English
Related papers

Related papers: SDA: Steering-Driven Distribution Alignment for Op…

200 papers

When aligning large language models (LLMs), their performance on various tasks (such as being helpful, harmless, and honest) depends heavily on the composition of their training data. However, selecting a data mixture that achieves strong…

Machine Learning · Computer Science 2025-06-03 Nicholas E. Corrado , Julian Katz-Samuels , Adithya Devraj , Hyokun Yun , Chao Zhang , Yi Xu , Yi Pan , Bing Yin , Trishul Chilimbi

Large language models (LLMs) have achieved remarkable progress, with post-training playing a crucial role in enhancing their reasoning capabilities. Among post-training paradigms, supervised fine-tuning (SFT) is widely used: it leverages…

Computation and Language · Computer Science 2026-05-27 Lisong Sun , Li Wang , Chen Zhang , Jinyang Wu , Kui Zhang , Tianhao Peng , Wenjun Wu

Distributional alignment enables large language models (LLMs) to predict how a target population distributes its responses across answer options, rather than collapsing disagreement into a single consensus answer. However, existing…

Machine Learning · Computer Science 2026-03-17 Viet-Thanh Pham , Lizhen Qu , Zhuang Li , Gholamreza Haffari

This paper investigates how Large Language Models (LLMs) represent non-English tokens -- a question that remains underexplored despite recent progress. We propose a lightweight intervention method using representation steering, where a…

Computation and Language · Computer Science 2025-08-27 Omar Mahmoud , Buddhika Laknath Semage , Thommen George Karimpanal , Santu Rana

Large Language Models (LLMs) exhibit strong but shallow alignment: they directly refuse harmful queries when a refusal is expected at the very start of an assistant turn, yet this protection collapses once a harmful continuation is underway…

Machine Learning · Computer Science 2025-10-22 Jiawei Zhang , Andrew Estornell , David D. Baek , Bo Li , Xiaojun Xu

Fine-tuning large language models (LLMs) based on human preferences, commonly achieved through reinforcement learning from human feedback (RLHF), has been effective in improving their performance. However, maintaining LLM safety throughout…

Artificial Intelligence · Computer Science 2025-02-18 Yingshui Tan , Yilei Jiang , Yanshi Li , Jiaheng Liu , Xingyuan Bu , Wenbo Su , Xiangyu Yue , Xiaoyong Zhu , Bo Zheng

LLMs have emerged as powerful evaluators in the LLM-as-a-Judge paradigm, offering significant efficiency and flexibility compared to human judgments. However, previous methods primarily rely on single-point evaluations, overlooking the…

Artificial Intelligence · Computer Science 2025-05-20 Luyu Chen , Zeyu Zhang , Haoran Tan , Quanyu Dai , Hao Yang , Zhenhua Dong , Xu Chen

Large Language Models (LLMs) have demonstrated remarkable adaptability, showcasing their capacity to excel in tasks for which they were not explicitly trained. However, despite their impressive natural language processing (NLP)…

Computation and Language · Computer Science 2023-09-08 Supun Manathunga , Isuru Hettigoda

In high-stakes domains, small task-specific vision models are crucial due to their low computational requirements and the availability of numerous methods to explain their results. However, these explanations often reveal that the models do…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Alexander Koebler , Lukas Kuhn , Ingo Thon , Florian Buettner

Large language models (LLMs) augmented with retrieval systems have significantly advanced natural language processing tasks by integrating external knowledge sources, enabling more accurate and contextually rich responses. To improve the…

Computation and Language · Computer Science 2025-05-28 Xin Sun , Jianan Xie , Zhongqi Chen , Qiang Liu , Shu Wu , Yuehe Chen , Bowen Song , Weiqiang Wang , Zilei Wang , Liang Wang

Diffusion large language models (dLLMs) are emerging as a compelling alternative to dominant autoregressive models, replacing strictly sequential token generation with iterative denoising and parallel generation dynamics. However, their…

Computation and Language · Computer Science 2026-04-07 Jingyi Yang , Yuxian Jiang , Xuhao Hu , Shuang Cheng , Biqing Qi , Jing Shao

Large Language Models (LLMs) are increasingly deployed for clinical reasoning tasks, which inherently require eliciting calibrated probabilistic beliefs based on available evidence. However, real-world clinical data are frequently…

Artificial Intelligence · Computer Science 2026-03-19 Yuta Kobayashi , Vincent Jeanselme , Shalmali Joshi

The black-box nature of large language models (LLMs) poses challenges in interpreting results, impacting issues such as data intellectual property protection and hallucination tracing. Training data attribution (TDA) methods are considered…

Computation and Language · Computer Science 2024-11-20 Kangxi Wu , Liang Pang , Huawei Shen , Xueqi Cheng

Aligning large language models (LLMs) with human objectives is crucial for real-world applications. However, fine-tuning LLMs for alignment often suffers from unstable training and requires substantial computing resources. Test-time…

Artificial Intelligence · Computer Science 2024-11-05 Lingkai Kong , Haorui Wang , Wenhao Mu , Yuanqi Du , Yuchen Zhuang , Yifei Zhou , Yue Song , Rongzhi Zhang , Kai Wang , Chao Zhang

Latent Dirichlet Allocation (LDA) is a prominent generative probabilistic model used for uncovering abstract topics within document collections. In this paper, we explore the effectiveness of augmenting topic models with Large Language…

Computation and Language · Computer Science 2025-07-14 Mengze Hong , Chen Jason Zhang , Di Jiang

Precise control over language model generation is vital for ensuring both safety and reliability. Although prompt engineering and steering are commonly used to intervene in model behaviors, the vast number of parameters in models often…

Computation and Language · Computer Science 2025-06-04 Mengru Wang , Ziwen Xu , Shengyu Mao , Shumin Deng , Zhaopeng Tu , Huajun Chen , Ningyu Zhang

Large Language Models (LLMs) exhibit impressive performance across diverse domains but often suffer from overconfidence, limiting their reliability in critical applications. We propose SteerConf, a novel framework that systematically steers…

Computation and Language · Computer Science 2025-05-27 Ziang Zhou , Tianyuan Jin , Jieming Shi , Qing Li

Large Language Models (LLMs) are typically aligned with human values using preference data or predefined principles such as helpfulness, honesty, and harmlessness. However, as AI systems progress toward Artificial General Intelligence (AGI)…

Computation and Language · Computer Science 2025-12-08 Panatchakorn Anantaprayoon , Nataliia Babina , Jad Tarifi , Nima Asgharbeygi

Aligning Large Language Models (LLMs) traditionally relies on costly training and human preference annotations. Self-alignment seeks to reduce these expenses by enabling models to align themselves. To further lower costs and achieve…

Computation and Language · Computer Science 2024-11-15 Somanshu Singla , Zhen Wang , Tianyang Liu , Abdullah Ashfaq , Zhiting Hu , Eric P. Xing

Training large language models (LLMs) from scratch can yield models with unique functionalities and strengths, but it is costly and often leads to redundant capabilities. A more cost-effective alternative is to fuse existing pre-trained…

Computation and Language · Computer Science 2025-09-23 Runjia Zeng , James Chenhao Liang , Cheng Han , Zhiwen Cao , Jiahao Liu , Xiaojun Quan , Yingjie Victor Chen , Lifu Huang , Tong Geng , Qifan Wang , Dongfang Liu