{"total":21,"rows":[{"id":"2402.04177","title":"Scaling Laws for Downstream Task Performance of Large Language Models","created":"2024-02-06","cited_by_count":49,"area":null},{"id":"2502.19249","title":"Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases","created":"2025-02-26","cited_by_count":37,"area":null},{"id":"2304.13060","title":"Injecting structural hints: Using language models to study inductive biases in language learning","created":"2023-04-25","cited_by_count":35,"area":null},{"id":"2203.10326","title":"Pretraining with Artificial Language: Studying Transferable Knowledge in Language Models","created":"2022-03-19","cited_by_count":28,"area":null},{"id":"2206.10139","title":"Insights into Pre-training via Simpler Synthetic Tasks","created":"2022-06-21","cited_by_count":26,"area":null},{"id":"2203.04911","title":"DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question Answering","created":"2022-03-09","cited_by_count":15,"area":null},{"id":"2210.10693","title":"Robustness of Demonstration-based Learning Under Limited Data Scenario","created":"2022-10-19","cited_by_count":11,"area":null},{"id":"2312.14378","title":"Multimodal Attention Merging for Improved Speech Recognition and Audio Event Classification","created":"2023-12-22","cited_by_count":10,"area":null},{"id":"2601.21725","title":"Procedural Pretraining: Warming Up Language Models with Abstract Data","created":"2026-01-29","cited_by_count":10,"area":null},{"id":"2212.09864","title":"Synthetic Pre-Training Tasks for Neural Machine Translation","created":"2022-12-19","cited_by_count":8,"area":null},{"id":"2511.13945","title":"Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformers","created":"2025-11-17","cited_by_count":8,"area":null},{"id":"2601.03448","title":"Enhancing Linguistic Competence of Language Models through Pre-training with Language Learning Tasks","created":"2026-01-06","cited_by_count":4,"area":null},{"id":"2505.15769","title":"Transfer of Structural Knowledge from Synthetic Languages","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2608.20442","title":"Stored in Optimizer State, Valued by Later Training: A Causal Account of Subliminal Trait Transfer","created":"2026-08-20","cited_by_count":3,"area":null},{"id":"2403.18031","title":"The Impact of Syntactic and Semantic Proximity on Machine Translation with Back-Translation","created":"2024-03-26","cited_by_count":2,"area":null},{"id":"2303.14011","title":"SPEC: Summary Preference Decomposition for Low-Resource Abstractive Summarization","created":"2023-03-24","cited_by_count":1,"area":null},{"id":"2405.02024","title":"Analyzing Narrative Processing in Large Language Models (LLMs): Using GPT4 to test BERT","created":"2024-05-03","cited_by_count":1,"area":null},{"id":"2604.15503","title":"Brain Score Tracks Shared Properties of Languages: Evidence from Many Natural Languages and Structured Sequences","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2609.17831","title":"Procedural Pretraining for Molecular Property Prediction","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.37631","title":"Procedural Core: A Compact Recurrent Initialization for Vision Transformers","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38764","title":"Lasting Effects of Abstract Pretraining Beyond Perplexity","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}