English
Related papers

Related papers: Collapse of Self-trained Language Models

200 papers

The proliferation of AI-generated content online has fueled concerns over \emph{model collapse}, a degradation in future generative models' performance when trained on synthetic data generated by earlier models. Industry leaders, premier…

Machine Learning · Computer Science 2025-03-19 Rylan Schaeffer , Joshua Kazdan , Alvan Caleb Arulandu , Sanmi Koyejo

Neural networks have recently achieved human-level performance on various challenging natural language processing (NLP) tasks, but it is notoriously difficult to understand why a neural network produced a particular prediction. In this…

Computation and Language · Computer Science 2020-05-01 Sharan Narang , Colin Raffel , Katherine Lee , Adam Roberts , Noah Fiedel , Karishma Malkan

Pre-trained language models (e.g. BART) have shown impressive results when fine-tuned on large summarization datasets. However, little is understood about this fine-tuning process, including what knowledge is retained from pre-training time…

Computation and Language · Computer Science 2022-03-16 Tanya Goyal , Jiacheng Xu , Junyi Jessy Li , Greg Durrett

To mitigate societal biases implicitly encoded in recent successful pretrained language models, a diverse array of approaches have been proposed to encourage model fairness, focusing on prompting, data augmentation, regularized fine-tuning,…

Computation and Language · Computer Science 2025-01-30 Jingxuan Xu , Wuyang Chen , Linyi Li , Yao Zhao , Yunchao Wei

When an agent cannot represent a perfectly accurate model of its environment's dynamics, model-based reinforcement learning (MBRL) can fail catastrophically. Planning involves composing the predictions of the model; when flawed predictions…

Machine Learning · Computer Science 2017-07-28 Erik Talvitie

With the development of large language models (LLMs) like the GPT series, their widespread use across various application scenarios presents a myriad of challenges. This review initially explores the issue of domain specificity, where LLMs…

Computation and Language · Computer Science 2023-10-23 Xiaoliang Chen , Liangbin Li , Le Chang , Yunhe Huang , Yuxuan Zhao , Yuxiao Zhang , Dinuo Li

The GPT (Generative Pre-trained Transformer) language models are an artificial intelligence and natural language processing technology that enables automatic text generation. There is a growing interest in applying GPT language models to…

Computers and Society · Computer Science 2024-03-25 Manuel de Buenaga , Francisco Javier Bueno

Task-oriented dialogue systems have been a promising area in the NLP field. Previous work showed the effectiveness of using a single GPT-2 based model to predict belief states and responses via causal language modeling. In this paper, we…

Computation and Language · Computer Science 2021-10-12 Po-Nien Kung , Chung-Cheng Chang , Tse-Hsuan Yang , Hsin-Kai Hsu , Yu-Jia Liou , Yun-Nung Chen

Existing efforts to improve logical reasoning ability of language models have predominantly relied on supervised fine-tuning, hindering generalization to new domains and/or tasks. The development of Large Langauge Models (LLMs) has…

Computation and Language · Computer Science 2024-06-18 Fangkai Jiao , Zhiyang Teng , Bosheng Ding , Zhengyuan Liu , Nancy F. Chen , Shafiq Joty

Language models retain a significant amount of world knowledge from their pre-training stage. This allows knowledgeable models to be applied to knowledge-intensive tasks prevalent in information retrieval, such as ranking or question…

Computation and Language · Computer Science 2023-06-13 Jonas Wallat , Tianyi Zhang , Avishek Anand

Natural language is compositional; the meaning of a sentence is a function of the meaning of its parts. This property allows humans to create and interpret novel sentences, generalizing robustly outside their prior experience. Neural…

Computation and Language · Computer Science 2021-06-30 Henry Conklin , Bailin Wang , Kenny Smith , Ivan Titov

Model editing has become an increasingly popular alternative for efficiently updating knowledge within language models. Current methods mainly focus on reliability, generalization, and locality, with many methods excelling across these…

Artificial Intelligence · Computer Science 2024-10-25 Qi Li , Xiang Liu , Zhenheng Tang , Peijie Dong , Zeyu Li , Xinglin Pan , Xiaowen Chu

Zero-shot cross-lingual transfer by fine-tuning multilingual pretrained models shows promise for low-resource languages, but often suffers from misalignment of internal representations between languages. We hypothesize that even when the…

Computation and Language · Computer Science 2024-09-18 Ryokan Ri , Shun Kiyono , Sho Takase

Large language models such as GPT and Llama are trained with a next-token prediction loss. In this work, we suggest that training language models to predict multiple future tokens at once results in higher sample efficiency. More…

Computation and Language · Computer Science 2026-03-03 Athul Radhakrishnan , Siddhant Mohan , Mahima Sachdeva

Synthetically-generated data plays an increasingly larger role in training large language models. However, while synthetic data has been found to be useful, studies have also shown that without proper curation it can cause LLM performance…

Machine Learning · Computer Science 2025-12-02 Kareem Amin , Sara Babakniya , Alex Bie , Weiwei Kong , Umar Syed , Sergei Vassilvitskii

As artificial intelligence (AI) becomes more widely used, concerns are growing that model collapse could lead to knowledge collapse, i.e. a degradation to a narrow and inaccurate set of ideas. Prior work has demonstrated single-model…

Machine Learning · Computer Science 2026-03-16 Damian Hodel , Jevin D. West

Do language models (LMs) offer insights into human language learning? A common argument against this idea is that because their architecture and training paradigm are so vastly different from humans, LMs can learn arbitrary inputs as easily…

Computation and Language · Computer Science 2025-09-24 Xiulin Yang , Tatsuya Aoyama , Yuekun Yao , Ethan Wilcox

Recent Language Models (LMs) achieve breakthrough performance in code generation when trained on human-authored problems, even solving some competitive-programming problems. Self-play has proven useful in games such as Go, and thus it is…

Machine Learning · Computer Science 2023-04-13 Patrick Haluptzok , Matthew Bowers , Adam Tauman Kalai

Large language models (LLMs) are reshaping how knowledge is produced, with increasing reliance on AI systems for generation, summarization, and reasoning. While prior work has studied cognitive offloading in humans and model collapse in…

Human-Computer Interaction · Computer Science 2026-05-08 Xuening Wu , Yanlan Kang , Qianya Xu , Kexuan Xie , Jiaqi Mi , Honggang Wang , Yubin Liu , Zeping Chen

Humans can retain old knowledge while learning new information, but Large Language Models (LLMs) often suffer from catastrophic forgetting when post-pretrained or supervised fine-tuned (SFT) on domain-specific data. Moreover, for Multimodal…

Computation and Language · Computer Science 2026-04-24 Zilun Zhang , Yutao Sun , Tiancheng Zhao , Leigang Sha , Ruochen Xu , Kyusong Lee , Jianwei Yin