR01HL184168 · NHLBI · UNIVERSITY OF PITTSBURGH AT PITTSBURGH · PI Wei Gao, Aidong ZHANG · 2025 to 2026

$594k

NHLBI NIH HHS R01 HL170368NHLBI NIH HHS R01 HL184168

6 · The paper itself

Abstract

LLM inference is computationally expensive due to the LLM's large parameter sizes. Existing techniques reduce the computing cost via model retraining, but cannot well adapt to different downstream tasks or variant input data at runtime. To avoid such retraining efforts for runtime adaptability, a better option is

Identifiers

PMID42732342

PMCPMC13570667

What OpenQuestion holds

Textmetadata

Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.