Imagen de Portada

Filling in the Mechanisms: How do LMs Learn Filler-Gap Dependencies under Developmental Constraints?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Desai, Atrey, Nair, Sathvik
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Clozing the Gap: Exploring Why Language Model Surprisal Outperforms Cloze Surprisal
por: Nair, Sathvik, et al.
Publicado: (2026)

Test-Time Reasoners Are Strategic Multiple-Choice Test-Takers
por: Balepur, Nishant, et al.
Publicado: (2025)

Across the Levels of Analysis: Explaining Predictive Processing in Humans Requires More Than Machine-Estimated Probabilities
por: Nair, Sathvik, et al.
Publicado: (2026)

How Inclusively do LMs Perceive Social and Moral Norms?
por: Galarnyk, Michael, et al.
Publicado: (2025)

How to Make LMs Strong Node Classifiers?
por: Xu, Zhe, et al.
Publicado: (2024)

A Psycholinguistic Evaluation of Language Models' Sensitivity to Argument Roles
por: Lee, Eun-Kyoung Rosa, et al.
Publicado: (2024)

Learning How to Ask: Querying LMs with Mixtures of Soft Prompts
por: Qin, Guanghui, et al.
Publicado: (2021)

Training Bilingual LMs with Data Constraints in the Targeted Language
por: Seto, Skyler, et al.
Publicado: (2024)

What Exactly do Children Receive in Language Acquisition? A Case Study on CHILDES with Automated Detection of Filler-Gap Dependencies
por: Zhou, Zhenghao Herbert, et al.
Publicado: (2026)

Generalizations across filler-gap dependencies in neural language models
por: Howitt, Katherine, et al.
Publicado: (2024)

Lost in Translation: The Algorithmic Gap Between LMs and the Brain
por: Tosato, Tommaso, et al.
Publicado: (2024)

Speakers Fill Lexical Semantic Gaps with Context
por: Pimentel, Tiago, et al.
Publicado: (2020)

Are BabyLMs Second Language Learners?
por: Edman, Lukas, et al.
Publicado: (2024)

Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions
por: Wiegreffe, Sarah, et al.
Publicado: (2024)

Filling the Gap for Uzbek: Creating Translation Resources for Southern Uzbek
por: Mamasaidov, Mukhammadsaid, et al.
Publicado: (2025)

Gap-Filling Prompting Enhances Code-Assisted Mathematical Reasoning
por: Mohammadkhani, Mohammad Ghiasvand
Publicado: (2024)

Linguistic Generalizations are not Rules: Impacts on Evaluation of LMs
por: Weissweiler, Leonie, et al.
Publicado: (2025)

Enhancing Retrieval-Augmented LMs with a Two-stage Consistency Learning Compressor
por: Xu, Chuankai, et al.
Publicado: (2024)

Do Construction Distributions Shape Formal Language Learning In German BabyLMs?
por: Bunzeck, Bastian, et al.
Publicado: (2025)

Anything Goes? A Crosslinguistic Study of (Im)possible Language Learning in LMs
por: Yang, Xiulin, et al.
Publicado: (2025)

Causal Interventions Reveal Shared Structure Across English Filler-Gap Constructions
por: Boguraev, Sasha, et al.
Publicado: (2025)

Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?
por: Bhaskar, Adithya, et al.
Publicado: (2025)

Compositional preference models for aligning LMs
por: Go, Dongyoung, et al.
Publicado: (2023)

Humans and transformer LMs: Abstraction drives language learning
por: Jian, Jasper, et al.
Publicado: (2026)

FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMs
por: Alnuhait, Deema, et al.
Publicado: (2024)

Beyond Pattern Recognition: Probing Mental Representations of LMs
por: Miller, Moritz, et al.
Publicado: (2025)

Crafting In-context Examples according to LMs' Parametric Knowledge
por: Lee, Yoonsang, et al.
Publicado: (2023)

Learning to vary: Teaching LMs to reproduce human linguistic variability in next-word prediction
por: Groot, Tobias, et al.
Publicado: (2025)

Filling in the Clinical Gaps in Benchmark: Case for HealthBench for the Japanese medical system
por: Hisada, Shohei, et al.
Publicado: (2025)

Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models
por: Feng, Shangbin, et al.
Publicado: (2023)

How Non-Linguistic Is the Indus Sign System? A Synthetic-Baseline Scorecard
por: Nair, Ashish
Publicado: (2026)

Child-directed speech facilitates production, not comprehension, in BabyLMs
por: Bunzeck, Bastian, et al.
Publicado: (2026)

Mitigating the Influence of Distractor Tasks in LMs with Prior-Aware Decoding
por: Douglas, Raymond, et al.
Publicado: (2024)

HumanRankEval: Automatic Evaluation of LMs as Conversational Assistants
por: Gritta, Milan, et al.
Publicado: (2024)

A suite of LMs comprehend puzzle statements as well as humans
por: Goldberg, Adele E, et al.
Publicado: (2025)

Studies with impossible languages falsify LMs as models of human language
por: Bowers, Jeffrey S., et al.
Publicado: (2025)

Are You There God? Lightweight Narrative Annotation of Christian Fiction with LMs
por: Hicke, Rebecca M. M., et al.
Publicado: (2025)

Is Self-Supervised Learning Enough to Fill in the Gap? A Study on Speech Inpainting
por: Asaad, Ihab, et al.
Publicado: (2024)

Enabling Approximate Joint Sampling in Diffusion LMs
por: Bansal, Parikshit, et al.
Publicado: (2025)

SoftLMs: Efficient Adaptive Low-Rank Approximation of Language Models using Soft-Thresholding Mechanism
por: Bhatnagar, Priyansh, et al.
Publicado: (2024)