Related papers: Brain-Language Model Alignment: Insights into the …
The Platonic Representation Hypothesis suggests that neural networks trained on different modalities (e.g., text and images) align and eventually converge toward the same representation of reality. If true, this has significant implications…
We argue that representations in AI models, particularly deep networks, are converging. First, we survey many examples of convergence in the literature: over time and across multiple domains, the ways by which different neural networks…
Research has repeatedly demonstrated that intermediate hidden states extracted from large language models and speech audio models predict measured brain response to natural language stimuli. Yet, very little is known about the…
Understanding whether large language models (LLMs) and the human brain converge on similar computational principles remains a fundamental and important question in cognitive neuroscience and AI. Do the brain-like patterns observed in LLMs…
The Platonic Representation Hypothesis posits that learned representations from models trained on different modalities converge to a shared latent structure of the world. However, this hypothesis has largely been examined in vision and…
The Platonic Representation Hypothesis suggests that representations from neural networks are converging to a common statistical model of reality. We show that the existing metrics used to measure representational similarity are confounded…
Large language models trained under diverse objectives and architectures have been shown to develop increasingly similar internal representations, an observation formalized as the Platonic Representation Hypothesis. Whether this…
Cognitive science and neuroscience have long faced the challenge of disentangling representations of language from representations of conceptual meaning. As the same problem arises in today's language models (LMs), we investigate the…
Recent cognitive modeling studies have reported that larger language models (LMs) exhibit a poorer fit to human reading behavior (Oh and Schuler, 2023b; Shain et al., 2024; Kuribayashi et al., 2024), leading to claims of their cognitive…
Research has repeatedly demonstrated that intermediate hidden states extracted from large language models are able to predict measured brain response to natural language stimuli. Yet, very little is known about the representation properties…
Language models have been shown to be very effective in predicting brain recordings of subjects experiencing complex language stimuli. For a deeper understanding of this alignment, it is important to understand the correspondence between…
Neuroscientists evaluate deep neural networks for natural language processing as possible candidate models for how language is processed in the brain. These models are often trained without explicit linguistic supervision, but have been…
A recent study (Kuribayashi et al., 2025) has shown that human sentence processing behavior, typically measured on syntactically unchallenging constructions, can be effectively modeled using surprisal from early layers of large language…
Previous work has shown correlations between the hidden states of large language models and fMRI brain responses, on language tasks. These correlations have been taken as evidence of the representational similarity of these models and brain…
From extracting features to generating text, the outputs of large language models (LLMs) typically rely on the final layers, following the conventional wisdom that earlier layers capture only low-level cues. However, our analysis shows that…
Artificial and biological systems may evolve similar computational solutions despite fundamental differences in architecture and learning mechanisms -- a form of convergent evolution. We demonstrate this phenomenon through large-scale…
The Strong Platonic Representation Hypothesis suggests that representational convergence in artificial neural networks can be harnessed constructively: embeddings can be translated across models through a universal latent space without…
Over the years, many researchers have seemingly made the same observation: Brain and language model activations exhibit some structural similarities, enabling linear partial mappings between features extracted from neural recordings and…
Recent work has shown that scaling large language models (LLMs) improves their alignment with human brain activity, yet it remains unclear what drives these gains and which representational properties are responsible. Although larger models…
Language Models (LMs) have demonstrated impressive capabilities in solving complex reasoning tasks, particularly when prompted to generate intermediate explanations. However, it remains an open question whether these intermediate reasoning…