English
Related papers

Related papers: Context-Free Synthetic Data Mitigates Forgetting

200 papers

Tracking how data is mentioned and used in research papers provides critical insights for improving data discoverability, quality, and production. However, manually identifying and classifying dataset mentions across vast academic…

Computation and Language · Computer Science 2025-02-17 Aivin V. Solatorio , Rafael Macalaba , James Liounis

We lack a systematic understanding of the effects of fine-tuning (via methods such as instruction-tuning or reinforcement learning from human feedback), particularly on tasks outside the narrow fine-tuning distribution. In a simplified…

Computation and Language · Computer Science 2024-04-16 Suhas Kotha , Jacob Mitchell Springer , Aditi Raghunathan

Large Language Models (LLMs) struggle with long-context reasoning, not only due to the quadratic scaling of computational complexity with sequence length but also because of the scarcity and expense of annotating long-context data. There…

Computation and Language · Computer Science 2025-04-18 Linda He , Jue Wang , Maurice Weber , Shang Zhu , Ben Athiwaratkun , Ce Zhang

In this paper, we explore the utility of translationese as synthetic data created using machine translation for pre-training language models (LMs) for low-resource languages (LRLs). Our simple methodology consists of translating large…

Computation and Language · Computer Science 2025-07-08 Meet Doshi , Raj Dabre , Pushpak Bhattacharyya

Recently proposed evaluation benchmarks aim to characterize the effective context length and the forgetting tendencies of large language models (LLMs). However, these benchmarks often rely on simplistic 'needle in a haystack' retrieval or…

Computation and Language · Computer Science 2025-10-07 Raquib Bin Yousuf , Aadyant Khatri , Shengzhe Xu , Mandar Sharma , Naren Ramakrishnan

We show that in language learning, contrary to received wisdom, keeping exceptional training instances in memory can be beneficial for generalization accuracy. We investigate this phenomenon empirically on a selection of benchmark natural…

Computation and Language · Computer Science 2007-05-23 Walter Daelemans , Antal van den Bosch , Jakub Zavrel

Existing studies addressing gender bias of pre-trained language models, usually build a small gender-neutral data set and conduct a second phase pre-training on the model with such data. However, given the limited size and concentrated…

Computation and Language · Computer Science 2023-07-03 Zahra Fatemi , Chen Xing , Wenhao Liu , Caiming Xiong

The phenomenon of model collapse, introduced in (Shumailov et al., 2023), refers to the deterioration in performance that occurs when new models are trained on synthetic data generated from previously trained models. This recursive training…

Machine Learning · Computer Science 2024-04-09 Mohamed El Amine Seddik , Suei-Wen Chen , Soufiane Hayou , Pierre Youssef , Merouane Debbah

Synthetic data is a standard component in training large language models, yet systematic comparisons across design dimensions, including rephrasing strategy, generator model, and source data, remain absent. We conduct extensive controlled…

On-the-fly retrieval of relevant knowledge has proven an essential element of reliable systems for tasks such as open-domain question answering and fact verification. However, because retrieval systems are not perfect, generation models are…

Computation and Language · Computer Science 2023-11-15 Zhiruo Wang , Jun Araki , Zhengbao Jiang , Md Rizwan Parvez , Graham Neubig

Controlling the output of Large Language Models (LLMs) through context-sensitive constraints has emerged as a promising approach to overcome the limitations of Context-Free Grammars (CFGs) in guaranteeing generation validity. However, such…

Computation and Language · Computer Science 2026-04-14 Mohammad Albinhassan , Pranava Madhyastha , Mark Law , Alessandra Russo

Long-context LLMs are increasingly in demand for applications such as retrieval-augmented generation. To defray the cost of pretraining LLMs over long contexts, recent work takes an approach of synthetic context extension: fine-tuning LLMs…

Computation and Language · Computer Science 2025-05-29 Xinyu Zhao , Fangcong Yin , Greg Durrett

Large language models (LLMs) can be leveraged to help with writing formulas in spreadsheets, but resources on these formulas are scarce, impacting both the base performance of pre-trained models and limiting the ability to fine-tune them.…

Computation and Language · Computer Science 2025-07-14 Usneek Singh , José Cambronero , Sumit Gulwani , Aditya Kanade , Anirudh Khatry , Vu Le , Mukul Singh , Gust Verbruggen

A standard practice when using large language models is for users to supplement their instruction with an input context containing new information for the model to process. However, models struggle to reliably follow the input context,…

Machine Learning · Computer Science 2025-04-22 Sachin Goyal , Christina Baek , J. Zico Kolter , Aditi Raghunathan

Pretrained language models have improved zero-shot text classification by allowing the transfer of semantic knowledge from the training data in order to classify among specific label sets in downstream tasks. We propose a simple way to…

Computation and Language · Computer Science 2023-10-24 Lingyu Gao , Debanjan Ghosh , Kevin Gimpel

Large Language Models (LLMs) exhibit strong general language capabilities. However, fine-tuning these models on domain-specific tasks often leads to catastrophic forgetting, where the model overwrites or loses essential knowledge acquired…

Computation and Language · Computer Science 2025-02-18 Shezheng Song , Hao Xu , Jun Ma , Shasha Li , Long Peng , Qian Wan , Xiaodong Liu , Jie Yu

Synthetic data has been proposed as a solution to address the issue of high-quality data scarcity in the training of large language models (LLMs). Studies have shown that synthetic data can effectively improve the performance of LLMs on…

Computation and Language · Computer Science 2024-06-19 Jie Chen , Yupeng Zhang , Bingning Wang , Wayne Xin Zhao , Ji-Rong Wen , Weipeng Chen

Inorganic synthesis planning currently relies primarily on heuristic approaches or machine-learning models trained on limited datasets, which constrains its generality. We demonstrate that language models, without task-specific fine-tuning,…

Materials Science · Physics 2025-06-17 Thorben Prein , Elton Pan , Janik Jehkul , Steffen Weinmann , Elsa A. Olivetti , Jennifer L. M. Rupp

Machine translation (MT) models used in industries with constantly changing topics, such as translation or news agencies, need to adapt to new data to maintain their performance over time. Our aim is to teach a pre-trained MT model to…

Computation and Language · Computer Science 2021-04-01 Farid Arthaud , Rachel Bawden , Alexandra Birch

Long-context modelling for large language models (LLMs) has been a key area of recent research because many real world use cases require reasoning over longer inputs such as documents. The focus of research into modelling long context has…

Computation and Language · Computer Science 2025-02-24 Wenhao Zhu , Pinzhen Chen , Hanxu Hu , Shujian Huang , Fei Yuan , Jiajun Chen , Alexandra Birch