Cover Image

On the generalization of language models from in-context learning and finetuning: a controlled study

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lampinen, Andrew K., Chaudhry, Arslan, Chan, Stephanie C. Y., Wild, Cody, Wan, Diane, Ku, Alex, Bornschein, Jörg, Pascanu, Razvan, Shanahan, Murray, McClelland, James L.
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

How do language models learn facts? Dynamics, curricula and hallucinations
by: Zucchet, Nicolas, et al.
Published: (2025)

Latent learning: episodic memory complements parametric learning by enabling flexible reuse of experiences
by: Lampinen, Andrew Kyle, et al.
Published: (2025)

The broader spectrum of in-context learning
by: Lampinen, Andrew Kyle, et al.
Published: (2024)

Improving Latent Generalization Using Test-time Compute
by: Chaudhry, Arslan, et al.
Published: (2026)

Leta Semadeni's Romansh‐German poetry: Poetic praxis between languages
by: Richard McClelland
Published: (2025)

LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities
by: Schmied, Thomas, et al.
Published: (2025)

Linear representations in language models can change dramatically over a conversation
by: Lampinen, Andrew Kyle, et al.
Published: (2026)

Fine-Tuned In-Context Learners for Efficient Adaptation
by: Bornschein, Jorg, et al.
Published: (2025)

Kalman Filter for Online Classification of Non-Stationary Data
by: Titsias, Michalis K., et al.
Published: (2023)

Agnosticism About Artificial Consciousness
by: McClelland, Tom
Published: (2024)

Agnosticism about artificial consciousness
by: Tom McClelland
Published: (2025)

“Whether my Body Breaks or the Plum Tree Withers”: Iwanaga Maki, Social Welfare Pioneer, and the jūjikai Women's Religious Order
by: Gwyn McClelland
Published: (2024)

Photoshop 6 para dummies / Deke McClelland ; revisado por Barbara Obermeier
by: McClelland, Deke
Published: (2001)

The Natural
by: McClelland, Kate
Published: (2005)

Roman Catholicism and the History of Christianity in Modern Japan
by: Gwyn McClelland
Published: (2025)

Beyond the Carnot limit: work extraction via an entropy battery
by: McClelland, Liam Judd
Published: (2025)

The Education of Women in the United States: A Guide to Theory, Teaching, and Research. Garland Reference Library of Social Science Volume 551. Source Books on Education Volume 23.
by: McClelland, Averil Evans
Published: (1992)

Trends and Issues in the 1993 Professional Education Literature.
by: McClelland, Susan, et al.
Published: (1994)

Reflections on David E. Rumelhart and the Rumelhart Prize
by: James L. McClelland
Published: (2025)

Meta-learning how to Share Credit among Macro-Actions
by: Hosu, Ionel-Alexandru, et al.
Published: (2025)

When can transformers compositionally generalize in-context?
by: Kobayashi, Seijin, et al.
Published: (2024)

Just-in-time and distributed task representations in language models
by: Li, Yuxuan, et al.
Published: (2025)

Learned feature representations are biased by complexity, learning order, position, and more
by: Lampinen, Andrew Kyle, et al.
Published: (2024)

Revisiting Dynamic Evaluation: Online Adaptation for Large Language Models
by: Rannen-Triki, Amal, et al.
Published: (2024)

Modeling Language as a Sequence of Thoughts
by: Borazjanizadeh, Nasim, et al.
Published: (2025)

Seeing Others as Objects: Perceptual Objectification & Affordances
by: Paulina Sliwa, et al.
Published: (2025)

Young Critics with a Passion for Books.
by: Clark, Mary, et al.
Published: (1997)

Routes to Roots: Acquiring Genealogical and Local History Materials in a Large Canadian Public Library
by: McClelland, Arthur G. W.
Published: (2004)

Use of endoparasitic helminths as tags in delineating stocks of American plaice (Hippoglossoides platessoides) from the southern Gulf of St. Lawrence and Cape Breton Shelf
by: McClelland, Gary, et al.
Published: (2007)

Symbol tuning improves in-context learning in language models
by: Wei, Jerry, et al.
Published: (2023)

Language models show human-like content effects on reasoning tasks
by: Dasgupta, Ishita, et al.
Published: (2022)

The in-context inductive biases of vision-language models differ across modalities
by: Allen, Kelsey, et al.
Published: (2025)

Retrieval-Augmented Decision Transformer: External Memory for In-context RL
by: Schmied, Thomas, et al.
Published: (2024)

Lattice: Learning to Efficiently Compress the Memory
by: Karami, Mahdi, et al.
Published: (2025)

Deep Grokking: Would Deep Neural Networks Generalize Better?
by: Fan, Simin, et al.
Published: (2024)

Neural Computation Without Slots: Steps Towards Biologically Plausible Memory and Attention in Natural and Artificial Intelligence
by: Bhandarkar, Shaunak, et al.
Published: (2025)

Round and Round We Go! What makes Rotary Positional Encodings useful?
by: Barbero, Federico, et al.
Published: (2024)

Still "Talking About Large Language Models": Some Clarifications
by: Shanahan, Murray
Published: (2024)

Simulacra as Conscious Exotica
by: Shanahan, Murray
Published: (2024)

Palatable Conceptions of Disembodied Being
by: Shanahan, Murray
Published: (2025)