Image de couverture de livre

In-Context Learning in Speech Language Models: Analyzing the Role of Acoustic Features, Linguistic Structure, and Induction Heads

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Pouw, Charlotte, Mohebbi, Hosein, Alishahi, Afra, Zuidema, Willem
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A Linguistically Motivated Analysis of Intonational Phrasing in Text-to-Speech Systems: Revealing Gaps in Syntactic Sensitivity
par: Pouw, Charlotte, et autres
Publié: (2025)

Disentangling Textual and Acoustic Features of Neural Speech Representations
par: Mohebbi, Hosein, et autres
Publié: (2024)

Perception of Phonological Assimilation by Neural Speech Recognition Models
par: Pouw, Charlotte, et autres
Publié: (2024)

What do self-supervised speech models know about Dutch? Analyzing advantages of language-specific pre-training
par: Kloots, Marianne de Heer, et autres
Publié: (2025)

Tracking the emergence of linguistic structure in self-supervised models learning from speech
par: Kloots, Marianne de Heer, et autres
Publié: (2026)

How Language Models Prioritize Contextual Grammatical Cues?
par: Amirzadeh, Hamidreza, et autres
Publié: (2024)

Human-like Linguistic Biases in Neural Speech Models: Phonetic Categorization and Phonotactic Constraints in Wav2Vec2.0
par: Kloots, Marianne de Heer, et autres
Publié: (2024)

Temporal Dependencies in In-Context Learning: The Role of Induction Heads
par: Bajaj, Anooshka, et autres
Publié: (2026)

Linguistic Structure Induction from Language Models
par: Momen, Omar
Publié: (2024)

On the Emergence of Induction Heads for In-Context Learning
par: Musat, Tiberiu, et autres
Publié: (2025)

Gender Disambiguation in Machine Translation: Diagnostic Evaluation in Decoder-Only Architectures
par: Manna, Chiara, et autres
Publié: (2026)

On the reliability of feature attribution methods for speech classification
par: Shen, Gaofei, et autres
Publié: (2025)

Identifying Semantic Induction Heads to Understand In-Context Learning
par: Ren, Jie, et autres
Publié: (2024)

DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers
par: Langedijk, Anna, et autres
Publié: (2023)

Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence
par: Minegishi, Gouki, et autres
Publié: (2025)

Findings of the BlackboxNLP 2025 Shared Task: Localizing Circuits and Causal Variables in Language Models
par: Arad, Dana, et autres
Publié: (2025)

Induction Head Toxicity Mechanistically Explains Repetition Curse in Large Language Models
par: Wang, Shuxun, et autres
Publié: (2025)

Structured Voronoi Sampling
par: Amini, Afra, et autres
Publié: (2023)

Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers
par: Chen, Siyu, et autres
Publié: (2024)

AdParaphrase: Paraphrase Dataset for Analyzing Linguistic Features toward Generating Attractive Ad Texts
par: Murakami, Soichiro, et autres
Publié: (2025)

Analyzing the Attention Heads for Pronoun Disambiguation in Context-aware Machine Translation Models
par: Mąka, Paweł, et autres
Publié: (2024)

SLAM: Structural Linguistic Activation Marking for Language Models
par: Harel-Canada, Fabrice, et autres
Publié: (2026)

ContextGuard: Structured Self-Auditing for Context Learning in Language Models
par: Jin, Hongbo, et autres
Publié: (2026)

Analyzing Multi-Head Attention on Trojan BERT Models
par: Wang, Jingwei
Publié: (2024)

Can Large Language Models Code Like a Linguist?: A Case Study in Low Resource Sound Law Induction
par: Naik, Atharva, et autres
Publié: (2024)

Better Estimation of the Kullback--Leibler Divergence Between Language Models
par: Amini, Afra, et autres
Publié: (2025)

Grammar Induction from Visual, Speech and Text
par: Zhao, Yu, et autres
Publié: (2024)

Linguistic Features Extracted by GPT-4 Improve Alzheimer's Disease Detection based on Spontaneous Speech
par: Heitz, Jonathan, et autres
Publié: (2024)

The Role of Diversity in In-Context Learning for Large Language Models
par: Xiao, Wenyang, et autres
Publié: (2025)

Exploring In-Context Learning of Textless Speech Language Model for Speech Classification Tasks
par: Hsu, Ming-Hao, et autres
Publié: (2023)

Syntactic Control of Language Models by Posterior Inference
par: Xefteri, Vicky, et autres
Publié: (2025)

Induction Signatures Are Not Enough: A Matched-Compute Study of Load-Bearing Structure in In-Context Learning
par: Sabry, Mohammed, et autres
Publié: (2025)

Undesirable Biases in NLP: Addressing Challenges of Measurement
par: van der Wal, Oskar, et autres
Publié: (2022)

Analyzing the Role of Semantic Representations in the Era of Large Language Models
par: Jin, Zhijing, et autres
Publié: (2024)

Do Language Models Exhibit Human-like Structural Priming Effects?
par: Jumelet, Jaap, et autres
Publié: (2024)

Inductive Linguistic Reasoning with Large Language Models
par: Ramji, Raghav, et autres
Publié: (2024)

Linguistic Profiling of a Neural Language Model
par: Miaschi, Alessio, et autres
Publié: (2020)

Context Structure Reshapes the Representational Geometry of Language Models
par: Hosseini, Eghbal A., et autres
Publié: (2026)

Context-level Language Modeling by Learning Predictive Context Embeddings
par: Dai, Beiya, et autres
Publié: (2025)

Hate Speech Detection using Large Language Models with Data Augmentation and Feature Enhancement
par: Nge, Brian Jing Hong, et autres
Publié: (2026)