Cover Image

FlashHead: Efficient Drop-In Replacement for the Classification Head in Language Model Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tranheden, Wilhelm, Ahmed, Shahnawaz, Dubhashi, Devdatt, Matthiesen, Jonna, von Essen, Hannes
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Information Retrieval
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

HeadRank: Decoding-Free Passage Reranking via Preference-Aligned Attention Heads
by: Wang, Juyuan, et al.
Published: (2026)

Learning to Route Queries to Heads for Attention-based Re-ranking with Large Language Models
by: Tian, Yuxing, et al.
Published: (2026)

Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models
by: Jin, Zhuoran, et al.
Published: (2024)

MAGE: Multi-Head Attention Guided Embeddings for Low Resource Sentiment Classification
by: Vashisht, Varun, et al.
Published: (2025)

Multi-Head RAG: Solving Multi-Aspect Problems with LLMs
by: Besta, Maciej, et al.
Published: (2024)

Towards Efficient and Effective Unlearning of Large Language Models for Recommendation
by: Wang, Hangyu, et al.
Published: (2024)

Membership Inference Attack against Large Language Model-based Recommendation Systems: A New Distillation-based Paradigm
by: Cuihong, Li, et al.
Published: (2025)

KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Models
by: Chen, Weijie, et al.
Published: (2024)

Intent Classification on Low-Resource Languages with Query Similarity Search
by: Bhalla, Arjun, et al.
Published: (2025)

A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models
by: Zhuang, Shengyao, et al.
Published: (2023)

Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender System
by: Kim, Sein, et al.
Published: (2024)

Access Paths for Efficient Ordering with Large Language Models
by: Zhao, Fuheng, et al.
Published: (2025)

Web Retrieval-Aware Chunking (W-RAC) for Efficient and Cost-Effective Retrieval-Augmented Generation Systems
by: Allu, Uday, et al.
Published: (2026)

Visual Model Checking: Graph-Based Inference of Visual Routines for Image Retrieval
by: Molina, Adrià, et al.
Published: (2026)

Incorporating Group Prior into Variational Inference for Tail-User Behavior Modeling in CTR Prediction
by: Xu, Han, et al.
Published: (2024)

FBS Model-based Maintenance Record Accumulation for Failure-Cause Inference in Manufacturing Systems
by: Fujiu, Takuma, et al.
Published: (2025)

Enhancing Performance and Scalability of Large-Scale Recommendation Systems with Jagged Flash Attention
by: Xu, Rengan, et al.
Published: (2024)

Lookahead: An Inference Acceleration Framework for Large Language Model with Lossless Generation Accuracy
by: Zhao, Yao, et al.
Published: (2023)

Spatial Information Integration in Small Language Models for Document Layout Generation and Classification
by: Melendez, Pablo, et al.
Published: (2025)

Counterfactual Inference for Eliminating Sentiment Bias in Recommender Systems
by: Pan, Le, et al.
Published: (2025)

LIBER: Lifelong User Behavior Modeling Based on Large Language Models
by: Zhu, Chenxu, et al.
Published: (2024)

RecExplainer: Aligning Large Language Models for Explaining Recommendation Models
by: Lei, Yuxuan, et al.
Published: (2023)

A Survey on Large Language Models for Recommendation
by: Wu, Likang, et al.
Published: (2023)

On-Device Large Language Models for Sequential Recommendation
by: Xia, Xin, et al.
Published: (2026)

Representation Learning with Large Language Models for Recommendation
by: Ren, Xubin, et al.
Published: (2023)

RAGdb: A Zero-Dependency, Embeddable Architecture for Multimodal Retrieval-Augmented Generation on the Edge
by: Khalid, Ahmed Bin
Published: (2025)

Modeling User Viewing Flow Using Large Language Models for Article Recommendation
by: Liu, Zhenghao, et al.
Published: (2023)

Exploring $\ell_0$ Sparsification for Inference-free Sparse Retrievers
by: Shen, Xinjie, et al.
Published: (2025)

Enhancing ID-based Recommendation with Large Language Models
by: Chen, Lei, et al.
Published: (2024)

Unlocking the Potential of Large Language Models for Explainable Recommendations
by: Luo, Yucong, et al.
Published: (2023)

The Evolution of Reranking Models in Information Retrieval: From Heuristic Methods to Large Language Models
by: Pandit, Tejul, et al.
Published: (2025)

Hierarchical Tree Search-based User Lifelong Behavior Modeling on Large Language Model
by: Xia, Yu, et al.
Published: (2025)

LLM2Rec: Large Language Models Are Powerful Embedding Models for Sequential Recommendation
by: He, Yingzhi, et al.
Published: (2025)

Graph Contrastive Learning on Multi-label Classification for Recommendations
by: Wu, Jiayang, et al.
Published: (2025)

Taxonomy Inference for Tabular Data Using Large Language Models
by: Wu, Zhenyu, et al.
Published: (2025)

Towards Competitive Search Relevance For Inference-Free Learned Sparse Retrievers
by: Geng, Zhichao, et al.
Published: (2024)

GLIER: Generative Legal Inference and Evidence Ranking for Legal Case Retrieval
by: Li, Minghan, et al.
Published: (2026)

Efficient Evaluation of Large Language Models via Collaborative Filtering
by: Zhong, Xu-Xiang, et al.
Published: (2025)

VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration
by: Geng, Jiahui, et al.
Published: (2025)

Mitigating Propensity Bias of Large Language Models for Recommender Systems
by: Zhang, Guixian, et al.
Published: (2024)