English
Related papers

Related papers: ConTrans: Weak-to-Strong Alignment Engineering via…

200 papers

Large language models (LLMs) are vulnerable to jailbreak attacks - resulting in harmful, unethical, or biased text generations. However, existing jailbreaking methods are computationally costly. In this paper, we propose the weak-to-strong…

Computation and Language · Computer Science 2025-07-25 Xuandong Zhao , Xianjun Yang , Tianyu Pang , Chao Du , Lei Li , Yu-Xiang Wang , William Yang Wang

While Large Language Models (LLMs) achieve strong performance across diverse tasks, their inference dynamics remain poorly understood because of the limited resolution of existing analysis tools. In this work, we identify an intrinsic…

Artificial Intelligence · Computer Science 2026-05-08 Chengda Lu , Xiaoyu Fan , Wei Xu

Concept Bottleneck Models (CBMs) ground image classification on human-understandable concepts to allow for interpretable model decisions. Crucially, the CBM design inherently allows for human interventions, in which expert users are given…

Machine Learning · Computer Science 2024-08-07 Nishad Singhi , Jae Myung Kim , Karsten Roth , Zeynep Akata

Pretraining large language models (LLMs) on vast and heterogeneous datasets is crucial for achieving state-of-the-art performance across diverse downstream tasks. However, current training paradigms treat all samples equally, overlooking…

Machine Learning · Computer Science 2025-02-11 Daouda Sow , Herbert Woisetschläger , Saikiran Bulusu , Shiqiang Wang , Hans-Arno Jacobsen , Yingbin Liang

Fine-tuning large language models (LLMs) for downstream tasks often leads to catastrophic forgetting, notably degrading the safety of originally aligned models. While some existing methods attempt to restore safety by incorporating…

Computation and Language · Computer Science 2025-08-29 Hua Farn , Hsuan Su , Shachi H Kumar , Saurav Sahay , Shang-Tse Chen , Hung-yi Lee

Pre-trained large language models (LLMs) reflect the inherent social biases of their training corpus. Many methods have been proposed to mitigate this issue, but they often fail to debias or they sacrifice model accuracy. We use…

Computation and Language · Computer Science 2023-11-01 Li S. Yifei , Lyle Ungar , João Sedoc

Human Activity Recognition (HAR) is a core task in pervasive computing systems, where models must operate under strict computational constraints while remaining robust to heterogeneous and evolving deployment conditions. Recent advances…

Machine Learning · Computer Science 2026-05-13 Aleksandr Bredikhin , Philippe Lalanda , German Vega

English, as a very high-resource language, enables the pretraining of high-quality large language models (LLMs). The same cannot be said for most other languages, as leading LLMs still underperform for non-English languages, likely due to a…

Computation and Language · Computer Science 2024-11-07 Jiayi Wang , Yao Lu , Maurice Weber , Max Ryabinin , Yihong Chen , Raphael Tang , Pontus Stenetorp

Large Language Models (LLMs) are highly resource-intensive to fine-tune due to their enormous size. While low-rank adaptation is a prominent parameter-efficient fine-tuning approach, it suffers from sensitivity to hyperparameter choices,…

Diffusion language models (DLMs) have recently demonstrated capabilities that complement standard autoregressive (AR) models, particularly in non-sequential generation and bidirectional editing. Although recent work has shown that…

Machine Learning · Computer Science 2026-05-11 Fred Zhangzhi Peng , Alexis Fox , Anru R. Zhang , Alexander Tong

Automating C-to-Rust migration is critical for improving software security without sacrificing performance. Traditional rule-based methods struggle with diverse C idioms, often producing rigid and unidiomatic Rust code. Large Language…

Software Engineering · Computer Science 2026-04-06 Jia Feng , Wenjie Gan , Cuiyun Gao , Chaozheng Wang , Feng Luo , Xin Xia , Ge Li , Kui Liu

Fine-tuning is a crucial process for adapting large language models (LLMs) to diverse applications. In certain scenarios, such as multi-tenant serving, deploying multiple LLMs becomes necessary to meet complex demands. Recent studies…

Computation and Language · Computer Science 2024-11-27 Bowen Ping , Shuo Wang , Hanqing Wang , Xu Han , Yuzhuang Xu , Yukun Yan , Yun Chen , Baobao Chang , Zhiyuan Liu , Maosong Sun

Taking advantage of the widespread use of ontologies to organise and harmonize knowledge across several distinct domains, this paper proposes a novel approach to improve an embedding-Large Language Model (embedding-LLM) of interest by…

Computation and Language · Computer Science 2024-06-03 Francesco Ronzano , Jay Nanavati

Weight binarization has emerged as a promising strategy to reduce the complexity of large language models (LLMs). Existing approaches fall into post-training binarization, which is simple but causes severe performance loss, and…

Machine Learning · Statistics 2026-04-22 Ba-Hien Tran , Van Minh Nguyen

Modern LLMs struggle with efficient updates, as each new pretrained model version requires repeating expensive alignment processes. This challenge also applies to domain- or languagespecific models, where fine-tuning on specialized data…

Computation and Language · Computer Science 2025-11-07 Pin-Jie Lin , Rishab Balasubramanian , Fengyuan Liu , Nikhil Kandpal , Tu Vu

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing (NLP) tasks, such as question-answering, sentiment analysis, text summarization, and machine…

Machine Learning · Computer Science 2024-08-05 Afia Anjum , Maksim E. Eren , Ismael Boureima , Boian Alexandrov , Manish Bhattarai

Learning to rank (LTR) plays a crucial role in various Information Retrieval (IR) tasks. Although supervised LTR methods based on fine-grained relevance labels (e.g., document-level annotations) have achieved significant success, their…

Information Retrieval · Computer Science 2025-08-21 Yiteng Tu , Zhichao Xu , Tao Yang , Weihang Su , Yujia Zhou , Yiqun Liu , Fen Lin , Qin Liu , Qingyao Ai

In this paper we introduce ShiftCNN, a generalized low-precision architecture for inference of multiplierless convolutional neural networks (CNNs). ShiftCNN is based on a power-of-two weight representation and, as a result, performs only…

Computer Vision and Pattern Recognition · Computer Science 2017-06-09 Denis A. Gudovskiy , Luca Rigazio

Multilingual large language models (LLMs) seem to generalize somewhat across languages. We hypothesize this is a result of implicit vector space alignment. Evaluating such alignment, we see that larger models exhibit very high-quality…

Computation and Language · Computer Science 2024-10-03 Qiwei Peng , Anders Søgaard

Pre-trained language models (PLMs) have been prevailing in state-of-the-art methods for natural language processing, and knowledge-enhanced PLMs are further proposed to promote model performance in knowledge-intensive tasks. However,…

Computation and Language · Computer Science 2024-01-12 Xintao Wang , Zhouhong Gu , Jiaqing Liang , Dakuan Lu , Yanghua Xiao , Wei Wang