6 papers
High Volatility and Action Bias Distinguish LLMs from Humans in Group Coordination
Sahaj Singh Maini, Robert L. Goldstone, Zoran Tiganj
Humans exhibit remarkable abilities to coordinate in groups. As large language models (LLMs) become more capable, it remains an open question whether they can demonstrate comparabl…
Temporal Dependencies in In-Context Learning: The Role of Induction Heads
Anooshka Bajaj, Deven Mahesh Mistry, Sahaj Singh Maini +3
Large language models (LLMs) exhibit strong in-context learning capabilities, but how they track and retrieve information from context remains underexplored. Drawing on the free re…
Who Do LLMs Trust? Human Experts Matter More Than Other LLMs
Anooshka Bajaj, Zoran Tiganj
Large language models (LLMs) increasingly operate in environments where they encounter social information such as other agents' answers, tool outputs, or human recommendations. In…
Beyond Semantics: How Temporal Biases Shape Retrieval in Transformer and State-Space Models
Anooshka Bajaj, Deven Mahesh Mistry, Sahaj Singh Maini +2
In-context learning is governed by both temporal and semantic relationships, shaping how Large Language Models (LLMs) retrieve contextual information. Analogous to human episodic m…
Gradual Forgetting: Logarithmic Compression for Extending Transformer Context Windows
Billy Dickson, Zoran Tiganj
Most approaches to long-context processing increase the complexity of the transformer's internal architecture by integrating mechanisms such as recurrence or auxiliary memory modul…
Vision-language models learn the geometry of human perceptual space
Craig Sanders, Billy Dickson, Sahaj Singh Maini +2
In cognitive science and AI, a longstanding question is whether machines learn representations that align with those of the human mind. While current models show promise, it remain…