English
Related papers

Related papers: The Delta Learning Hypothesis: Preference Tuning o…

200 papers

Reinforcement learning is used to align language models with human preference signals after first pre-training the model to predict the next token of text within a large corpus using likelihood maximization. Before being deployed in a…

Computation and Language · Computer Science 2024-08-30 Alec Solway

Recent work has demonstrated that using parameter efficient tuning techniques such as prefix tuning (or P-tuning) on pretrained language models can yield performance that is comparable or superior to fine-tuning while dramatically reducing…

Computation and Language · Computer Science 2023-06-30 Stephen Obadinma , Hongyu Guo , Xiaodan Zhu

We introduce Integrated Weak Learning, a principled framework that integrates weak supervision into the training process of machine learning models. Our approach jointly trains the end-model and a label model that aggregates multiple…

Machine Learning · Computer Science 2022-06-22 Peter Hayes , Mingtian Zhang , Raza Habib , Jordan Burgess , Emine Yilmaz , David Barber

Data selection for finetuning Large Language Models (LLMs) can be framed as a budget-constrained optimization problem: maximizing a model's downstream performance under a strict training data budget. Solving this problem is generally…

Machine Learning · Computer Science 2025-10-01 Animesh Jha , Harshit Gupta , Ananjan Nandi

It is common in deep learning to warm up the learning rate $\eta$, often by a linear schedule between $\eta_{\text{init}} = 0$ and a predetermined target $\eta_{\text{trgt}}$. In this paper, we show through systematic experiments using SGD…

Machine Learning · Computer Science 2024-11-05 Dayal Singh Kalra , Maissam Barkeshli

The impact of different multilingual data mixtures in pretraining large language models (LLMs) has been a topic of ongoing debate, often raising concerns about potential trade-offs between language coverage and model performance (i.e., the…

Computation and Language · Computer Science 2025-10-31 Negar Foroutan , Paul Teiletche , Ayush Kumar Tarun , Antoine Bosselut

Language models are known to encode a great amount of factual knowledge through pretraining. However, such knowledge might be insufficient to cater to user requests, requiring the model to integrate external knowledge sources and adhere to…

Computation and Language · Computer Science 2024-07-19 Sizhe Zhou , Sha Li , Yu Meng , Yizhu Jiao , Heng Ji , Jiawei Han

Large language model (LLM) alignment is typically achieved through learning from human preference comparisons, making the quality of preference data critical to its success. Existing studies often pre-process raw training datasets to…

Machine Learning · Computer Science 2026-03-17 Zizhuo Zhang , Qizhou Wang , Shanshan Ye , Jianing Zhu , Jiangchao Yao , Bo Han , Masashi Sugiyama

Training deep neural networks requires many training samples, but in practice, training labels are expensive to obtain and may be of varying quality, as some may be from trusted expert labelers while others might be from heuristics or other…

Information Retrieval · Computer Science 2018-06-25 Mostafa Dehghani , Jaap Kamps

The success of modern multimodal representation learning relies on internet-scale datasets. Due to the low quality of a large fraction of raw web data, data curation has become a critical step in the training pipeline. Filtering using a…

Machine Learning · Computer Science 2025-12-17 Divyansh Pareek , Sewoong Oh , Simon S. Du

In this work, we investigate whether small language models can determine high-quality subsets of large-scale text datasets that improve the performance of larger language models. While existing work has shown that pruning based on the…

Machine Learning · Computer Science 2024-06-03 Zachary Ankner , Cody Blakeney , Kartik Sreenivasan , Max Marion , Matthew L. Leavitt , Mansheej Paul

Existing weak supervision approaches use all the data covered by weak signals to train a classifier. We show both theoretically and empirically that this is not always optimal. Intuitively, there is a tradeoff between the amount of…

Machine Learning · Statistics 2023-03-08 Hunter Lang , Aravindan Vijayaraghavan , David Sontag

Aligning language models (LMs) with preferences is an important problem in natural language generation. A key challenge is that preferences are typically provided at the sequence level while LM training and generation both occur at the…

Computation and Language · Computer Science 2025-01-09 Shentao Yang , Shujian Zhang , Congying Xia , Yihao Feng , Caiming Xiong , Mingyuan Zhou

Preference optimization methods such as DPO align large language models (LLMs) using paired comparisons, but their effectiveness can be highly sensitive to the quality and difficulty of preference pairs. A common heuristic treats…

Artificial Intelligence · Computer Science 2026-02-03 Jinlong Pang , Zhaowei Zhu , Na Di , Yichi Zhang , Yaxuan Wang , Chen Qian , Yang Liu

Preference based alignment objectives implicitly assume that all human preferences are expressed with equal strength. In practice, however, preference strength varies across individuals and contexts -- a phenomenon established in behavioral…

Machine Learning · Computer Science 2026-01-13 Saki Imai , Pedram Heydari , Anthony Sicilia , Asteria Kaeberlein , Katherine Atwell , Malihe Alikhani

Studies of reinforcement learning in humans and animals have demonstrated a preference for options that yielded relatively better outcomes in the past, even when those options are associated with lower absolute reward. The present study…

Computation and Language · Computer Science 2024-01-29 William M. Hayes , Nicolas Yax , Stefano Palminteri

Preference-based finetuning of vision--language models (VLMs) is brittle: trivially wrong negatives inject uninformative gradients that destabilize training. We recast alignment as \textbf{learning-dynamics--aware optimization} and…

Machine Learning · Computer Science 2025-10-15 Jusheng Zhang , Kaitong Cai , Jing Yang , Keze Wang

Alignment is a crucial step to enhance the instruction-following and conversational abilities of language models. Despite many recent work proposing new algorithms, datasets, and training pipelines, there is a lack of comprehensive studies…

Computation and Language · Computer Science 2024-10-04 Xiao Yu , Qingyang Wu , Yu Li , Zhou Yu

One-hot labels do not represent soft decision boundaries among concepts, and hence, models trained on them are prone to overfitting. Using soft labels as targets provide regularization, but different soft labels might be optimal at…

Machine Learning · Computer Science 2020-09-22 Nidhi Vyas , Shreyas Saxena , Thomas Voice

Weak supervision searches have in principle the advantages of both being able to train on experimental data and being able to learn distinctive signal properties. However, the practical applicability of such searches is limited by the fact…

High Energy Physics - Phenomenology · Physics 2024-03-05 Hugues Beauchesne , Zong-En Chen , Cheng-Wei Chiang