English
Related papers

Related papers: Annotations Mitigate Post-Training Mode Collapse

200 papers

Instruction Fine-Tuning enhances pre-trained language models from basic next-word prediction to complex instruction-following. However, existing One-off Instruction Fine-Tuning (One-off IFT) method, applied on a diverse instruction, may not…

Computation and Language · Computer Science 2024-06-18 Wei Pang , Chuan Zhou , Xiao-Hua Zhou , Xiaojie Wang

Current collaborative perception methods often rely on fully annotated datasets, which can be expensive to obtain in practical situations. To reduce annotation costs, some works adopt sparsely supervised learning techniques and generate…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Yushan Han , Hui Zhang , Honglei Zhang , Jing Wang , Yidong Li

Current foundation models have shown impressive performance across various tasks. However, several studies have revealed that these models are not effective for everyone due to the imbalanced geographical and economic representation of the…

Computer Vision and Pattern Recognition · Computer Science 2024-03-13 Oana Ignat , Longju Bai , Joan Nwatu , Rada Mihalcea

Language models demonstrate remarkable abilities when pre-trained on large text corpora and fine-tuned for specific tasks, but how and why pre-training shapes the success of the final model remains poorly understood. Notably, although…

Despite being highly performant, deep neural networks might base their decisions on features that spuriously correlate with the provided labels, thus hurting generalization. To mitigate this, 'model guidance' has recently gained popularity,…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Sukrut Rao , Moritz Böhle , Amin Parchami-Araghi , Bernt Schiele

Post-training large language models (LLMs) often suffers from catastrophic forgetting, where improvements on a target objective degrade previously acquired capabilities. Recent evidence suggests that this phenomenon is primarily driven by…

Machine Learning · Computer Science 2026-05-07 Xinyu Wang , Changzhi Sun , Yuanbin Wu , Xiaoling Wang

Structured learning is appropriate when predicting structured outputs such as trees, graphs, or sequences. Most prior work requires the training set to consist of complete trees, graphs or sequences. Specifying such detailed ground truth…

Machine Learning · Computer Science 2012-07-03 Xinghua Lou , Fred Hamprecht

Data annotated by humans is a source of knowledge by describing the peculiarities of the problem and therefore fueling the decision process of the trained model. Unfortunately, the annotation process for subjective natural language…

Computation and Language · Computer Science 2023-12-14 Kamil Kanclerz , Julita Bielaniewicz , Marcin Gruza , Jan Kocon , Stanisław Woźniak , Przemysław Kazienko

Recent work has demonstrated that pre-training in-domain language models can boost performance when adapting to a new domain. However, the costs associated with pre-training raise an important question: given a fixed budget, what steps…

Computation and Language · Computer Science 2022-05-16 Fan Bai , Alan Ritter , Wei Xu

Text style transfer is an important task in controllable language generation. Supervised approaches have pushed performance improvement on style-oriented rewriting such as formality conversion. However, challenges remain due to the scarcity…

Computation and Language · Computer Science 2022-05-20 Zhengyuan Liu , Nancy F. Chen

Controlling the patterns a model learns is essential to preventing reliance on irrelevant or misleading features. Such reliance on irrelevant features, often called shortcut features, has been observed across domains, including medical…

Machine Learning · Computer Science 2025-09-23 Mihnea Ghitu , Vihari Piratla , Matthew Wicker

Despite growing interest in incorporating feedback to improve language models, most efforts focus only on sequence-level annotations. In this work, we explore the potential of utilizing fine-grained span-level annotations from offline…

Computation and Language · Computer Science 2024-10-23 Lily H. Zhang , Hamid Dadkhahi , Mara Finkelstein , Firas Trabelsi , Jiaming Luo , Markus Freitag

Neural models trained for next utterance generation in dialogue task learn to mimic the n-gram sequences in the training set with training objectives like negative log-likelihood (NLL) or cross-entropy. Such commonly used training…

Computation and Language · Computer Science 2021-06-22 Prasanna Parthasarathi , Mohamed Abdelsalam , Joelle Pineau , Sarath Chandar

Contextualised word embeddings is a powerful tool to detect contextual synonyms. However, most of the current state-of-the-art (SOTA) deep learning concept extraction methods remain supervised and underexploit the potential of the context.…

Computation and Language · Computer Science 2021-09-07 Jingqing Zhang , Luis Bolanos , Tong Li , Ashwani Tanwar , Guilherme Freire , Xian Yang , Julia Ive , Vibhor Gupta , Yike Guo

Annotated data is an essential ingredient in natural language processing for training and evaluating machine learning models. It is therefore very desirable for the annotations to be of high quality. Recent work, however, has shown that…

Computation and Language · Computer Science 2022-09-27 Jan-Christoph Klie , Bonnie Webber , Iryna Gurevych

Most machine learning and data analytics applications, including performance engineering in software systems, require a large number of annotations and labelled data, which might not be available in advance. Acquiring annotations often…

Software Engineering · Computer Science 2023-09-21 Peter Samoaa , Linus Aronsson , Antonio Longa , Philipp Leitner , Morteza Haghir Chehreghani

Abundant data is the key to successful machine learning. However, supervised learning requires annotated data that are often hard to obtain. In a classification task with limited resources, Active Learning (AL) promises to guide annotators…

Computation and Language · Computer Science 2017-05-09 Markus Borg , Iben Lennerstad , Rasmus Ros , Elizabeth Bjarnason

State-of-the-art natural language understanding classification models follow two-stages: pre-training a large language model on an auxiliary task, and then fine-tuning the model on a task-specific labeled dataset using cross-entropy loss.…

Computation and Language · Computer Science 2021-04-06 Beliz Gunel , Jingfei Du , Alexis Conneau , Ves Stoyanov

Adapting model parameters to incoming streams of data is a crucial factor to deep learning scalability. Interestingly, prior continual learning strategies in online settings inadvertently anchor their updated parameters to a local parameter…

Machine Learning · Computer Science 2022-09-30 Siddhartha Datta , Nigel Shadbolt

Dialogue systems benefit greatly from optimizing on detailed annotations, such as transcribed utterances, internal dialogue state representations and dialogue act labels. However, collecting these annotations is expensive and…

Computation and Language · Computer Science 2019-11-27 Bo-Hsiang Tseng , Marek Rei , Paweł Budzianowski , Richard E. Turner , Bill Byrne , Anna Korhonen