Imagen de Portada

If You Can't Use Them, Recycle Them: Optimizing Merging at Scale Mitigates Performance Tradeoffs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Khalifa, Muhammad, Tan, Yi-Chern, Ahmadian, Arash, Hosking, Tom, Lee, Honglak, Wang, Lu, Üstün, Ahmet, Sherborne, Tom, Gallé, Matthias
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Agents Explore but Agents Ignore: LLMs Lack Environmental Curiosity
por: Engländer, Leon, et al.
Publicado: (2026)

If You Can't Beat Them, Eat Them – Stinging Nettle
por: NA
Publicado: (1989)

They Can't Hear Us Does Not Mean We Can't Serve Them.
por: McDaniel, Julie Ann
Publicado: (1992)

Library Media Paraprofessionals--We Can't Live without Them!
por: Pawlowski, Connie, et al.
Publicado: (1993)

Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs
por: Ahmadian, Arash, et al.
Publicado: (2024)

State-Funded Informational Databases: You May Lose Them Even if You Use Them!
por: Bell, Mary Ann
Publicado: (2005)

RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs
por: Dang, John, et al.
Publicado: (2024)

CHILL at SemEval-2025 Task 2: You Can't Just Throw Entities and Hope -- Make Your LLM to Get Them Right
por: Lee, Jaebok, et al.
Publicado: (2025)

By Their Fruits You Will Know Them: Comparing Formalizations of Law by the Decisions They Encode
por: Vernie, Julius, et al.
Publicado: (2026)

Why the Center Can't Hold: A Diagnosis of Puritanized America
por: O’Neill, Tom
Publicado: (2019)

Conversations: Love Them, Hate Them, Steer Them
por: Chebrolu, Niranjan, et al.
Publicado: (2025)

Who Are These People and Why Can't We Call Them Librarians? [and] The Non-M.L.S. Professional in a Network Environment.
por: Oetting, Edward C., et al.
Publicado: (1989)

You Have to Grow Wefts to Fold Them
por: Niu, Lauren, et al.
Publicado: (2024)

One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers
por: Abagyan, Diana, et al.
Publicado: (2025)

One Extension to Explain Them All, One Scale-Invariant Spectrum to Test Them All, and in One Model Bind Them
por: Forconi, Matteo, et al.
Publicado: (2025)

The Struggle You Can’t See
por: Lierman, Ash
Publicado: (2024)

Some of Them Want to Use You: Antecedents and Consequences of Supervisors' Employee‐Directed Objectification
por: Katerina Tsantila, et al.
Publicado: (2026)

The New Technologies: What Are They, How Can We Get Them, and Why Don't We Have Them?
por: Lowenthal, Ralph A.
Publicado: (1989)

Freer Arrows and Why You Need Them in Haskell
por: VanDomelen, Grant, et al.
Publicado: (2025)

When People Tell You Who They Are, Believe Them
por: Autumn A. Arnett
Publicado: (2025)

Researching Skills: They Need Them When They Need Them.
por: Burgess, Barbara J.
Publicado: (1987)

Core Competencies: What They Are and How To Use Them.
por: Naylor, Richard J.
Publicado: (2000)

You Can't Fight in Here! This is BBS!
por: Futrell, Richard, et al.
Publicado: (2026)

Reasoning Inconsistencies and How to Mitigate Them in Deep Learning
por: Arakelyan, Erik
Publicado: (2025)

Scalable Data Ablation Approximations for Language Models through Modular Training and Merging
por: Na, Clara, et al.
Publicado: (2024)

Essential Documents for School Libraries: Do You Have Them?
por: MacDonell, Colleen
Publicado: (2004)

Open to Them
por: Rosenfield, Clare
Publicado: (1982)

SimMerge: Learning to Select Merge Operators from Similarity Signals
por: Bolton, Oliver, et al.
Publicado: (2026)

LLMs Can Plan Only If We Tell Them
por: Sel, Bilgehan, et al.
Publicado: (2025)

Compositional Generalisation for Explainable Hate Speech Detection
por: Calabrese, Agostina, et al.
Publicado: (2025)

TRAM: Bridging Trust Regions and Sharpness Aware Minimization
por: Sherborne, Tom, et al.
Publicado: (2023)

You Can't Steal Nothing: Mitigating Prompt Leakages in LLMs via System Vectors
por: Cao, Bochuan, et al.
Publicado: (2025)

Valuable Volunteers: How to Find, Use, and Keep Them
por: McGown, Sue W.
Publicado: (2007)

Human Feedback is not Gold Standard
por: Hosking, Tom, et al.
Publicado: (2023)

Hierarchical Indexing for Retrieval-Augmented Opinion Summarization
por: Hosking, Tom, et al.
Publicado: (2024)

You Can't Spell Tragedy Without Rage
por: Elaine McGirr
Publicado: (2025)

Adaptive Experimentation When You Can't Experiment
por: Zhao, Yao, et al.
Publicado: (2024)

You Can't "Go By The Book" for Library Budget
por: Tanis, Norman E.
Publicado: (1969)

Lend Committee Support When You Can't Be There
Publicado: (2024)

One Model to Forecast Them All and in Entity Distributions Bind Them
por: Bölat, Kutay, et al.
Publicado: (2025)