English
Related papers

Related papers: Overtrained, Not Misaligned

200 papers

As Large Language Models (LLMs) achieve remarkable empirical success through scaling model and data size, pretraining has become increasingly critical yet computationally prohibitive, hindering rapid development. Despite the availability of…

Computation and Language · Computer Science 2026-02-06 Ji Zhao , Yufei Gu , Shitong Shao , Xun Zhou , Liang Xiang , Zeke Xie

Since the release of GPT2-1.5B in 2019, the large language models (LLMs) have evolved from specialized deep models to versatile foundation models. While demonstrating remarkable zero-shot ability, the LLMs still require fine-tuning on local…

Artificial Intelligence · Computer Science 2025-08-07 Yanjie Dong , Haijun Zhang , Chengming Li , Song Guo , Victor C. M. Leung , Xiping Hu

Finetuning is a common practice widespread across different communities to adapt pretrained models to particular tasks. Text classification is one of these tasks for which many pretrained models are available. On the other hand, ensembles…

Computation and Language · Computer Science 2024-10-29 Sebastian Pineda Arango , Maciej Janowski , Lennart Purucker , Arber Zela , Frank Hutter , Josif Grabocka

Recent advances in Large Language Models (LLMs) have led to impressive alignment where models learn to distinguish harmful from harmless queries through supervised finetuning (SFT) and reinforcement learning from human feedback (RLHF). In…

Artificial Intelligence · Computer Science 2025-06-18 Jiahao Yu , Haozheng Luo , Jerry Yao-Chieh Hu , Wenbo Guo , Han Liu , Xinyu Xing

The pretrained large language models (LLMs) are finetuned with labeled data for better instruction following ability and alignment with human values. In this paper, we study the learning dynamics of LLM finetuning on reasoning tasks and…

Computation and Language · Computer Science 2025-09-30 Zhiwen Ruan , Yun Chen , Yutao Hou , Peng Li , Yang Liu , Guanhua Chen

Despite significant advances in alignment techniques, we demonstrate that state-of-the-art language models remain vulnerable to carefully crafted conversational scenarios that can induce various forms of misalignment without explicit…

Computation and Language · Computer Science 2025-08-07 Siddhant Panpatil , Hiskias Dingeto , Haon Park

The EM algorithm is one of the most popular algorithm for inference in latent data models. The original formulation of the EM algorithm does not scale to large data set, because the whole data set is required at each iteration of the…

Machine Learning · Statistics 2019-10-29 Belhal Karimi , Hoi-To Wai , Eric Moulines , Marc Lavielle

The performance of machine learning models under distribution shift has been the focus of the community in recent years. Most of current methods have been proposed to improve the robustness to distribution shift from the algorithmic…

Computer Vision and Pattern Recognition · Computer Science 2022-05-26 Ziquan Liu , Yi Xu , Yuanhong Xu , Qi Qian , Hao Li , Rong Jin , Xiangyang Ji , Antoni B. Chan

It is common practice in deep learning to use overparameterized networks and train for as long as possible; there are numerous studies that show, both theoretically and empirically, that such practices surprisingly do not unduly harm the…

Machine Learning · Computer Science 2020-03-05 Leslie Rice , Eric Wong , J. Zico Kolter

We study the problem of fine-tuning a language model (LM) for a target task by optimally using the information from $n$ auxiliary tasks. This problem has broad applications in NLP, such as targeted instruction tuning and data selection in…

Computation and Language · Computer Science 2025-06-03 Dongyue Li , Ziniu Zhang , Lu Wang , Hongyang R. Zhang

Energy-based models (EBMs) are generative models that are usually trained via maximum likelihood estimation. This approach becomes challenging in generic situations where the trained energy is non-convex, due to the need to sample the Gibbs…

Machine Learning · Computer Science 2022-02-16 Carles Domingo-Enrich , Alberto Bietti , Marylou Gabrié , Joan Bruna , Eric Vanden-Eijnden

While the enormous parameter scale endows Large Models (LMs) with unparalleled performance, it also limits their adaptability across specific tasks. Parameter-Efficient Fine-Tuning (PEFT) has emerged as a critical approach for effectively…

Machine Learning · Computer Science 2025-12-22 Dong Chen , Zhengqing Hu , Shixing Zhao , Yibo Guo

While large language models (LLMs) often adopt finetuning to unlock their capabilities for downstream applications, our understanding on the inductive biases (especially the scaling properties) of different finetuning methods is still…

Computation and Language · Computer Science 2024-02-28 Biao Zhang , Zhongtao Liu , Colin Cherry , Orhan Firat

Understanding whether fine-tuning elicits latent capabilities or teaches new ones is a fundamental question for language model evaluation and safety. We develop a formal information-theoretic framework for quantifying how much predictive…

Machine Learning · Computer Science 2026-01-09 Elizabeth Donoway , Hailey Joren , Fabien Roger , Jan Leike

The Extreme Learning Machine (ELM) is a growing statistical technique widely applied to regression problems. In essence, ELMs are single-layer neural networks where the hidden layer weights are randomly sampled from a specific distribution,…

Machine Learning · Statistics 2025-07-31 Daniela De Canditiis , Fabiano Veglianti

Entity alignment is to find identical entities in different knowledge graphs. Although embedding-based entity alignment has recently achieved remarkable progress, training data insufficiency remains a critical challenge. Conventional…

Artificial Intelligence · Computer Science 2022-03-15 Kexuan Xin , Zequn Sun , Wen Hua , Bing Liu , Wei Hu , Jianfeng Qu , Xiaofang Zhou

Modern deep learning is increasingly characterized by the use of open-weight foundation models that can be fine-tuned on specialized datasets. This has led to a proliferation of expert models and adapters, often shared via platforms like…

Machine Learning · Computer Science 2025-06-18 Stefan Horoi , Guy Wolf , Eugene Belilovsky , Gintare Karolina Dziugaite

Parameter-efficient fine-tuning (PEFT) has emerged as an effective method for adapting pre-trained language models to various tasks efficiently. Recently, there has been a growing interest in transferring knowledge from one or multiple…

Computation and Language · Computer Science 2024-06-07 Zhisheng Lin , Han Fu , Chenghao Liu , Zhuo Li , Jianling Sun

Reward hacking--where agents exploit flaws in imperfect reward functions rather than performing tasks as intended--poses risks for AI alignment. Reward hacking has been observed in real training runs, with coding agents learning to…

Artificial Intelligence · Computer Science 2025-08-26 Mia Taylor , James Chua , Jan Betley , Johannes Treutlein , Owain Evans

Large Language Models (LLMs) are trained with next-token prediction, implemented in autoregressive Transformers via causal masking for parallelism. This creates a subtle misalignment: residual connections tie activations to the current…

Computation and Language · Computer Science 2026-03-03 Jonathan Lys , Vincent Gripon , Bastien Pasdeloup , Axel Marmoret , Lukas Mauch , Fabien Cardinaux , Ghouthi Boukli Hacene
‹ Prev 1 8 9 10 Next ›