Artificial Aphasias in Lesioned Language Models
Aphasias, selective language impairments which can arise from brain damage, reveal the functional organization of human language by providing causal links between affected brain regions and specific symptom profiles. Drawing on this literature, we introduce an aphasia-inspired technique to characterize the emergent functional organization of language models (LMs). We ``lesion'' (zero-out) model parameters and measure the effects of this intervention against clinical aphasia symptoms, as diagnosed by the Text Aphasia Battery (TAB). When applied to 112,426 outputs from five 1B-scale LMs, the full range of evaluated symptoms surface, but in distributions largely distinct from those of humans. Our method uncovers broad symptom-profile differences between attention components (query, key, value, output) and feed-forward components (up, gate, down), with weaker evidence for differences among components within the same mechanism. We also find an effect of depth, where lesions in early layers disproportionately cause syntactic and semantic symptoms while late-middle layers yield higher rates of phonological and fluency deficits. Although some LM lesions induce quantitatively more similar profiles to some human aphasia types than others, qualitative differences in symptom patterns between LMs and humans suggest that aphasia syndromes are heavily influenced by the details of learning and processing rather than being a domain-invariant consequence of disrupted language processing.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Beyond Binary: Multiclass Paraphasia Detection with Generative Pretrained Transformers and End-to-End Models
Aphasia is a language disorder that can lead to speech errors known as paraphasias, which involve the misuse, substitution, or invention of words. Automatic paraphasia detection can help those with Aphasia by facilitatin…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionSeq2seq for Automatic Paraphasia Detection in Aphasic Speech
Paraphasias are speech errors that are often characteristic of aphasia and they represent an important signal in assessing disease severity and subtype. Traditionally, clinicians manually identify paraphasias by transcri…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionComputational Lesions in Multilingual Language Models Separate Shared and Language-specific Brain Alignment
How the brain supports language across different languages is a basic question in neuroscience and a useful test for multilingual artificial intelligence. Neuroimaging has identified language-responsive brain regions acr…
Modeling Human Exploration Through Resource-Rational Reinforcement Learning
Equipping artificial agents with useful exploration mechanisms remains a challenge to this day. Humans, on the other hand, seem to manage the trade-off between exploration and exploitation effortlessly. In the present ar…
Meta-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1The minimal computational substrate of fluid intelligence
The quantification of cognitive powers rests on identifying a behavioural task that depends on them. Such dependence cannot be assured, for the powers a task invokes cannot be experimentally controlled or constrained a p…
Inductive BiasSpecificity