Cover Image

PreFT: Prefill-only finetuning for efficient inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lanpouthakoun, Andrew, Arora, Aryaman, Wu, Zhengxuan, Pai, Dhruv, Keigwin, Ben, Jurafsky, Dan, Potts, Christopher
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computation and Language Systems and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ReFT: Representation Finetuning for Language Models
by: Wu, Zhengxuan, et al.
Published: (2024)

CausalGym: Benchmarking causal interpretability methods on linguistic tasks
by: Arora, Aryaman, et al.
Published: (2024)

Bayesian scaling laws for in-context learning
by: Arora, Aryaman, et al.
Published: (2024)

AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
by: Wu, Zhengxuan, et al.
Published: (2025)

Improved Representation Steering for Language Models
by: Wu, Zhengxuan, et al.
Published: (2025)

Mechanistic evaluation of Transformers and state space models
by: Arora, Aryaman, et al.
Published: (2025)

ADAG: Automatically Describing Attribution Graphs
by: Arora, Aryaman, et al.
Published: (2026)

Language Model Circuits Are Sparse in the Neuron Basis
by: Arora, Aryaman, et al.
Published: (2026)

A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments
by: Wu, Zhengxuan, et al.
Published: (2024)

pyvene: A Library for Understanding and Improving PyTorch Models via Interventions
by: Wu, Zhengxuan, et al.
Published: (2024)

Kalman Filtering Based Flight Management System Modeling for AAM Aircraft
by: Kandoria, Balram, et al.
Published: (2026)

ReCOGS: How Incidental Details of a Logical Form Overshadow an Evaluation of Semantic Interpretation
by: Wu, Zhengxuan, et al.
Published: (2023)

BERTer: The Efficient One
by: Saligram, Pradyumna, et al.
Published: (2024)

False Friends Are Not Foes: Investigating Vocabulary Overlap in Multilingual Language Models
by: Kallini, Julie, et al.
Published: (2025)

Predicting positive transfer for improved low-resource speech recognition using acoustic pseudo-tokens
by: San, Nay, et al.
Published: (2024)

Understanding 6G through Language Models: A Case Study on LLM-aided Structured Entity Extraction in Telecom Domain
by: Yuan, Ye, et al.
Published: (2025)

Benign Nonconvex Landscapes in Optimal and Robust Control, Part II: Extended Convex Lifting
by: Zheng, Yang, et al.
Published: (2024)

A Stable Polygamy Approach to Spectrum Access with Channel Reuse
by: Ami, Dan Ben, et al.
Published: (2024)

Subspace Pruning via Principal Vectors for Accurate Koopman-Based Approximations
by: Shah, Dhruv, et al.
Published: (2026)

Controller Design for Bilinear Neural Feedback Loops
by: Shah, Dhruv, et al.
Published: (2025)

A Unified Algebraic Framework for Subspace Pruning in Koopman Operator Approximation via Principal Vectors
by: Shah, Dhruv, et al.
Published: (2026)

Dual-Interaction-Aware Cooperative Control Strategy for Alleviating Mixed Traffic Congestion
by: Liu, Zhengxuan, et al.
Published: (2026)

Airspeed estimation for UAVs using only propeller feedback
by: Ntouros, Evangelos, et al.
Published: (2025)

Policy Optimization of Mixed H2/H-infinity Control: Benign Nonconvexity and Global Optimality
by: Pai, Chih-Fan, et al.
Published: (2026)

Equivariant Filter Design for Range-only SLAM
by: Ge, Yixiao, et al.
Published: (2025)

Linearly Controlled Language Generation with Performative Guarantees
by: Cheng, Emily, et al.
Published: (2024)

Sistemas de control basados en el estandar grafcet para la alteracion de bombas centrifugas
by: Guevara, Andres, et al.
Published: (2024)

Data-Driven Template-Free Invariant Generation
by: Xia, Yuan, et al.
Published: (2023)

Enhancing Hallucination Detection through Noise Injection
by: Liu, Litian, et al.
Published: (2025)

TickTalk -- Timing API for Dynamically Federated Cyber-Physical Systems
by: Iannucci, Bob, et al.
Published: (2019)

Processing Natural Language on Embedded Devices: How Well Do Transformer Models Perform?
by: Sarkar, Souvika, et al.
Published: (2023)

Formal Simulation and Visualisation of Hybrid Programs
by: Mendes, Pedro, et al.
Published: (2024)

PretVM: Predictable, Efficient Virtual Machine for Real-Time Concurrency
by: Lin, Shaokai, et al.
Published: (2024)

A 10.8mW Mixed-Signal Simulated Bifurcation Ising Solver using SRAM Compute-In-Memory with 0.6us Time-to-Solution
by: Dee, Alana Marie, et al.
Published: (2025)

Verifiable Natural Language to Linear Temporal Logic Translation: A Benchmark Dataset and Evaluation Suite
by: English, William H, et al.
Published: (2025)

Language-Aided State Estimation
by: Miyoshi, Yuki, et al.
Published: (2025)

Large Language Models for Power Scheduling: A User-Centric Approach
by: Mongaillard, Thomas, et al.
Published: (2024)

A 16.28 ppm/$^\circ$C Temperature Coefficient, 0.5V Low-Voltage CMOS Voltage Reference with Curvature Compensation
by: Reddy, Harshith, et al.
Published: (2025)

Online Nonstochastic Prediction: Logarithmic Regret via Predictive Online Least Squares
by: Pai, Chih-Fan, et al.
Published: (2026)

Knowledge Boundary Probing and Demand-Guided Intervention for LLM-Based Power System Code Generation
by: Wu, Hui, et al.
Published: (2026)