565 citations · 1.1k across the 47 of their papers we have counts for
14 papers · 1 filter
Linear representations in language models can change dramatically over a conversation
Andrew Kyle Lampinen, Yuxuan Li, Eghbal Hosseini +2
Language model representations often contain linear directions that correspond to high-level concepts. Here, we study the dynamics of these representations: how representations evo…
Context Structure Reshapes the Representational Geometry of Language Models
Eghbal A. Hosseini, Yuxuan Li, Yasaman Bahri +2
Large Language Models (LLMs) have been shown to organize the representations of input sequences into straighter neural trajectories in their deep layers, which has been hypothesize…
Just-in-time and distributed task representations in language models
Yuxuan Li, Declan Campbell, Stephanie C. Y. Chan +1
Many of language models' impressive capabilities originate from their in-context learning: based on instructions or examples, they can infer and perform new tasks without weight up…
On the generalization of language models from in-context learning and finetuning: a controlled study
Andrew K. Lampinen, Arslan Chaudhry, Stephanie C. Y. Chan +7
Large language models exhibit exciting capabilities, yet can show surprisingly narrow generalization from finetuning. E.g. they can fail to generalize to simple reversals of relati…
The broader spectrum of in-context learning
Andrew Kyle Lampinen, Stephanie C. Y. Chan, Aaditya K. Singh +1
The ability of language models to learn a task from a few examples in context has generated substantial interest. Here, we provide a perspective that situates this type of supervis…
Evaluating Spatial Understanding of Large Language Models
Yutaro Yamada, Yihan Bao, Andrew K. Lampinen +2
Large language models (LLMs) show remarkable capabilities across a variety of tasks. Despite the models only seeing text in training, several recent studies suggest that LLM repres…
Symbol tuning improves in-context learning in language models
Jerry Wei, Le Hou, Andrew Lampinen +8
We present symbol tuning - finetuning language models on in-context input-label pairs where natural language labels (e.g., "positive/negative sentiment") are replaced with arbitrar…
Machine Psychology
Thilo Hagendorff, Ishita Dasgupta, Marcel Binz +5
Large language models (LLMs) show increasingly advanced emergent capabilities and are being incorporated across various societal domains. Understanding their behavior and reasoning…
Transformers generalize differently from information stored in context vs in weights
Stephanie C. Y. Chan, Ishita Dasgupta, Junkyung Kim +3
Transformer models can use two fundamentally different kinds of information: information stored in weights during training, and information provided ``in-context'' at inference tim…
Can language models handle recursively nested grammatical structures? A case study on comparing models and humans
Andrew Kyle Lampinen
How should we compare the capabilities of language models (LMs) and humans? I draw inspiration from comparative psychology to highlight some challenges. In particular, I consider a…
Language models show human-like content effects on reasoning tasks
Ishita Dasgupta, Andrew K. Lampinen, Stephanie C. Y. Chan +5
Reasoning is a key ability for an intelligent system. Large language models (LMs) achieve above-chance performance on abstract reasoning tasks, but exhibit many imperfections. Howe…
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao +448
Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabil…
Can language models learn from explanations in context?
Andrew K. Lampinen, Ishita Dasgupta, Stephanie C. Y. Chan +6
Language Models (LMs) can perform new tasks by adapting to a few in-context examples. For humans, explanations that connect examples to task principles can improve learning. We the…
One-shot and few-shot learning of word embeddings
Andrew K. Lampinen, James L. McClelland
Standard deep learning systems require thousands or millions of examples to learn a concept, and cannot integrate new concepts easily. By contrast, humans have an incredible abilit…