3 citations · 7 across the 6 of their papers we have counts for
7 papers
Worse Together: How Performance Breaks Down in Multi-User Multi-Agent Teams
Sahan Paliskara, Nattaput Namchittai, Andrew Lampinen
People are increasingly delegating tasks to AI agents, and those agents are increasingly encountering other people's agents over shared resources such as a codebase, a calendar, or…
Beneath the Surface: Investigating LLMs' Capabilities for Communicating with Subtext
Kabir Ahuja, Yuxuan Li, Andrew Kyle Lampinen
Human communication is fundamentally creative, and often makes use of subtext -- implied meaning that goes beyond the literal content of the text. Here, we systematically study whe…
Improving Latent Generalization Using Test-time Compute
Arslan Chaudhry, Sridhar Thiagarajan, Andrew Lampinen
Language Models (LMs) exhibit two distinct mechanisms for knowledge acquisition: in-weights learning (i.e., encoding information within the model weights) and in-context learning (…
How do language models learn facts? Dynamics, curricula and hallucinations
Nicolas Zucchet, Jörg Bornschein, Stephanie Chan +3
Large language models accumulate vast knowledge during pre-training, yet the dynamics governing this acquisition remain poorly understood. This work investigates the learning dynam…
Naturalistic Computational Cognitive Science: Towards generalizable models and theories that capture the full range of natural behavior
Wilka Carvalho, Andrew Lampinen
How can cognitive science build generalizable theories that span the full scope of natural situations and behaviors? We argue that progress in Artificial Intelligence (AI) offers t…
Rel-A.I.: An Interaction-Centered Approach To Measuring Human-LM Reliance
Kaitlyn Zhou, Jena D. Hwang, Xiang Ren +3
The ability to communicate uncertainty, risk, and limitation is crucial for the safety of large language models. However, current evaluations of these abilities rely on simple cali…
Interpretability Illusions in the Generalization of Simplified Models
Dan Friedman, Andrew Lampinen, Lucas Dixon +2
A common method to study deep learning systems is to use simplified model representations--for example, using singular value decomposition to visualize the model's hidden states in…