Papers with human language learning
Babysit A Language Model From Scratch: Interactive Language Learning by Trials and Demonstrations (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models have adopted a non-interactive training paradigm, and refined pre-trained models through feedback afterward. |
| Approach: | They propose a trial-and-demonstration learning framework that incorporates student trials, teacher demonstrations, and a reward conditioned on language competence at various developmental stages. |
| Outcome: | The proposed framework accelerates word acquisition for student models of equal and smaller numbers of parameters and a strong correlation between the frequency of words in trials and learning curves. |
Real-World Compositional Generalization with Disentangled Sequence-to-Sequence Learning (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to compositional generalization have been designed with semantic parsing in mind. |
| Approach: | They propose a disentangled sequence-to-sequence model which encourages more disentanglement and improves its compute and memory efficiency. |
| Outcome: | The proposed model improves generalization performance across existing tasks and datasets and a new machine translation benchmark. |
BabyLM’s First Constructions: Causal interventions provide a signal of learning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent work shows sensitivity to constructions in pretrained language models, but their relevance to human language learning is doubted. |
| Approach: | They use construction grammars to demonstrate sensitivity to constructions in pretrained language models. |
| Outcome: | The proposed models learn diverse constructions even hard cases that are superficially indistinguishable. |
Code-Switching Curriculum Learning for Multilingual Transfer in LLMs (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) exhibit near human-level performance in various tasks, but performance drops after a handful of high-resource languages due to the imbalance in pre-training data. |
| Approach: | They propose a code-switching curriculum learning model to enhance cross-lingual transfer for LLMs by progressively training models with a curriculum consisting of token-level code-changing, sentence-level codeswitching, and monolingual corpora. |
| Outcome: | The proposed model improves language transfer to Korean, with significant gains in Japanese and Indonesian . the proposed model mitigates spurious correlations between language resources and safety alignment . |
Compositional Generalization for Primitive Substitutions (D19-1)
Copied to clipboard
| Challenge: | Existing approaches to encoding compositional generalization are lacking . et al., 2017) argue that neural networks lack compositional ability . |
| Approach: | They propose a method to encode compositionality in neural networks using two representations . they reduce the entropy in each representation to improve generalization . |
| Outcome: | The proposed approach improves performance on five NLP tasks including instruction learning and machine translation. |
Can Large Language Models Understand Internet Buzzwords Through User-Generated Content (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for generating definitions of internet buzzwords rely on user-generated content, such as posts and reviews, to understand them. |
| Approach: | They propose a method to generate accurate buzzword definitions using UGC as examples. |
| Outcome: | The proposed method mirrors human language learning skills and can produce more accurate definitions. |
Large Language Models: The Need for Nuance in Current Debates and a Pragmatic Perspective on Understanding (2023.emnlp-main)
Copied to clipboard
| Challenge: | Current Large Language Models (LLMs) are unparalleled in their ability to generate grammatically correct, fluent text. |
| Approach: | They argue that LLMs only parrot statistical patterns in training data and that language learning in LLM cannot inform human language learning. |
| Outcome: | The proposed model can generate grammatically correct, fluent text without requiring human intervention. |
Mandarin classifier systems optimize to accommodate communicative pressures (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies suggest that gendered languages are inherently optimized to accommodate communicative pressures on language learning and processing. |
| Approach: | They propose to use grammatical or probabilistic modifiers to smooth the entropy of nouns in context to find the same frequency, similarity, and co-occurrence interactions that structure gender systems. |
| Outcome: | The proposed noun classification device is sensitive to frequency, similarity, and co-occurrence interactions that structure gender systems. |
Anything Goes? A Crosslinguistic Study of (Im)possible Language Learning in LMs (2025.acl-long)
Copied to clipboard
| Challenge: | LMs are highly flexible learners, capable of acquiring linguistic patterns beyond those learnable by humans. |
| Approach: | They train LMs to model impossible and typologically unattested languages . they find that the model does not achieve perfect separation between attested and unattest languages - suggesting some human-like inductive biases . |
| Outcome: | The proposed model can largely distinguish attested from impossible languages, but does not achieve perfect separation between them and their impossible counterparts. |