Image de couverture de livre

Are BabyLMs Deaf to Gricean Maxims? A Pragmatic Evaluation of Sample-efficient Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Askari, Raha, Zarrieß, Sina, Alacam, Özge, Sieker, Judith
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Child-directed speech facilitates production, not comprehension, in BabyLMs
par: Bunzeck, Bastian, et autres
Publié: (2026)

How Hypocritical Is Your LLM judge? Listener-Speaker Asymmetries in the Pragmatic Competence of Large Language Models
par: Sieker, Judith, et autres
Publié: (2026)

Do Construction Distributions Shape Formal Language Learning In German BabyLMs?
par: Bunzeck, Bastian, et autres
Publié: (2025)

Are BabyLMs Second Language Learners?
par: Edman, Lukas, et autres
Publié: (2024)

LLMs Struggle to Reject False Presuppositions when Misinformation Stakes are High
par: Sieker, Judith, et autres
Publié: (2025)

Can LLMs Ground when they (Don't) Know: A Study on Direct and Loaded Political Questions
par: Lachenmaier, Clara, et autres
Publié: (2025)

Reference Games as a Testbed for the Alignment of Model Uncertainty and Clarification Requests
par: Ali, Manar, et autres
Publié: (2026)

The InviTE Corpus: Annotating Invectives in Tudor English Texts for Computational Modeling
par: Spliethoff, Sophie, et autres
Publié: (2025)

Mask and You Shall Receive: Optimizing Masked Language Modeling For Pretraining BabyLMs
par: Edman, Lukas, et autres
Publié: (2025)

BabyLMs for isiXhosa: Data-Efficient Language Modelling in a Low-Resource Context
par: Matzopoulos, Alexis, et autres
Publié: (2025)

Towards an Analysis of Discourse and Interactional Pragmatic Reasoning Capabilities of Large Language Models
par: Robrecht, Amelie, et autres
Publié: (2024)

Dialogue Is Not Enough to Make a Communicative BabyLM (But Neither Is Developmentally Inspired Reinforcement Learning)
par: Padovani, Francesca, et autres
Publié: (2025)

CLASS-IT: Conversational and Lecture-Aligned Small-Scale Instruction Tuning for BabyLMs
par: Capone, Luca, et autres
Publié: (2025)

BabyLM Turns 3: Call for papers for the 2025 BabyLM workshop
par: Charpentier, Lucas, et autres
Publié: (2025)

The Illusion of Competence: Evaluating the Effect of Explanations on Users' Mental Models of Visual Question Answering Systems
par: Sieker, Judith, et autres
Publié: (2024)

BabyLM Turns 4 and Goes Multilingual: Call for Papers for the 2026 BabyLM Workshop
par: Choshen, Leshem, et autres
Publié: (2026)

Bias Dynamics in BabyLMs: Towards a Compute-Efficient Sandbox for Democratising Pre-Training Debiasing
par: Trhlik, Filip, et autres
Publié: (2026)

Small Language Models Also Work With Small Vocabularies: Probing the Linguistic Abilities of Grapheme- and Phoneme-Based Baby Llamas
par: Bunzeck, Bastian, et autres
Publié: (2024)

[Call for Papers] The 2nd BabyLM Challenge: Sample-efficient pretraining on a developmentally plausible corpus
par: Choshen, Leshem, et autres
Publié: (2024)

Are Multimodal Large Language Models Pragmatically Competent Listeners in Simple Reference Resolution Tasks?
par: Junker, Simeon, et autres
Publié: (2025)

Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora
par: Warstadt, Alex, et autres
Publié: (2025)

BabyLM Challenge: Exploring the Effect of Variation Sets on Language Model Training Efficiency
par: Haga, Akari, et autres
Publié: (2024)

The Frequency Confound in Language-Model Surprisal and Metaphor Novelty
par: Momen, Omar, et autres
Publié: (2026)

Findings of the Second BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora
par: Hu, Michael Y., et autres
Publié: (2024)

BAMBINO-LM: (Bilingual-)Human-Inspired Continual Pretraining of BabyLM
par: Shen, Zhewen, et autres
Publié: (2024)

BabyLM's First Constructions: Causal probing provides a signal of learning
par: Rozner, Joshua, et autres
Publié: (2025)

BabyLM's First Words: Word Segmentation as a Phonological Probing Task
par: Goriely, Zébulon, et autres
Publié: (2025)

Subword models struggle with word learning, but surprisal hides it
par: Bunzeck, Bastian, et autres
Publié: (2025)

SceneGram: Conceptualizing and Describing Tangrams in Scene Context
par: Junker, Simeon, et autres
Publié: (2025)

Resilience through Scene Context in Visual Referring Expression Generation
par: Junker, Simeon, et autres
Publié: (2024)

Model Interpretability and Rationale Extraction by Input Mask Optimization
par: Brinner, Marc, et autres
Publié: (2025)

Teacher Demonstrations in a BabyLM's Zone of Proximal Development for Contingent Multi-Turn Interaction
par: Salhan, Suchir, et autres
Publié: (2025)

Bringing Up a Bilingual BabyLM: Investigating Multilingual Language Acquisition Using Small-Scale Models
par: Zeng, Linda, et autres
Publié: (2026)

Rationalizing Transformer Predictions via End-To-End Differentiable Self-Training
par: Brinner, Marc, et autres
Publié: (2025)

Efficient Scientific Full Text Classification: The Case of EICAT Impact Assessments
par: Brinner, Marc Felix, et autres
Publié: (2025)

Evaluating Diversity in Automatic Poetry Generation
par: Chen, Yanran, et autres
Publié: (2024)

SemCSE: Semantic Contrastive Sentence Embeddings Using LLM-Generated Summaries For Scientific Abstracts
par: Brinner, Marc, et autres
Publié: (2025)

Text or Image? What is More Important in Cross-Domain Generalization Capabilities of Hate Meme Detection Models?
par: Aggarwal, Piush, et autres
Publié: (2024)

A Federated Approach to Few-Shot Hate Speech Detection for Marginalized Communities
par: Ye, Haotian, et autres
Publié: (2024)

Gricean Norms as a Basis for Effective Collaboration
par: Saad, Fardin, et autres
Publié: (2025)