Pith. sign in

REVIEW 3 cited by

LLMSteer: Improving Long-Context LLM Inference by Steering Attention on Reused Contexts

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 2411.13009 v2 pith:FGZWM7QN submitted 2024-11-20 cs.LG cs.CL

Zhuohan Gu , Jiayi Yao , Kuntai Du , Junchen Jiang This is my paper
classification cs.LGcs.CL
keywords attentionllmsllmsteersteeringperformancebalancebaselinescompared
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

As large language models (LLMs) show impressive performance on complex tasks, they still struggle with longer contextual understanding and high computational costs. To balance efficiency and quality, we introduce LLMSteer, a fine-tuning-free framework that enhances LLMs through query-independent attention steering. Tested on popular LLMs and datasets, LLMSteer narrows the performance gap with baselines by 65.9% and reduces the runtime delay by up to 4.8x compared to recent attention steering methods.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering Attractors

    cs.LG 2025-10 conditional novelty 7.0 of 10

    Eyes-on-Me makes RAG data poisoning reusable: a transferable attention-steering attractor is optimized once, then combined with different attack payloads at near-zero cost.

  2. Data-Efficient Adaptation of LLMs via Attention Head Reweighting

    cs.LG 2026-07 conditional novelty 5.0 of 10

    Learning a single scalar per attention head lets LLMs adapt to few-shot text classification better than LoRA, with 200–1000x fewer trainable parameters.

  3. Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms

    cs.CL 2025-05 conditional novelty 5.0 of 10

    STA selects sparse autoencoder features by activation amplitude and frequency to build steering vectors that improve LLM safety control over prompt engineering and standard steering.

Pith tools