Raphaël Millière
YOU?
Author Swipe
View article: Anthropocentric bias in language model evaluation
Anthropocentric bias in language model evaluation Open
Evaluating the cognitive capacities of large language models (LLMs) requires overcoming not only anthropomorphic but also anthropocentric biases. This article identifies two types of anthropocentric bias that have been neglected: overlooki…
View article: Mapping the phenomenology of intranasal 5-MeO-DMT in psychedelic-naïve healthy adults
Mapping the phenomenology of intranasal 5-MeO-DMT in psychedelic-naïve healthy adults Open
5-Methoxy-N,N-dimethyltryptamine (5-MeO-DMT) is a naturally occurring psychedelic tryptamine. Plants containing 5-MeO-DMT have been used throughout history, and in recent years both synthetic and toad-derived 5-MeO-DMT use is being increas…
View article: Micro-phenomenology of immersion and perceived presences under DMT
Micro-phenomenology of immersion and perceived presences under DMT Open
N,N-Dimethyltryptamine (DMT) is a potent psychedelic compound known to induce immersive experiences and perceived encounters with sentient presences. Despite previous research documenting these phenomena, a fine-grained structural analysis…
View article: DMT micro-phenomenology
DMT micro-phenomenology Open
DMT reliably induces profound experiences of immersion in other worlds and encounters with seemingly autonomous presences, yet the lived qualities and unfolding of these experiences remain poorly understood. Using micro-phenomenological in…
View article: Language Models as Models of Language
Language Models as Models of Language Open
This chapter critically examines the potential contributions of modern language models to theoretical linguistics. Despite their focus on engineering goals, these models' ability to acquire sophisticated linguistic knowledge from mere expo…
View article: LLMs as Models for Analogical Reasoning
LLMs as Models for Analogical Reasoning Open
Analogical reasoning -- the capacity to identify and map structural relationships between different domains -- is fundamental to human cognition and learning. Recent studies have shown that large language models (LLMs) can sometimes match …
View article: Philosophy of cognitive science in the age of deep learning
Philosophy of cognitive science in the age of deep learning Open
Deep learning has enabled major advances across most areas of artificial intelligence research. This remarkable progress extends beyond mere engineering achievements and holds significant relevance for the philosophy of cognitive science. …
View article: Philosophy of Cognitive Science in the Age of Deep Learning
Philosophy of Cognitive Science in the Age of Deep Learning Open
Deep learning has enabled major advances across most areas of artificial intelligence research. This remarkable progress extends beyond mere engineering achievements and holds significant relevance for the philosophy of cognitive science. …
View article: A Philosophical Introduction to Language Models - Part II: The Way Forward
A Philosophical Introduction to Language Models - Part II: The Way Forward Open
In this paper, the second of two companion pieces, we explore novel philosophical questions raised by recent progress in large language models (LLMs) that go beyond the classical debates covered in the first part. We focus particularly on …
View article: A Philosophical Introduction to Language Models -- Part I: Continuity With Classic Debates
A Philosophical Introduction to Language Models -- Part I: Continuity With Classic Debates Open
Large language models like GPT-4 have achieved remarkable proficiency in a broad spectrum of language-based tasks, some of which are traditionally associated with hallmarks of human intelligence. This has prompted ongoing disagreements abo…
View article: The Alignment Problem in Context
The Alignment Problem in Context Open
A core challenge in the development of increasingly capable AI systems is to make them safe and reliable by ensuring their behaviour is consistent with human values. This challenge, known as the alignment problem, does not merely apply to …
View article: Decoding In-Context Learning: Neuroscience-inspired Analysis of Representations in Large Language Models
Decoding In-Context Learning: Neuroscience-inspired Analysis of Representations in Large Language Models Open
Large language models (LLMs) exhibit remarkable performance improvement through in-context learning (ICL) by leveraging task-specific examples in the input. However, the mechanisms behind this improvement remain elusive. In this work, we i…
View article: The Altered Xperience Project (AXP): Quantitative and Qualitative Data from a Citizen Science Initiative on the Subjective Experience of Altered States of Consciousness
The Altered Xperience Project (AXP): Quantitative and Qualitative Data from a Citizen Science Initiative on the Subjective Experience of Altered States of Consciousness Open
The Altered Xperience Project (AXP) is an ongoing research project that takes the form of an open citizen science initiative. Its main goal is to systematically collect and consolidate data on the subjective experiences induced by various …
View article: The Vector Grounding Problem
The Vector Grounding Problem Open
Large language models (LLMs) produce seemingly meaningful outputs, yet they are trained on text alone without direct interaction with the world. This leads to a modern variant of the classical symbol grounding problem in AI: can LLMs' inte…
View article: Drug-induced alterations of bodily awareness
Drug-induced alterations of bodily awareness Open
Psychoactive compounds can have more or less noticeable effects on conscious experience, through neuropharmacological pathways involving activation (agonism) or blockade (antagonism) of different neurotransmitter receptors. Some of these c…
View article: Adversarial Attacks on Image Generation With Made-Up Words
Adversarial Attacks on Image Generation With Made-Up Words Open
Text-guided image generation models can be prompted to generate images using nonce words adversarially designed to robustly evoke specific visual concepts. Two approaches for such generation are introduced: macaronic prompting, which invol…
View article: Selfless Memories
Selfless Memories Open
Many authors claim that being conscious constitutively involves being self-conscious, or conscious of oneself . This claim appears to be threatened by reports of ‘selfless’ episodes, or conscious episodes lacking self-consciousness, recent…
View article: Deep Learning and Synthetic Media
Deep Learning and Synthetic Media Open
Deep learning algorithms are rapidly changing the way in which audiovisual media can be produced. Synthetic audiovisual media generated with deep learning - often subsumed colloquially under the label "deepfakes" - have a number of impress…
View article: Drug-Induced Alterations of Bodily Awareness
Drug-Induced Alterations of Bodily Awareness Open
Philosophical and empirical research on bodily awareness has mostly focused so far on bodily disorders – such as anorexia nervosa, somatoparaphrenia, or xenomelia (body integrity dysphoria) – and bodily illusions induced in an experimental…
View article: The varieties of selflessness
The varieties of selflessness Open
Many authors argue that conscious experience involves a sense of self or self-consciousness. According to the strongest version of this claim, there can be no selfless states of consciousness, namely states of consciousness that lack self-…
View article: Radical disruptions of self-consciousness
Radical disruptions of self-consciousness Open
This special issue is about something most of us might find very hard to conceive: states of consciousness in which self-consciousness is radically disrupted or altogether missing.
View article: The multi-dimensional approach to drug-induced states: A commentary on Bayne and Carter’s “dimensions of consciousness and the psychedelic state”
The multi-dimensional approach to drug-induced states: A commentary on Bayne and Carter’s “dimensions of consciousness and the psychedelic state” Open
Bayne and Carter argue that the mode of consciousness induced by psychedelic drugs does not fit squarely within the traditional account of modes as levels of consciousness, and favors instead a multi-dimensional account according to which …
View article: Neural correlates of the DMT experience as assessed via multivariate EEG
Neural correlates of the DMT experience as assessed via multivariate EEG Open
Studying transitions in and out of the altered state of consciousness caused by intravenous (IV) N,N-Dimethyltryptamine (DMT – a fast-acting tryptamine psychedelic) offers a safe and powerful means of advancing knowledge on the neurobiolog…
View article: Psychedelics, Meditation, and Self-Consciousness
Psychedelics, Meditation, and Self-Consciousness Open
In recent years, the scientific study of meditation and psychedelic drugs has seen remarkable developments. The increased focus on meditation in cognitive neuroscience has led to a cross-cultural classification of standard meditation style…
View article: Looking for the Self: Phenomenology, Neurophysiology and Philosophical Significance of Drug-induced Ego Dissolution
Looking for the Self: Phenomenology, Neurophysiology and Philosophical Significance of Drug-induced Ego Dissolution Open
There is converging evidence that high doses of hallucinogenic drugs can produce significant alterations of self-experience, described as the dissolution of the sense of self and the loss of boundaries between self and world. This article …